JP7688989B2 - Information processing device, control method, program, and storage medium - Google Patents

Description

This disclosure relates to processing of measured data.

Laser radar devices have been known for some time that irradiate a detection space with pulses of laser light and detect objects in the detection space based on the level of the reflected light. For example, Patent Document 1 discloses a lidar that scans the surrounding space by appropriately controlling the emission direction (scanning direction) of repeatedly emitted light pulses, and generates point cloud data representing information about objects in the vicinity, such as distance and reflectance, by observing the returned light. Patent Document 2 discloses a technology for recognizing objects based on point cloud data output by the lidar.

JP 2018-009831 A JP 2018-116004 A

When measurement data generated by a measurement device such as a lidar according to a specified measurement cycle is uploaded and collected and managed by a server device, the volume of measurement data generated is large, so if all measurement data is targeted for transmission, the communication load and processing load of the server device will be excessive.

This disclosure has been made to solve the above problems, and its main objective is to provide an information processing device that can effectively reduce the amount of measured data.

The claimed invention is
An acquisition means for acquiring measurement data by a measuring device mounted on a vehicle ;
an object detection means for detecting a predetermined type of object other than a road based on the measurement data;
an extraction means for extracting object detection data corresponding to the detected object from the measurement data;
a determination means for determining whether or not the detection result by the object detection means matches the prior information based on a comparison result between the detection result and the prior information regarding the object;
a transmitting means for transmitting the object detection data to a data collection device when the detection result does not match the prior information;
The information processing device has the following features.

The claimed invention also includes:
A computer-implemented control method, comprising:
Acquire measurement data from a measuring device mounted on the vehicle ,
Detecting a predetermined type of object other than a road based on the measurement data;
extracting object detection data corresponding to the detected object from the measurement data;
determining whether or not the detection result matches the prior information based on a comparison result between the detection result of the object and the prior information regarding the object;
If the detection result does not match the prior information, transmitting the object detection data to a data collection device.
It is a control method.

The claimed invention also includes:
Acquire measurement data from a measuring device mounted on the vehicle ,
Detecting a predetermined type of object other than a road based on the measurement data;
extracting object detection data corresponding to the detected object from the measurement data;
determining whether or not the detection result matches the prior information based on a comparison result between the detection result of the object and the prior information regarding the object;
The program causes a computer to execute a process of transmitting the object detection data to a data collection device when the detection result and the prior information do not match.

FIG. 1 is a schematic diagram of a data collection system. FIG. 1 is a block diagram of an information processing device. 13 is an example of a flowchart executed by the information processing device. 1 is a diagram showing a pulsed laser beam emitted by a lidar, which is an external sensor. 1 is an overhead view of a road on which a vehicle equipped with multiple external sensors travels. 1 is a diagram showing a road on which a vehicle equipped with an external sensor is traveling, observed from the side. 13 is an example of a flowchart executed by an information processing device in a modified example.

According to a preferred embodiment of the present invention, the information processing device has an acquisition means for acquiring measurement data from a measurement device, an object detection means for performing processing related to object detection based on the measurement data, an extraction means for extracting object detection data from the measurement data, which is data corresponding to the detected object, and a transmission means for transmitting the object detection data to a data collection device. With this aspect, the information processing device can limit the data to be transmitted to the data collection device to data corresponding to the detected object, and preferably reduce the amount of transmitted data.

In one aspect of the information processing device, the measuring device includes a first measuring device and a second measuring device, the acquiring means acquires first measurement data by the first measuring device and second measurement data by the second measuring device, the object detection means detects the object based on the first measurement data and the object based on the second measurement data, respectively, and the transmitting means transmits the object detection data to the data collecting device when the object detection result based on the first measurement data and the object detection result based on the second measurement data are inconsistent. With this aspect, the information processing device can limit the data to be transmitted to the data collecting device to data in which a contradiction has occurred in the object detection result, and can suitably reduce the amount of transmitted data.

In another aspect of the information processing device, the first measuring device and the second measuring device have a common measurement range, and the information processing device further has a contradiction determination means for determining whether or not there is a contradiction between the detection result of the object based on the first measurement data in the measurement range and the detection result of the object based on the second measurement data in the measurement range. With this aspect, the information processing device can preferably determine whether or not there is a contradiction in the detection result of the object when multiple measurement sensors are used.

In another aspect of the information processing device, the information processing device further includes an erroneous detection determination means for determining whether or not the object has been erroneously detected by the object detection means based on a comparison result between the detection result of the object by the object detection means and prior information regarding the object, and the extraction means extracts the data when it is determined that the erroneous detection has occurred. With this aspect, the information processing device can limit the data to be transmitted to the data collection device to data in which an erroneous detection of an object has occurred, and can suitably reduce the amount of transmitted data.

In another aspect of the information processing device, the prior information is map information including information about the object, information about a model of the object, or information about constraints on the object. By using such prior information, the information processing device can appropriately determine whether or not an object has been erroneously detected.

In a preferred example of the information processing device, the measuring device is mounted on a vehicle, and the object detection means performs processing related to the detection of objects other than roads. In another preferred example of the information processing device, the object detection means performs processing related to the detection of objects specified by the data collection device.

According to another preferred embodiment of the present invention, a control method executed by a computer includes acquiring measurement data from a measurement device, performing processing related to object detection based on the measurement data, extracting object detection data corresponding to the detected object from the measurement data, and transmitting the object detection data to a data collection device. By executing this control method, the computer can limit the data to be transmitted to the data collection device to data corresponding to the detected object, and preferably reduce the amount of transmitted data.

According to another preferred embodiment of the present invention, the program causes a computer to execute the following processes: acquire measurement data from a measurement device, perform processing related to object detection based on the measurement data, extract object detection data from the measurement data that is data corresponding to the detected object, and transmit the object detection data to a data collection device. By executing this program, the computer can limit the data to be transmitted to the data collection device to data corresponding to the detected object, and preferably reduce the amount of transmitted data. Preferably, the program is stored in a storage medium.

Below, a preferred embodiment of the present invention will be described with reference to the drawings.

(1) Overview of the data collection system
1 shows a schematic configuration of a data collection system according to Example 1. The data collection system includes an information processing device 1 that processes data generated by a sensor group 2, and a data collection device 5 that is a server device that collects and manages data.

The information processing device 1 is electrically connected to the sensor group 2, compresses (including data selection) data output by the sensor group 2, and transmits the compressed data as upload information "Iu" to the data collection device 5. The information processing device 1 is, for example, a moving body such as a vehicle, ship, self-propelled robot, or drone, or a computer that controls the moving body. The information processing device 1 may be, for example, a navigation device mounted on a moving body such as a vehicle or ship, or an electronic control device built into the moving body.

The sensor group 2 includes an external sensor 3 and an internal sensor 4. The external sensor 3 is one or more sensors that sense the external world of the information processing device 1 or the mobile body equipped with the information processing device 1. The external sensor 3 is, for example, a range sensor such as a lidar, a camera, an ultrasonic sensor, etc. The internal sensor 4 is one or more sensors that sense the internal world of the information processing device 1 or the mobile body equipped with the information processing device 1. The internal sensor 4 is, for example, an angular velocity sensor, a GNSS (Global Navigation Satellite System) receiver, an acceleration sensor, an IMU (Inertial Measurement Unit), other autonomous positioning devices, etc. In this way, the sensor group 2 includes various sensors used for self-position estimation, obstacle detection, human detection, etc. Note that at least some of the sensors in the sensor group 2 may be sensors built into the information processing device 1.

The data collection device 5 is a device that collects measurement data by the lidar, receives upload information Iu from the information processing device 1, and stores the received upload information Iu. Note that, although only one pair of the information processing device 1 and the sensor group 2 is illustrated in FIG. 1, instead, there may be multiple pairs of the information processing device 1 and the sensor group 2. In this case, the data collection device 5 receives upload information Iu from each information processing device 1. For example, the data collection device 5 uses the upload information Iu received from the information processing device 1 as training data for an object recognition model based on machine learning such as deep learning. Note that the upload information Iu may include, in addition to the measurement data output by the external sensor 3, information on the self-position (i.e., the measurement position) at the time of measurement estimated by the information processing device 1 and information on the measurement time.

(2) Configuration of the information processing device
2 is a block diagram showing an example of a hardware configuration of the information processing device 1. The information processing device 1 mainly includes an interface 11, a memory 12, and a controller 13. These elements are connected to each other via a bus line.

The interface 11 performs interface operations related to the exchange of data between the information processing device 1 and an external device. In this embodiment, the interface 11 acquires output data from the sensor group 2 and supplies it to the controller 13. The interface 11 also transmits upload information Iu generated by the controller 13 to the data collection device 5 based on the control of the controller 13. If the information processing device 1 is mounted on a moving object such as a vehicle, the interface 11 may also supply a signal related to the control of the moving object generated by the controller 13 to an electronic control unit (ECU: Electronic Control Unit) of the moving object. The interface 11 may be a wireless interface such as a network adapter for wireless communication, or may be a hardware interface for connecting to an external device via a cable or the like. The interface 11 may also perform interface operations with various peripheral devices such as an input device, a display device, and a sound output device.

The memory 12 is composed of various types of volatile and non-volatile memory, such as a RAM (Random Access Memory), a ROM (Read Only Memory), a hard disk drive, and a flash memory. The memory 12 stores a program for the controller 13 to execute a predetermined process. The program executed by the controller 13 may be stored in a storage medium other than the memory 12.

In addition, the memory 12 stores various information related to the processing executed by the controller 13. For example, the memory 12 stores object recognition information I1.

The object recognition information I1 is information necessary for recognizing (detecting) an object based on the measurement data output by the external sensor 3. For example, the object recognition information I1 may be a parameter of an inference model that infers the presence or absence (and type of object) of an object contained in the measurement data when the measurement data output by the external sensor 3 is input. When the input data is, for example, an image of a camera, such an inference model may be any machine learning model such as a deep learning model used in recognition techniques such as semantic segmentation and instance segmentation. The data input to the above inference model is not limited to an image output by a camera, but may be point cloud data for one measurement cycle output by a lidar, or may be data output by another external sensor. Note that the point cloud data for one measurement cycle of the lidar can be regarded as image data when the measurement direction is the pixel position and the data for each measurement direction is pixel data, so that it is possible to learn the inference model in the same way as the image of a camera. In addition, an inference model may be provided for each type of external sensor. In this case, the inference models are trained in advance using data output by the target external sensor as training data (learning data), and the parameters of each inference model obtained by training are stored as object recognition information I1.

The controller 13 includes one or more processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and a TPU (Tensor Processing Unit), and controls the entire information processing device 1. In this case, the controller 13 executes various processes described below by executing programs stored in the memory 12, etc.

Functionally, the controller 13 also has a self-position estimation unit 14, an object detection unit 15, and an upload unit 16.

The self-position estimation unit 14 performs self-position estimation based on the data generated by the sensor group 2, and generates position information indicating the position of the information processing device 1 (including attitudes such as Yaw, Roll, and Pitch. The same applies below). In this case, the self-position estimation unit 14 may generate the position information by any self-position estimation method. For example, the self-position estimation unit 14 may generate the position information based on the output of a GNSS receiver or the like included in the sensor group 2. In another example, the self-position estimation unit 14 may generate the position information by executing a self-position estimation method using measurement data of the external sensor 3 and map data. Examples of such self-position estimation methods include a self-position estimation method based on the result of matching measurement data of a landmark with map data of the landmark, and a self-position estimation method based on NDT (Normal Distribution Transform) matching using voxel data. And its own

The object detection unit 15 detects an object present within the measurement range of the external sensor 3 based on the measurement data output by the external sensor 3 and the object recognition information I1. In this case, the object to be detected (also called the "detection target object") is a predetermined type of object, and for example, when the external sensor 3 is mounted on a vehicle, it is an object other than a road (which may be limited to a stationary object). The object detection unit 15 may receive information specifying the detection target object from the data collection device 5 and determine the detection target object based on the information. When the object detection unit 15 detects a detection target object, it extracts measurement data (also called the "object detection data") corresponding to the detection target object from the measurement data used for object detection, and supplies the extracted object detection data to the upload unit 16. For example, when the detection of the detection target object is performed using point cloud data obtained from a lidar, the object detection data is data representing the measured position of the detection target object. Furthermore, when detection of a target object is performed using an image obtained from a camera or the like, the object detection data is either the entire image including the target object, or an image obtained by cutting out the smallest area including the target object (e.g., a bounding box).

The upload unit 16 transmits the upload information Iu including the object detection data to the data collection device 5 via the interface 11. In this case, for example, the upload unit 16 may transmit the object detection data generated according to the measurement period to the data collection device 5 sequentially, or may transmit the object detection data collectively at predetermined time intervals to the data collection device 5. The upload unit 16 may also preferably include in the upload information Iu, together with the object detection data, information on the measurement position generated by the self-position estimation unit 14 and information indicating the type of the corresponding external sensor 3. The upload unit 16 may also compress the upload information Iu using any lossless or lossy compression, and transmit the compressed upload information Iu to the data collection device 5.

The controller 13 functions as an "acquisition means," an "object detection means," an "inconsistency determination means," an "erroneous detection determination means," an "extraction means," a "transmission means," a computer that executes a program, etc.

The processing executed by the controller 13 is not limited to being realized by software programs, but may be realized by any combination of hardware, firmware, and software. The processing executed by the controller 13 may also be realized by using a user-programmable integrated circuit, such as an FPGA (Field-Programmable Gate Array) or a microcomputer. In this case, the program executed by the controller 13 in this embodiment may be realized by using this integrated circuit.

(3) Processing flow
3 is an example of a flowchart executed by the information processing device 1 in the first embodiment. The information processing device 1 repeatedly executes the process of the flowchart in FIG.

First, the object detection unit 15 of the information processing device 1 acquires the measurement data generated by the external sensor 3 via the interface 11 (step S11). In this case, when the external sensor 3 used performs scanning or the like, the object detection unit 15 acquires data obtained by one period of measurement.

Next, the object detection unit 15 detects an object based on the measurement data acquired in step S11 (step S12). In this case, the object detection unit 15 acquires a detection result of the object to be detected, for example, by inputting the measurement data to an inference device configured by referring to the object recognition information I1.

Then, the object detection unit 15 determines whether or not a detection target object has been detected (step S13). If a detection target object has been detected (step S13; Yes), object detection data corresponding to the detected object is extracted from the measurement data acquired in step S11. Then, the upload unit 16 transmits upload information Iu including the object detection data to the data collection device 5 (step S14). The upload information Iu transmitted to the data collection device 5 is preferably used as training data for an object recognition model based on machine learning such as deep learning. Note that instead of sequentially transmitting the object detection data of the detection target object detected in step S13, the upload unit 16 may transmit the object detection data of the detection target object detected at multiple measurement timings all at once.

On the other hand, if the object detection unit 15 does not detect a detection target object in step S13 (step S13; No), it discards the measurement data acquired in step S11 (step S15).

In this way, the information processing device 1 according to the first embodiment can efficiently transmit data useful to the data collection device 5 to the data collection device 5.

(4) Specific examples
Fig. 4 is a diagram showing a pulsed laser beam emitted by a lidar, which is an external sensor 3. In the example of Fig. 4, the lidar emits a pulsed laser beam at a predetermined angular range (about 210° in this example) including the forward direction of the vehicle, with a predetermined angular resolution determined by the pulse period. Note that the lidar emits a pulsed laser beam at a predetermined angular range in the vertical direction in addition to the horizontal direction, or the scanning surface is tilted with respect to the horizontal direction, so that the lidar also irradiates the road surface with the pulsed laser beam.

In this case, the pulsed laser emitted by the lidar is irradiated to each object including the white lines 51a to 51c, the road sign 52, the utility pole 53, the building 54, and the vehicle ahead 55, and the reflected light is received by the lidar. In this case, the information processing device 1 receives point cloud data generated based on the light reception signal of the reflected light from the lidar 30 (see step S11 in FIG. 3), and detects the detection target object (see step S12 in FIG. 3). Here, for example, the detection target object is assumed to be all objects other than the road (including the white line). Then, the information processing device 1 detects the road sign 52, the utility pole 53, the building 54, and the vehicle ahead 55 as the detection target objects (see step S13), and extracts the data determined to belong to the road sign 52, the utility pole 53, the building 54, and the vehicle ahead 55, respectively, as object detection data. Then, the information processing device 1 transmits upload information Iu including the extracted object detection data to the data collection device 5 (see step S14). In this case, the information processing device 1 preferably transmits upload information Iu that associates object detection data for each detected object with information on the type of the detected object to the data collection device 5.

(5) Modifications
The information processing device 1 may determine whether there is a contradiction in the object detection results for each external sensor 3 based on the measurement data output by the multiple external sensors 3, and transmit object detection data related to the measurement data in which there is a contradiction to the data collection device 5. In addition to this, or instead of this, the information processing device 1 may determine whether or not there has been a false detection of an object by comparing the object detection result with prior information related to the object, and transmit object detection data related to the measurement data in which there has been a false detection to the data collection device 5. According to these aspects, the information processing device 1 can suitably supply important data as an analysis target for improving the accuracy of the object detection process to the data collection device 5.

Figure 5 is an overhead view of a road on which a vehicle equipped with external sensors 3A and 3B is traveling. In Figure 5, the measurement range "FOV1" of external sensor 3A, the measurement range "FOV2" of external sensor 3B, and a common (overlapping) measurement range "FOV12" shared by external sensors 3A and 3B are clearly shown. A vehicle 56 is present in the common measurement range FOV12. External sensors 3A and 3B may be a combination of different types of external sensors (e.g., a lidar and a camera), or may be the same type of external sensors (e.g., both are lidars). Here, the detection target object includes a vehicle.

In this case, the information processing device 1 detects the detection target object based on the measurement data of the external sensors 3A and 3B belonging to the common measurement range FOV12. Then, the information processing device 1 determines whether the detection result of the detection target object based on the measurement data (also called "first measurement data") in the common measurement range FOV12 of the external sensor 3A is inconsistent with the detection result of the detection target object based on the data (also called "second measurement data") in the common measurement range FOV12 of the external sensor 3B. Then, if these detection results are different, the information processing device 1 transmits upload information Iu including object detection data extracted from the first measurement data and the second measurement data, respectively, to the data collection device 5. In this case, the information processing device 1 determines that the detection results are inconsistent, for example, when the type and number of the detection target object detected based on the first measurement data do not match the type and number of the detection target object detected based on the second measurement data. For example, if the information processing device 1 detects a forward vehicle 56 based on the first measurement data but cannot detect the forward vehicle 56 based on the second measurement data, it determines that these detection results are inconsistent and transmits upload information Iu based on the first and second measurement data used for the detection to the data collection device 5. In this case, the information processing device 1 extracts object detection data corresponding to the detected detection target object from the first and second measurement data, respectively (or all data if the detection target object cannot be detected), and transmits upload information Iu including the extracted data to the data collection device 5.

Figure 6 is a side view of a road on which a vehicle equipped with an external sensor 3 is traveling. In the example of Figure 6, the information processing device 1 detects a guide 57, a traffic light 58, and a vehicle ahead 59 as detection target objects based on the measurement data output by the external sensor 3. In this case, the information processing device 1 performs an error determination of the detection result based on prior information on the detection target objects pre-stored in the memory 12. The prior information may be model information that models the detection target object, may be constraint conditions on the detection target object, or may be map information including information on the detection target object (position information, type information, appearance information, etc.).

For example, when the information processing device 1 includes a vehicle constraint condition that the vehicle is in contact with a road as the prior information, the information processing device 1 determines whether the position of the forward vehicle 59 detected based on the measurement data of the external sensor 3 is in contact with the road. In this case, for example, the information processing device 1 identifies the road data and the forward vehicle 59 data from the measurement data of the external sensor 3, and determines whether the distance between the identified data (for example, the distance between the center of gravity positions in the height direction) is within a predetermined distance. Then, when the distance between the above-mentioned data is longer than the predetermined distance, the external sensor 3 determines that the above-mentioned constraint condition is violated and that a false detection has occurred. Therefore, in this case, the external sensor 3 transmits upload information Iu including object detection data corresponding to the forward vehicle 59 to the data collection device 5. The constraint condition is not limited to the condition that the vehicle is in contact with the road surface, and may be various conditions such as the size of the vehicle. Note that the prior information has appropriate constraint conditions registered for each type of object to be detected.

In another example, when the information processing device 1 stores map information including information on the guide 57 and the traffic light 58 in the memory 12, the information processing device 1 determines whether the position and size, etc. of the guide 57 and the traffic light 58 detected based on the measurement data of the external sensor 3 match the position and size, etc. of the guide 57 and the traffic light 58 recorded in the map information. In this case, the information processing device 1 may perform the above-mentioned estimation by applying any object recognition technology that estimates the position and size, etc. of an object based on the output of a camera or a lidar. For example, the information processing device 1 estimates the position on the map of each of the guide 57 and the traffic light 58 based on the position on the map based on the self-location estimation result and the relative position with respect to the information processing device 1 indicated by the measurement data of the external sensor 3. The information processing device 1 also estimates the size, etc. of each of the guide 57 and the traffic light 58 based on the measurement data corresponding to each of the guide 57 and the traffic light 58. Then, when the detection result of the guide 57 and the traffic light 58 based on the measurement data does not match the prior information of the guide 57 and the traffic light 58 included in the map information previously stored in the memory 12, the information processing device 1 determines that an erroneous detection has occurred. Therefore, in this case, the information processing device 1 transmits upload information Iu including object detection data corresponding to the guide 57 and the traffic light 58 to the data collection device 5.

In yet another example, when model information of the detection target object is stored in memory 12 or the like as prior information, information processing device 1 performs a three-dimensional matching process between the three-dimensional shape of the detection target object indicated by the model information and the three-dimensional shape based on the detection result. Then, when the degree of matching by the three-dimensional matching is less than a predetermined threshold, information processing device 1 determines that a false detection has occurred, and transmits upload information Iu including the corresponding object detection data to data collection device 5.

Figure 7 is an example of a flowchart showing the processing procedure of the information processing device 1 in the modified example. The information processing device 1 repeatedly executes the processing of the flowchart shown in Figure 7.

First, the object detection unit 15 of the information processing device 1 acquires the measurement data generated by the external sensor 3 via the interface 11 (step S21). Next, the object detection unit 15 detects an object based on the measurement data acquired in step S21 (step S22). Then, the object detection unit 15 determines whether or not the detection target object has been detected (step S23).

If a detection target object is detected (step S23; Yes), it is determined whether there is a contradiction or erroneous detection in the detection result (step S24). In this case, if there is a common measurement range among multiple external sensors 3, the object detection unit 15 determines whether there is a contradiction in the detection result based on the measurement data of each external sensor 3. Furthermore, if prior information regarding the detection target object is stored in the memory 12 or the like, the object detection unit 15 compares the detection result with the prior information to determine whether there is erroneous detection.

If there is a contradiction or a false positive in the detection result (step S24; Yes), the upload unit 16 transmits upload information Iu including measurement data related to the contradiction or false positive to the data collection device 5 (step S25). On the other hand, if there is no contradiction or false positive in the detection result (step S24; No), the upload unit 16 discards the target measurement data (step S26).

As described above, the information processing device 1 according to the modified example can efficiently supply the upload information Iu, which contains limited data that is important as an analysis target for improving the accuracy of the object detection process, to the data collection device 5, and can effectively reduce the amount of data to be transmitted.

As described above, the controller 13 of the information processing device 1 according to the embodiment acquires measurement data from the external sensor 3 and performs processing related to object detection based on the measurement data. The controller 13 then extracts object detection data, which is data corresponding to the detected object, from the measurement data, and transmits the extracted object detection data to the data collection device 5. This allows the information processing device 1 to efficiently transmit data useful to the data collection device 5.

In the above-described embodiment, the program can be stored using various types of non-transitory computer readable media and supplied to a computer, such as a controller. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer readable media include magnetic storage media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical storage media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R/Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)).

Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. In other words, the present invention naturally includes various modifications and amendments that a person skilled in the art could make in accordance with the entire disclosure, including the scope of the claims, and the technical ideas. In addition, the disclosures of the above cited patent documents and the like are incorporated into this document by reference.

Reference Signs List 1 Information processing device 2 Sensor group 3 External sensor 4 Internal sensor 5 Data collection device

Claims (9)

An acquisition means for acquiring measurement data by a measuring device mounted on a vehicle ;
an object detection means for detecting a predetermined type of object other than a road based on the measurement data;
an extraction means for extracting object detection data corresponding to the detected object from the measurement data;
a determination means for determining whether or not the detection result by the object detection means matches the prior information based on a comparison result between the detection result and the prior information regarding the object;
a transmitting means for transmitting the object detection data to a data collection device when the detection result does not match the prior information;
An information processing device having the above configuration. the measurement device includes a first measurement device and a second measurement device;
the acquiring means acquires first measurement data by the first measuring device and second measurement data by the second measuring device;
the object detection means detects the object based on the first measurement data and detects the object based on the second measurement data,
The information processing device according to claim 1 , wherein the transmitting means transmits the object detection data to the data collecting device when a result of the object detection based on the first measurement data and a result of the object detection based on the second measurement data are inconsistent. the first measurement device and the second measurement device have a common measurement range,
3. The information processing apparatus according to claim 2, further comprising a contradiction determination means for determining whether or not there is a contradiction between a detection result of the object based on the first measurement data in the measurement range and a detection result of the object based on the second measurement data in the measurement range. The determination means determines whether or not the object has been erroneously detected by the object detection means based on a result of the comparison,
The information processing device according to claim 1 , wherein the transmission means transmits the object detection data to the data collection device when it is determined that the erroneous detection has occurred. The information processing device according to any one of claims 1 to 4, wherein the advance information is map information indicating at least the position and size of each of the predetermined types of objects, information regarding a model of the objects, or information regarding constraint conditions of the objects. The information processing device according to claim 1 , wherein the object detection means detects the object specified by the data collection device. A computer-implemented control method, comprising:
Acquire measurement data from a measuring device mounted on the vehicle ,
Detecting a predetermined type of object other than a road based on the measurement data;
extracting object detection data corresponding to the detected object from the measurement data;
determining whether or not the detection result matches the prior information based on a comparison result between the detection result of the object and the prior information regarding the object;
If the detection result does not match the prior information, transmitting the object detection data to a data collection device.
Control methods. Acquire measurement data from a measuring device mounted on the vehicle ,
Detecting a predetermined type of object other than a road based on the measurement data;
extracting object detection data corresponding to the detected object from the measurement data;
determining whether or not the detection result matches the prior information based on a comparison result between the detection result of the object and the prior information regarding the object;
A program that causes a computer to execute a process of transmitting the object detection data to a data collection device when the detection result and the prior information do not match. A storage medium storing the program according to claim 8 .