JP6915673B2 - Information processing system - Google Patents

Description

The present invention relates to an information processing system, a program, and an information processing method.

As a means of restricting or managing people who enter or leave a specific place such as an office or an event venue, a collation system is used to check whether or not the person who is going to pass is a pre-registered person. In particular, in recent years, with the development of human face recognition technology, a walk-through face recognition system that performs face recognition from a person's face image taken by a camera installed at a gate has been used.

Japanese Unexamined Patent Publication No. 2016-083225

Here, in the walk-through face recognition system, it is necessary to open and close the gate by collating the people lined up at the gate in order so that the person can pass through the gate smoothly. However, there are various people who try to pass through the gate, and it is difficult to properly determine the order. As a result, there arises a problem that it is difficult to pass through the gate smoothly.

Therefore, an object of the present invention is to solve the above-mentioned problem that it is difficult to smoothly pass through the gate.

The information processing device, which is one embodiment of the present invention, is
A collation means that performs collation processing between the target in the captured image obtained by capturing the area before passing through the gate and the pre-registered target.
A distance estimation means for estimating the distance from the gate to the target in the captured image using a reference value set based on the attribute of the target in the captured image, and
A gate control means that controls the opening and closing of the gate based on the collation result and the estimated distance to the target in the captured image.
With,
It takes the configuration.

Further, the information processing system, which is one form of the present invention, is
An imaging means that acquires a captured image of the pre-passage area with respect to the gate,
A collation means that performs collation processing between the object in the captured image and the object registered in advance, and
A distance estimating means for estimating the distance from the gate to the target in the captured image using a reference value set based on the attribute of the object in the captured image is provided.
A gate control means that controls the opening and closing of the gate based on the collation result and the estimated distance to the target in the captured image.
With,
It takes the configuration.

Further, the program which is one form of the present invention is
For information processing equipment
A collation means that performs collation processing between the target in the captured image obtained by capturing the area before passing through the gate and the pre-registered target.
A distance estimation means for estimating the distance from the gate to the target in the captured image using a reference value set based on the attribute of the target in the captured image, and
A gate control means that controls the opening and closing of the gate based on the collation result and the estimated distance to the target in the captured image.
To realize,
It takes the configuration.

Further, the information processing method, which is one form of the present invention, is
In addition to performing collation processing between the target in the captured image of the area before passing through the gate and the pre-registered target,
The distance from the gate to the target in the captured image is measured using the reference value set based on the attribute of the target in the captured image.
The opening and closing of the gate is controlled based on the collation result and the measured distance to the target in the captured image.
It takes the configuration.

The present invention can provide an information processing system capable of realizing smooth passage of a gate by being configured as described above.

It is a figure which shows the usage situation of the face recognition system in Embodiment 1 of this invention. It is a block diagram which shows the structure of the face recognition system in Embodiment 1 of this invention. It is a figure which shows the imaging state by the face recognition system disclosed in FIG. It is a figure which shows the usage situation of the face recognition system disclosed in FIG. It is a flowchart which shows the processing operation by the face recognition system disclosed in FIG. It is a flowchart which shows the processing operation by the face recognition system in Embodiment 2 of this invention. It is a block diagram which shows the structure of the information processing system in Embodiment 3 of this invention. It is a block diagram which shows the structure of the information processing apparatus in Embodiment 3 of this invention.

<Embodiment 1>
The first embodiment of the present invention will be described with reference to FIGS. 1 to 5. FIG. 1 is a diagram showing a usage status of the face recognition system. FIG. 2 is a diagram showing a configuration of a face recognition system. 3 to 5 are diagrams for explaining the processing operation of the face recognition system.

[overall structure]
The face recognition system 10 (information processing system) in the present invention is a system used for restricting or managing the entry and exit of a person (target) in a specific place such as an office or an event venue. For example, the imaging device C constituting the face recognition system 10 is installed near each gate that is opened and closed when a person enters and exits, in the vicinity of the gate.

In the example shown in FIG. 1, a plurality of gates G are arranged adjacent to each other in parallel, and a person passes in the direction indicated by the arrow from the right side of FIG. 1 toward each gate G. Therefore, the region on the right side of FIG. 1 with respect to each gate G is a region on the front side where a person passes through the gate (region on the front side of passage). Then, in the area before passing through each gate G, each lane through which a person who intends to pass through each gate G passes side by side is located in parallel corresponding to each gate G. Each lane may or may not be partitioned by some member. Further, in the present embodiment, a case where a plurality of gates G are arranged adjacent to each other is illustrated, but only one gate G may be used.

In the situation shown in FIG. 1, the image pickup apparatus C constituting the face recognition system 10 in the present embodiment is near each corresponding gate G and is installed on the right side when viewed from a person facing each gate G. However, the installation position of the image pickup device is not limited to the position shown in FIG. 1, and may be installed at any position such as the left side of the gate or above the gate. The face recognition system 10 also includes a display device D in the vicinity of each image pickup device C.

Then, the face recognition system 10 takes an image of a person heading for the gate G with the equipped image pickup device C. Then, it is collated from the face image of the person reflected in the photographed image whether or not the person is a pre-registered person, and if the collation is successful, the gate G is opened so that the person can pass through. Hereinafter, the configuration of the face recognition system 10 will be described in detail.

[Face recognition system configuration]
The face recognition system 10 in the present embodiment is an information processing device having an arithmetic device and a storage device integrally configured with an image pickup device C (camera) and a display device D (display). Conversely, the image pickup device C is equipped with an information processing device and a display device D having a calculation device and a storage device that perform face recognition processing. However, the face recognition system 10 is not necessarily limited to being integrally configured with the image pickup device C and the display device D. For example, the image pickup device C, the display device D, and the information processing device for processing the captured image are configured by separate devices, and may be installed at different locations.

Specifically, as shown in FIG. 2, the face recognition system 10 includes an image pickup device C and a display device D, and has a reference value setting unit 11 constructed by an arithmetic unit executing a program and a distance measurement. A unit 12, a collating unit 13, and a gate control unit 14 are provided. Further, the face recognition system 10 includes a reference value storage unit 15 and a collation data storage unit 16 built in the storage device.

The imaging device C (imaging means) includes a camera and a camera control unit that acquire a captured image of a region on the front side of passage with respect to the gate G, that is, a region in front of the gate of the corresponding lane at a predetermined frame rate. Then, in the image pickup apparatus C, for example, as shown in FIG. 1, the range sandwiched by the reference numeral Ca line is the photographing region. For example, when three persons P10, P11, and P12 are present in the lane as shown in FIG. 1, the captured image taken by the imaging device C is as shown in FIG. 3A. The captured image is set so as to be substantially in focus within a range of a preset distance in the perspective direction with respect to the image pickup apparatus C.

The reference value setting unit 11 (distance estimation means) acquires a photographed image from the image pickup apparatus C and sets the reference value necessary for measuring the distance to the target in the photographed image as follows. do. Specifically, the reference value setting unit 11 first extracts an image portion of the face region of the person to be processed from the captured image. The extraction of the face area of a person is performed by, for example, determining from the position and color of the moving person with respect to the whole image. Then, the reference value setting unit 11 performs an attribute analysis process for determining the attribute of the person from the image portion of the face area. Here, the attributes of a person are, for example, gender, age (age, adult, child), race, and the like.

In the above attribute analysis process, for example, the attribute discrimination information which is the information necessary for discriminating the attribute is extracted from the image portion of the face area, and the extracted attribute discrimination information and the pre-registered attribute discrimination reference information are combined. Compare and determine the attributes of the person. Here, the attribute discrimination information is information representing physical characteristics that generally appear in a person's face region for each attribute such as gender and age. Since the attribute analysis process for determining attributes such as the gender and age (age) of a person can be realized by existing technology, details of such process will be omitted. Further, the distinguishable attribute is not limited to the above-mentioned attribute, and may be any attribute.

Subsequently, the reference value setting unit 11 sets a reference value corresponding to the attribute of the determined person. Here, the reference value is registered in advance in the reference value storage unit 15. For example, in the present embodiment, the reference value of the inter-eye distance representing the distance between both eyes of a person is registered for each attribute. .. As an example, when a certain numerical value is registered as the standard value of the attribute such as "male", the distance between the eyes, which is the standard value of the attribute such as "female", is smaller than the standard value of male. Is set. In addition, for example, when a certain numerical value is registered as the inter-eye distance, which is the reference value of the attribute such as "adult" whose age is from 15 years old to 70s, the reference value of the attribute such as "children" whose age is less than 15 years old. The inter-eye distance, which is a value, is set to a value smaller than the standard value for adults. In this way, the reference value is a value corresponding to the general physique of the person's attribute. Then, the reference value setting unit 11 sets the reference value registered corresponding to the attribute determined for the person extracted from the captured image as the reference value of the person.

The distance measuring unit 12 (distance estimating means) measures the distance to the person using the reference value set for the person as described above. Specifically, the distance measuring unit 12 first detects the inter-eye distance representing the distance between both eyes of the person from the image portion of the face region of the person as the target information representing the characteristics of the person in the captured image. For example, as shown by the symbols d10, d11, and d12 in FIG. 3B, the distance between each eye of each person P10, P11, and P12 in the captured image is detected. Then, the detected inter-eye distances d10, d11, d12 are compared with the reference values set for each person P10, P11, P12, and the distance from the gate G to each person is measured. For example, the distance from the gate G to the person is measured from the difference in the distance between the eyes detected from the person and the ratio of the difference with respect to the reference value set for the person. The distance measuring unit 12 may measure the relative distance of the person in the captured image, that is, the order with respect to the gate G, as the distance to the gate G.

Here, an example of distance measurement from the gate G to the persons P10, P11, and P12 will be described. In the example of FIG. 1, the persons P10, P11, and P12 are arranged in this order toward the gate G, and the captured image is taken as shown in FIG. 3 (b). At this time, if the physique and face size of each person P10, P11, P12 are almost the same, the inter-eye distances d10, d11, d12 of each person P10, P11, P12 are generally d10> d11>. It becomes d12. On the other hand, if the person P10 is a child and the people P11 and P12 are adults, it is generally considered that the child's face is small and the eye-to-eye distance is short, and the actually measured eye-to-eye distance is also It becomes d11> d12> d10. In such a situation, in the present embodiment, the attribute of the person P10 is determined to be "child", a reference value of a small value is set, and the distance is measured using the reference value and the detected inter-eye distance d10. NS. Then, the attributes of the persons P11 and P12 are determined to be "adults", a reference value having a value larger than the reference value of the child is set, and the distance is measured using the reference value and the detected inter-eye distances d11 and d12. Will be done. As a result, as shown in FIG. 4, the distances D10, D11, and D12 to each person can be measured so as to be in the order of the persons P10, P11, and P12 in the same order as the actual order with respect to the gate G.

The method of detecting the inter-eye distance by the distance measuring unit 12 is not limited to the above-mentioned method, and any method may be used for detection. Further, the distance measuring unit 12 may measure the distance by detecting the size of another part of the person and other features as the target information instead of the distance between the eyes. In this case, the above-mentioned reference value also becomes a value corresponding to the target information.

Here, the distance measuring unit 12 is not necessarily limited to measuring the distance from the gate G to the person. For example, the distance measuring unit 12 may estimate the relative positional relationship between people with respect to the gate. As an example, the distance measuring unit 12 may estimate the proximity of each person to the gate, that is, the perspective relationship between the persons with respect to the gate G, based on the target information such as the inter-eye distance and the reference value described above. good.

The collation unit 13 (verification means) performs collation processing between the person in the captured image and the person registered in advance. At this time, the collation unit 13 performs the collation process based on the distance to the person measured as described above. For example, in the collation unit 13, a person is located in a predetermined range located at a preset distance from the gate G set immediately before the gate G, and the person is located closest to the gate G in the captured image. When doing so, the collation process of such a person is performed. The collation unit 13 may perform collation processing of such a person when the person is located in a predetermined range located at a preset distance from the gate G set immediately before the gate G. Alternatively, the matching process of the person may be performed based on other criteria according to the distance to the person. Further, when the distance measuring unit 12 estimates only the relative positional relationship between the persons with respect to the gate G as described above, the collating unit 13 refers to the person closest to the gate G from such a positional relationship. The collation process may be performed.

The collation process by the collation unit 13 is performed as follows, for example. First, the feature amount required for collation is generated from the face area of the person to be collated. Then, a collation score such as the degree of similarity between the generated feature amount and the feature amount of the person registered in the collation data storage unit 16 in advance is calculated, and it is determined whether or not the collation score is higher than the threshold value. If the collation score is higher than the threshold value, it is considered that the collation is successful, and it is determined that the person who is going to pass through the gate G is a pre-registered person. At this time, the feature amount of the person detected for collation may be the feature amount used in the existing face matching technique, or may be the feature amount calculated by any method. Moreover, the collation method may be any method.

The gate control unit 14 (gate control means) first determines whether or not a person can pass through the gate G based on the collation result by the collation unit 13. Specifically, it is determined that a person who has succeeded in collation by the collation unit 13 can pass through. Further, the gate control unit 14 has a function of displaying the collation result, that is, the success or failure of the collation on the display device D. Further, the gate control unit 14 also has a gate control function for opening and closing the gate G, and controls the person who is determined to be able to pass the gate G to open the gate G. In this way, the gate control unit 14 controls the opening and closing of the gate G according to the result of the collation process performed based on the distance to the gate G of the person, and therefore is based on the measured distance to the person in the captured image. It can be said that the opening and closing of the gate G is controlled.

The display device D is arranged so that a person who is going to pass through the gate G can see the display device D so that the display surface faces the region on the front side of the gate G. However, the display device D does not necessarily have to be equipped.

[motion]
Next, the operation of the face recognition system 10 described above will be described with reference to the flowchart of FIG. Here, the operation of the face recognition system 10 corresponding to the gate G will be described, and a case where people are lined up with respect to the gate G as shown in FIGS. 3 and 4 will be described as an example.

The imaging device C corresponding to the gate G continues to capture an image of the region before passing through the gate G. Then, the face recognition system 10 always performs the following processing on the captured image.

First, the reference value setting unit 11 extracts the persons (targets) P10, P11, and P12 to be processed from the captured image (step S1). Then, the attribute analysis process is performed on the image portion of the extracted face area of the person to determine the attribute of the person. For example, in the examples of FIGS. 1 and 3, it is assumed that the attribute of the person P10 is determined to be a child and the attributes of the persons P11 and P12 are determined to be an adult. Then, the reference value setting unit 11 sets the reference value registered in the reference value storage unit 15 corresponding to the attribute of the determined person as the reference value of the person (step S2). For example, in the examples of FIGS. 3 and 4, the person P10 is set with a reference value corresponding to a child, and the persons P11 and P12 are set with a reference value corresponding to an adult.

Subsequently, the distance measuring unit 12 determines the size of a predetermined portion that is characteristic of the person as the target information necessary for measuring the distance of the person to the gate G in the captured image, in this case, the distance between the eyes of the person. Is detected (step S3). For example, the inter-eye distances of the persons P10, P11, and P12 are detected as shown by the symbols d10, d11, and d12 in FIG. 3B.

Then, the distance measuring unit 12 compares the reference values set for each person P10, P11, P12 as described above with the inter-eye distances d10, d11, d12 of each person P10, P11, P12 for each person. Then, the distance from the gate G to each person P10, P11, P12 is measured (step S4). For example, in the example of FIG. 3B, the eye distance d11 of the person P11 is the second largest from the gate among the three people, but the reference values set for each person P10, P11, and P12 are different. Therefore, the distances D10, D11, and D12 to each person are measured so as to be in the order of the persons P10, P11, and P12 as shown in FIG. 4, as in the actual order with respect to the gate G.

Subsequently, the collation unit 13 performs collation processing of each person based on the distances to each person P10, P11, P12 measured as described above. At this time, the collation unit 13 determines that the person is located at a preset distance from the gate G set immediately before the gate G, and the person is located closest to the gate G in the captured image. The collation process of such a person is performed (step S5, step S6). Therefore, in the example of FIG. 4, the collation process of the person P10 is performed. Specifically, the collation unit 13 generates a feature amount necessary for collation from the face area of the person to be collated, and the generated feature amount and the person registered in the collation data storage unit 16 in advance. The matching score such as the similarity between the feature amount and the feature amount is calculated. Then, when the collation score is higher than the threshold value, the collation unit 13 determines that the collation is successful.

As a result of the collation process by the collation unit 13, when the collation of the person P10 located immediately before the gate G is successful (Yes in step S6), the gate control unit 14 permits the person P10 to pass through the gate G and opens the gate G. (Step S7). At this time, the gate control unit 14 displays the passability on the display device D.

If the collation by the collation unit 13 fails (No in step S6), the gate control unit 14 keeps the gate closed. Information may be displayed. For example, when it is determined that the quality of the above-mentioned feature amount required for collation is low (the quality of the face image is low) during the collation process by the collation unit 13, the feature amount of the quality required for collation can be obtained. Guide information such as may be displayed. The guide information is, for example, information such as "Please remove the mask" and "Please face the front".

As described above, according to the face recognition system 10 of the present embodiment, even when a person having various attributes is trying to pass through the gate G, the order of the person with respect to the gate G can be appropriately determined. It is possible to collate the person immediately before the gate and open / close the gate. For example, in the examples of FIGS. 3 and 4, there is a possibility that the person P11 actually located second from the gate G is erroneously determined to be the closest to the gate G based on the size of the person shown in the captured image. .. However, in the method of the present embodiment, the collation process for the person P10 closest to the gate G can be actually performed. As a result, the smooth passage of the gate G by a person can be realized.

The above-mentioned process of discriminating the attributes of a person and the process of measuring a distance are processes that place less load on the information processing device than the collation process of extracting and collating the feature amount of a person. Therefore, high-speed collation processing can be maintained, and smooth passage of the gate G by a person can be realized.

In the above, the case where the object passing through the gate G is a person is illustrated, but the object is not limited to the person and may be any object. For example, it may be an object such as luggage. Correspondingly, the information used for measuring the distance from the gate G, such as the above-mentioned reference value and the target information representing the feature of the target, may be information representing any feature that can be detected from the object. Further, when performing the collation process, any feature amount that can be detected from the object may be used.

<Embodiment 2>
Next, a second embodiment of the present invention will be described with reference to FIG. FIG. 6 is a diagram for explaining the processing operation of the face recognition system.

The face recognition system 10 in the present embodiment has the same configuration as that in the above-described first embodiment, but the process of setting the reference value is different depending on the attribute of the person. Hereinafter, the configuration different from that of the first embodiment will be mainly described in detail.

When the captured image is captured by the imaging device C, the collating unit 13 (collation means) in the present embodiment extracts a person in the captured image and first performs collating processing of the person. Specifically, the collation unit 13 extracts a person in the captured image, sets all the extracted people as collation targets, and generates a feature amount necessary for collation from the face area of the person. Then, a collation score such as the degree of similarity between the generated feature amount and the feature amount of the person registered in the collation data storage unit 16 in advance is calculated, and if the collation score is higher than the threshold value, the collation is successful.

When the collation is successful, the collation unit 13 acquires the information of the person registered in the collated collation data storage unit 16 and reads the attribute of the person included in the information of the person. Then, the collation unit 13 passes the read attribute to the reference value setting unit 11. The collation data storage unit 16 stores information on the attributes (gender, age, etc.) of the person that has been determined in advance, as well as the feature amount of the person used in the collation process.

Further, the reference value setting unit 11 (distance estimation means) in the present embodiment determines the attribute of the person in the captured image from the result of the collation process by the collation unit 13. That is, the reference value setting unit 11 determines the attribute of the registered person passed from the collation unit 13 as the attribute of the person in the captured image as described above. Then, the reference value setting unit 11 sets the reference value registered in the reference value storage unit 15 corresponding to the attribute of the determined person as the reference value of the person.

Then, the distance measuring unit 12 (distance estimating means) in the present embodiment measures the distance to the person using the reference value set for the person, as in the first embodiment. Specifically, the distance measuring unit 12 detects the inter-eye distance from the person in the captured image, compares the detected inter-eye distance with the reference value set for the person, and compares the distance between the gate G and each person. To measure. At this time, the distance measuring unit 12 associates each person in the captured image with the fact that the matching unit 13 has determined that the matching is successful and the measured distance. The distance measuring unit 12 measures the distance to the person in the photographed image each time the photographed image is acquired, and updates the distance associated with the person on the photographed image. It should be noted that the association of people in the captured images that are back and forth in time can be realized by tracking feature points and the like. Therefore, if a person in the captured image is successfully collated even once, the person is tracked in the subsequent captured image, and the fact that the collation is successful is associated with the updated distance.

Then, the gate control unit 14 (gate control means) in the present embodiment controls the opening and closing of the gate G based on the distance associated with the person in the captured image. That is, the gate control unit 14 already associates the person in the captured image with the fact that the collation is successful, and the distance associated with the person is preset from the gate G set immediately before the gate G. If it is within a predetermined range located at a set distance and the person is located closest to the gate G in the captured image, it is determined that the person can pass through. Then, the gate control unit 14 displays the collation result, that is, the success of the collation on the display device D, and controls to open the gate G. In this way, the gate control unit 14 controls the opening and closing of the gate G based on the distance of the person to the gate G in the captured image.

The gate control unit 14 may instruct the collation unit 13 again to perform the final collation process on the person in the captured image located immediately before the gate G. Then, the gate control unit 14 may open the gate G only when the final collation process is successful.

Here, although the collation was successful as a result of the collation process by the collation unit 13 described above, the attributes of the person in the captured image cannot be discriminated due to circumstances such as the attributes of the person not being registered in the collation data storage unit 16. In some cases. In that case, first, as in the first embodiment, the reference value setting unit 11 performs attribute analysis processing on the image portion of the person in the captured image to determine the attribute of the person, and the reference value corresponding to the attribute. To set. Then, the distance measuring unit 12 measures the distance to the person using the set reference value, and the gate control unit 14 controls the opening and closing of the gate based on the processing result of the collation process.

Even if the collation of the person in the captured image fails as a result of the collation process by the collation unit 13 described above, the reference value setting unit 11 determines the attribute of the person as in the first embodiment. , The distance to the person may be measured by the distance measuring unit 12. Then, by associating the fact of collation failure and the distance with the same person tracked in the subsequent captured image, the gate control unit 14 can perform when the person is positioned immediately before the gate G based on such information. It may be determined that the vehicle is impassable. At this time, the gate control unit 14 may display the guide information for the above-mentioned passage.

[motion]
Next, the operation of the face recognition system 10 described above will be described with reference to the flowchart of FIG. The imaging device C corresponding to the gate G continues to capture an image of the region before passing through the gate G. Then, the face recognition system 10 always performs the following processing on the captured image.

First, the collation unit 13 extracts a person (target) to be processed from the captured image (step S11). The collation unit 13 targets all the persons extracted from the captured image as the collation target, and generates the feature amount necessary for the collation from the face area of the person. Then, a collation score such as the degree of similarity between the generated feature amount and the feature amount of the person registered in the collation data storage unit 16 in advance is calculated, and the collation process is performed (step S12).

When the collation is successful (Yes in step S13), the collation unit 13 acquires the information of the person registered in the collated collation data storage unit 16 and includes the person's information included in the information of the person. Read the attribute (step S14). If the attribute of the person can be read (Yes in step S14), the reference value setting unit 11 determines the read attribute as the attribute of the person in the captured image. Then, the reference value setting unit 11 sets the reference value registered in the reference value storage unit 15 corresponding to the attribute of the determined person as the reference value of the person (step S15).

Subsequently, the distance measuring unit 12 determines the size of a predetermined portion that is characteristic of the person as the target information necessary for measuring the distance of the person to the gate G in the captured image, in this case, the distance between the eyes of the person. Is detected (step S16). Then, the distance measuring unit 12 compares the reference value set for the person with the eye-to-eye distance of the person as described above, and measures the distance from the gate G to the person (step S17). At this time, the distance measuring unit 12 associates the measured distance with the person in the captured image.

Subsequently, the gate control unit 14 determines that the distance of the person in the captured image is within the range of the set distance immediately before the gate, and the person is located closest to the gate G in the captured image. Controls to open the gate G (step S18). The distance to the person is always measured by the distance measuring unit 12 described above, and the latest distance is associated with the person in the captured image that has been successfully collated. Therefore, the gate control unit 14 controls to open the gate G every time the distance associated with the person who succeeded in collation is located at the set distance immediately before the gate.

Here, after the above-mentioned collation is successful (Yes in step S13), if the attribute of the person cannot be determined such as the attribute of the person is not registered in the collation data storage unit 16 (No in step S14), the reference value is set. The unit 11 sets the reference value of the person as in the first embodiment. That is, the reference value setting unit 11 extracts a person to be processed from the captured image, performs attribute analysis processing on the image portion of the face area of the extracted person, and determines the attribute of the person. Then, the reference value setting unit 11 sets the reference value registered in the reference value storage unit 15 corresponding to the attribute of the determined person as the attribute of the person (step S19).

After that, using the set reference value, the distance measuring unit 12 measures the distance to the gate G of the person in the captured image in the same manner as described above (steps S16 and S17). Then, when the gate control unit 14 indicates that the distance of the person in the captured image is within the range of the set distance immediately before the gate and the person is located closest to the gate G in the captured image. , Control to open the gate G (step S18).

As described above, in the face recognition system 10 of the present embodiment, unlike the first embodiment, the person is first collated, and then the gate G is opened according to the distance to the gate G of the person. There is. Therefore, when a person approaches the gate G, the gate G can be opened appropriately, and the person can smoothly pass through the gate G.

<Embodiment 3>
Next, a third embodiment of the present invention will be described with reference to FIGS. 7 and 8. FIG. 7 is a block diagram showing the configuration of the information processing system according to the third embodiment. FIG. 8 is a block diagram showing the configuration of the information processing apparatus according to the third embodiment. In this embodiment, the outline of the configuration of the face recognition system described in the first and second embodiments is shown.

As shown in FIG. 7, the information processing system 100 in this embodiment is
An imaging means 110 that acquires a captured image of a region before passing through the gate, and
A collation means 120 that performs collation processing between the object in the captured image and the object registered in advance, and
A distance estimating means 130 for measuring the distance from the gate to the target in the captured image using a reference value set based on the attribute of the target in the captured image, and
A gate control means 140 that controls the opening and closing of the gate based on the collation result and the estimated distance to the target in the captured image.
It is configured to be equipped with.

Further, in the present embodiment, the image pickup means 110 may be removed from the information processing system 100 shown in FIG.
That is, the information processing device 200 in this embodiment is
A collation means 220 that performs collation processing between the target in the captured image obtained by capturing the area before passing through the gate and the pre-registered target.
A distance estimation means 230 that estimates the distance to the target in the captured image using a reference value set based on the attributes of the target in the captured image, and
The gate control means 240 that controls the opening and closing of the gate based on the collation result and the estimated distance to the target in the captured image, and
It is configured to be equipped with.

The collation means 120, 220, the distance estimation means 130, 230, and the gate control means 140, 240 described above may be constructed by executing a program by the arithmetic unit, and may be constructed by an electronic circuit. It may be one.

Then, the information processing system 100 or the information processing device 200 having the above configuration is
In addition to performing collation processing between the target in the captured image of the area before passing through the gate and the pre-registered target,
The distance from the gate to the target in the captured image is estimated using the reference value set based on the attribute of the target in the captured image.
The opening and closing of the gate is controlled based on the collation result and the estimated distance to the target in the captured image.
It works to perform the process.

According to the information processing system 100 or the information processing device 200 described above, even when a person with various attributes is trying to pass through the gate, the order of the persons with respect to the gate can be appropriately determined, and the person immediately before the gate can be determined. It is possible to collate with and open / close the gate. As a result, smooth passage of the gate by a person can be realized.

<Additional notes>
Part or all of the above embodiments may also be described as in the appendix below. Hereinafter, the outline of the configuration of the information processing device, the information processing system, the program, and the information processing method in the present invention will be described. However, the present invention is not limited to the following configurations.

(Appendix 1)
A collation means that performs collation processing between the target in the captured image obtained by capturing the area before passing through the gate and the pre-registered target.
A distance estimation means for estimating the distance to the target in the captured image using a reference value set based on the attribute of the target in the captured image, and
A gate control means that controls the opening and closing of the gate based on the collation result and the estimated distance to the target in the captured image.
Information processing device equipped with.

(Appendix 2)
The information processing device according to Appendix 1.
The collation means performs the collation process based on the distance to the target in the estimated captured image, and then performs the collation process.
The gate control means controls the opening and closing of the gate based on the processing result of the collation process performed based on the distance to the target in the captured image.
Information processing device.

(Appendix 3)
The information processing device described in Appendix 2
The distance estimating means determines the attribute of the target based on the attribute analysis process for the image portion of the target in the captured image, sets the reference value corresponding to the attribute, and sets the set reference value. To estimate the distance to the object in the captured image,
Information processing device.

(Appendix 4)
The information processing device according to Appendix 1.
The distance estimating means discriminates the attribute of the target registered in advance from the result of the collation process as the attribute of the target in the captured image, sets the reference value corresponding to the attribute, and sets the set reference. The value is used to estimate the distance to the object in the captured image.
Information processing device.

(Appendix 5)
The information processing device according to Appendix 4,
When the distance estimation means cannot determine the attribute of the target in the captured image from the result of the collation process, the distance estimating means determines the attribute of the target based on the attribute analysis process for the image portion of the target in the captured image. Then, the reference value corresponding to the attribute is set, and the distance to the target in the captured image is estimated using the set reference value.
Information processing device.

(Appendix 6)
The information processing device according to any one of Appendix 1 to 5.
The distance estimating means detects target information representing the characteristics of the target in the captured image, and estimates the distance to the target in the captured image based on the reference value and the target information.
Information processing device.

(Appendix 7)
The information processing device according to Appendix 6.
The distance estimation means detects the size of a predetermined portion of the target in the captured image as the target information, and reaches the target in the captured image based on the size of the predetermined portion of the target with respect to the reference value. Estimate the distance,
Information processing device.

(Appendix 8)
The information processing device according to Appendix 7.
The distance estimation means mutually compares the size of a predetermined portion of the target with respect to the reference value set corresponding to the target for each target in the same captured image, and the target with respect to the gate. Determine the perspective relationship between objects in the image,
Information processing device.

(Appendix 9)
The information processing device according to any one of Supplementary note 1 to 8.
The gate control means controls the opening and closing of the gate based on the collation result of the collation means for the target and the distance from the gate to the target, which are associated with each other with respect to the target in the captured image. do,
Information processing device.

(Appendix 10)
An imaging means that acquires a captured image of the pre-passage area with respect to the gate,
A collation means that performs collation processing between the object in the captured image and the object registered in advance, and
A distance estimation means for estimating the distance from the gate to the target in the captured image using a reference value set based on the attribute of the target in the captured image, and
A gate control means that controls the opening and closing of the gate based on the collation result and the estimated distance to the target in the captured image.
Information processing system equipped with.

(Appendix 10.1)
The information processing system according to Appendix 10.
The collation means performs the collation process based on the distance to the target in the estimated captured image, and then performs the collation process.
The gate control means controls the opening and closing of the gate based on the processing result of the collation process performed based on the distance to the target in the captured image.
Information processing system.

(Appendix 10.2)
The information processing device according to Appendix 10.
The distance estimating means discriminates the attribute of the target registered in advance from the result of the collation process as the attribute of the target in the captured image, sets the reference value corresponding to the attribute, and sets the set reference. The value is used to estimate the distance to the object in the captured image.
Information processing system.

(Appendix 11)
For information processing equipment
A collation means that performs collation processing between the target in the captured image obtained by capturing the area before passing through the gate and the pre-registered target.
A distance estimation means for estimating the distance to the target in the captured image using a reference value set based on the attribute of the target in the captured image, and
A gate control means that controls the opening and closing of the gate based on the collation result and the estimated distance to the target in the captured image.
A program to realize.

(Appendix 11.1)
The program described in Appendix 11
The collation means performs the collation process based on the distance to the target in the estimated captured image, and then performs the collation process.
The gate control means controls the opening and closing of the gate based on the processing result of the collation process performed based on the distance to the target in the captured image.
program.

(Appendix 11.2)
The program described in Appendix 11
The distance estimating means discriminates the attribute of the target registered in advance from the result of the collation process as the attribute of the target in the captured image, sets the reference value corresponding to the attribute, and sets the set reference. The value is used to estimate the distance to the object in the captured image.
program.

(Appendix 12)
A collation process is performed between the target in the captured image obtained by capturing the area before passing through the gate and the pre-registered target.
The distance to the target in the captured image is measured using the reference value set based on the attribute of the target in the captured image.
The opening and closing of the gate is controlled based on the collation result and the estimated distance to the target in the captured image.
Information processing method.

(Appendix 13)
The information processing method described in Appendix 12
The collation process is performed based on the distance to the target in the estimated captured image, and the collation process is performed.
The opening and closing of the gate is controlled based on the processing result of the collation process performed based on the distance to the target in the captured image.
Information processing method.

(Appendix 13.1)
The information processing method described in Appendix 13
The attribute of the target is determined based on the attribute analysis process for the image portion of the target in the captured image, and the reference value corresponding to the attribute is set.
Information processing method.

(Appendix 14)
The information processing method described in Appendix 12
From the result of the collation process, the attribute of the target registered in advance is determined as the attribute of the target in the captured image, the reference value corresponding to the attribute is set, and the reference value is set.
Using the reference value, the distance to the target in the captured image is estimated.
Controlling the opening and closing of the gate based on the distance to the object in the captured image.
Information processing method.

(Appendix 15)
The information processing method described in Appendix 14,
When the attribute of the target in the captured image cannot be determined from the result of the collation process, the attribute of the target is determined based on the attribute analysis process for the image portion of the target in the captured image, and the attribute is set to the attribute. Set the corresponding reference value and set
Using the reference value, the distance to the target in the captured image is estimated.
Controlling the opening and closing of the gate based on the distance to the object in the captured image.
Controls the opening and closing of the gate,
Information processing method.

(Appendix 15.1)
The information processing method according to any one of Supplementary note 12 to 15.
Target information representing the characteristics of the target in the captured image is detected, and the distance to the target in the target image is measured based on the reference value and the target information.
Information processing method.

(Appendix 15.2)
The information processing method according to Appendix 15.1
The size of a predetermined portion of the target in the captured image is detected as the target information, and the distance to the target in the target image is measured based on the size of the predetermined portion of the target with respect to the reference value.
Information processing method.

(Appendix 15.3)
The information processing method described in Appendix 15.2.
For each object in the same captured image, the size of a predetermined portion of the target with respect to the reference value set corresponding to the object is compared with each other, and between the objects in the captured image with respect to the gate. Judging the perspective relationship,
Information processing method.

The above-mentioned program is stored in a storage device or recorded on a computer-readable recording medium. For example, the recording medium is a portable medium such as a flexible disk, an optical disk, a magneto-optical disk, and a semiconductor memory.

Although the invention of the present application has been described above with reference to the above-described embodiment and the like, the present invention is not limited to the above-described embodiment. Various changes that can be understood by those skilled in the art can be made to the structure and details of the present invention within the scope of the present invention.

10 Face recognition system 11 Reference value setting unit 12 Distance measurement unit 13 Verification unit 14 Gate control unit 15 Reference value storage unit 16 Verification data storage unit 100 Information processing system 200 Information processing device 110 Imaging means 120, 220 Matching means 130, 230 Distance Estimating means 140, 240 Gate control means C Imaging device D Display device G Gate

Claims (4)

A collation means that performs collation processing between the target in the captured image obtained by capturing the area before passing through the gate and the pre-registered target.
A positional relationship estimating means for estimating the positional relationship between the gate and the target using the distance between the eyes of the target in the captured image, and
A gate control means that controls the opening and closing of the gate based on the collation result of the collation means and the estimated positional relationship.
Bei to give a,
The positional relationship estimating means discriminates the attribute of the target registered in advance from the result of the collation process as the attribute of the target in the captured image, sets the reference inter-eye distance corresponding to the attribute, and sets the target. When the positional relationship between the gate and the target is estimated using the reference distance between the eyes and the attribute of the target in the captured image cannot be determined from the result of the collation process, a plurality of objects in the captured image are used. Each attribute of the plurality of targets is determined based on the attribute analysis process for each image portion of the target, the reference inter-eye distance corresponding to each attribute is set for each of the plurality of targets, and the shooting is performed. Each target inter-eye distance representing the inter-eye distance of each of the plurality of objects in the image is detected, and the target inter-eye distance and the reference inter-eye distance are compared for each of the plurality of objects in the captured image. Estimate the positional relationship between a plurality of objects and the gate,
Information processing system. The information processing system according to claim 1.
The gate control means opens and closes the gate based on the collation result of the collation means for the target and the positional relationship between the gate and the target, which are related to each other with respect to the target in the captured image. Control,
Information processing system. For information processing equipment
A collation means that performs collation processing between the target in the captured image obtained by capturing the area before passing through the gate and the pre-registered target.
A positional relationship estimating means for estimating the positional relationship between the gate and the target using the distance between the eyes of the target in the captured image, and
A gate control means that controls the opening and closing of the gate based on the collation result of the collation means and the estimated positional relationship.
Along with realizing
The positional relationship estimating means discriminates the attribute of the target registered in advance from the result of the collation process as the attribute of the target in the captured image, sets the reference inter-eye distance corresponding to the attribute, and sets the target. When the positional relationship between the gate and the target is estimated using the reference distance between the eyes and the attribute of the target in the captured image cannot be determined from the result of the collation process, a plurality of objects in the captured image are used. Each attribute of the plurality of targets is determined based on the attribute analysis process for each image portion of the target, the reference inter-eye distance corresponding to each attribute is set for each of the plurality of targets, and the shooting is performed. Each target inter-eye distance representing the inter-eye distance of each of the plurality of objects in the image is detected, and the target inter-eye distance and the reference inter-eye distance are compared for each of the plurality of objects in the captured image. Estimate the positional relationship between a plurality of objects and the gate,
A program to make that happen. In addition to performing collation processing between the target in the captured image of the area before passing through the gate and the pre-registered target,
The positional relationship between the gate and the target is estimated using the distance between the eyes of the target in the captured image.
When estimating the positional relationship between the gate and the target, the attribute of the target registered in advance is determined as the attribute of the target in the captured image from the result of the collation process, and the reference interval corresponding to the attribute is determined. When the distance is set, the positional relationship between the gate and the target is estimated using the set reference inter-eye distance, and the attribute of the target in the captured image cannot be determined from the result of the collation process. , Each attribute of the plurality of targets is determined based on the attribute analysis processing for each image portion of the plurality of targets in the captured image, and the reference inter-eye distance corresponding to each attribute is determined by the plurality of targets. In addition to setting each, each target eye distance representing the eye distance of each of the plurality of objects in the captured image is detected, and the target eye distance and the reference eye distance are set for each of the plurality of objects. By comparison, the positional relationship between the gate and the plurality of objects in the captured image is estimated.
Controlling the opening and closing of the gate based on the collation result and the estimated positional relationship.
Information processing method.

Images