JP7039872B2 - Vehicle travel recording device and viewing device - Google Patents

Description

The present invention relates to a traveling recording device and a browsing device for recording a traveling situation of a vehicle.

As a vehicle travel recording device, as described in Patent Document 1, when the acceleration during vehicle travel exceeds the threshold value, it is determined from the ambient sound whether or not an accident has occurred, and when an accident occurs, the accident occurs. Drive recorders configured to record surrounding images captured back and forth are known.

Japanese Unexamined Patent Publication No. 2006-199204

The above drive recorder records the surrounding images at the time of the accident so that the situation at the time of the accident can be grasped from the recorded images after the accident occurs. There was a problem that it was difficult to detect.

In other words, a hiyari hat is a situation that does not lead to an accident, but is one step before an accident can occur. If such a hiyari hat can be detected and the image or sound at that time can be recorded as a hiyari hat scene, the vehicle operation manager can give the driver guidance on safe driving based on the recorded information.

However, in the hiyari hat scene, even if the acceleration exceeds the threshold value, the same sounds as when the accident occurred, such as collision sound, braking sound, and crushing sound, may not be generated, so the image is recorded based on the surrounding sound. With the above drive recorder, it was not possible to record a hiyari hat scene that does not generate the same sound as when the accident occurred.

In addition, even if the above drive recorder can record a hiyari hat scene that did not lead to an accident, it is difficult for the operation manager to identify the cause of the hiyari hat from the recorded video and sound, so it is used for safe driving guidance. There is also the problem that it is difficult to do.

One aspect of the present disclosure is that it is desirable that the traveling recording device for recording the traveling condition of the vehicle can detect the hilarious hat while the vehicle is traveling and record information that can easily grasp the driving condition of the hilarious hat.

In the vehicle travel recording device of one aspect of the present disclosure, the travel information recording unit (12, 14) acquires and records travel information including an image around the vehicle while the vehicle is traveling.
Further, when a predetermined state change occurs while the vehicle is running, the request unit (22) requests the occupant to explain the situation, and the voice recognition unit (24) recognizes the utterance content uttered by the occupant in response to the request. do.

Then, the hiyari hat determination unit (32) determines whether or not the travel information recorded in the travel information recording unit is a hiyari hat scene based on the utterance content of the occupant recognized by the voice recognition unit.

As described above, according to the traveling recording device of the present disclosure, when a predetermined state change occurs while the vehicle is traveling, the utterance content of the situation explanation is acquired from the occupant, and the utterance content is recorded in the traveling information recording unit. It is possible to detect that the driving information is a hiyari hat scene.

Therefore, according to the traveling recording device of the present disclosure, it is possible to improve the detection accuracy of the hearing hat and accurately identify the hearing hat scene recorded in the traveling information recording unit. Therefore, if the driving information of the specified hiyari hat scene is recorded on the non-volatile recording medium (40), the cause of the hiyari hat can be identified based on the recorded driving information after the vehicle has been driven, and the driver can drive the vehicle. Can give guidance.

In addition to the driving information of the hiyari hat scene, if the occupant's utterance content used for determining the hiyari hat is recorded on a non-volatile recording medium or the like each time the hiyari hat is detected, the driver can use the utterance content to record the utterance content. It will be possible to identify the hiyari hat scenes that are likely to occur. Therefore, in this case, it becomes possible to more appropriately provide driving guidance to the driver.

Further, when the browsing device (50) is used to browse the hiyari hat scene from the traveling information recorded in the non-volatile recording medium, the utterance content corresponding to the scene can be output from the utterance content to the hiyari hat. You will be able to easily grasp the scene.

In addition, the reference numerals in parentheses described in this column and the scope of claims indicate the correspondence with the specific means described in the embodiment described later as one embodiment, and the technical scope of the present disclosure is defined. It is not limited.

It is a block diagram which shows the structure of the traveling recording apparatus and the browsing apparatus of embodiment. It is a flowchart which shows the operation of the traveling information recording part. It is a flowchart which shows the operation of the hearing hat primary determination part. It is a flowchart which shows the operation of the driving scene primary recording part. It is a flowchart which shows the operation of the situation explanation request part. It is a flowchart which shows the request sentence generation process shown in FIG. It is a flowchart which shows the operation of a voice recognition part. It is a flowchart which shows the operation of the secondary determination unit of a hiyari hat. It is a flowchart which shows the hiyari hat secondary determination score calculation process shown in FIG. It is a flowchart which shows the operation of the driving scene secondary recording part. It is a flowchart which shows the operation of the driving scene extraction unit and the driving scene display unit.

The embodiments of the present disclosure will be described below together with the drawings.
The travel recording device 10 of the present embodiment is mounted on a vehicle such as an automobile, detects a hilarious hat generated during vehicle travel, and records an image at that time and a vehicle state as travel information on a non-volatile recording medium. belongs to.

Then, after the vehicle has traveled, the recorded driving information is browsed by the vehicle operation manager using the viewing device 50, and is used to give guidance to the driver on safe driving.
As shown in FIG. 1, the travel recording device 10 includes a travel information recording unit 12, a hearing hat primary determination unit 16, a traveling scene primary recording unit 18, a situation explanation request unit 22, a voice recognition unit 24, and a hearing hat secondary determination unit 32. , And a traveling scene secondary recording unit 38 is provided.

The travel recording device 10 is composed of an electronic control unit (ECU) centered on a microcomputer including a CPU, ROM, RAM, and the like. Each of the above parts is realized by the CPU executing various programs according to the flowcharts illustrated in FIGS. 2 to 10.

While the vehicle is running, the driving information recording unit 12 acquires the behavior of the vehicle, the image around the vehicle, the position of the vehicle, the sound inside and outside the vehicle, the attributes of peripheral objects, etc. as driving information from other in-vehicle devices, and drives the vehicle. A driver ID, which is identification information of a person, is assigned and recorded in the driving information DB 14. The DB represents a database.

Here, the behavior of the vehicle is the vehicle speed, acceleration, accelerator, brake, steering operation amount, etc. by the driver, and the traveling information recording unit 12 controls the driving / braking system of the vehicle with these information. Obtained from the control device.

Further, the images around the vehicle are images of the front / rear and the left / right side in the traveling direction of the vehicle, and the traveling information recording unit 12 acquires these images from one or more cameras mounted on the vehicle. .. Further, the traveling information recording unit 12 acquires the position of the vehicle from an in-vehicle device such as a GPS receiver that can detect the position, and acquires voices inside and outside the vehicle via a microphone mounted on the vehicle.

In addition, the attributes of peripheral objects are the type, distance, relative speed, etc. of objects around the vehicle that can be estimated by existing object recognition methods from images around the vehicle and information from distance measurement sensors. The unit 12 acquires this information from a radar device, a navigation device, or the like.

Further, the traveling information DB 14 is composed of a volatile recording medium. Then, the traveling information recording unit 12 acquires the traveling information from another in-vehicle device and records it in the traveling information DB 14 by repeatedly executing the traveling information recording process shown in FIG. 2 at a predetermined cycle while the vehicle is traveling.

As shown in FIG. 2, in the travel information recording process, the various travel information described above is measured in S110, and the measured travel information is transferred from the old information to the recording medium constituting the travel information DB 14 in S120. It is executed by the procedure of overwriting in order.

As a result, the travel information DB 14 records the travel information for the past predetermined period from the latest one.
Next, the hearing hat primary determination unit 16 primarily determines whether or not a hearing hat has occurred based on the traveling information recorded in the traveling information DB 14, and repeats the hearing hat primary determination process shown in FIG. 3 at a predetermined cycle. Execute.

As shown in FIG. 3, in the hearing hat primary determination process, the latest acceleration recorded as one of the driving information in the driving information DB is acquired in S210, and the acceleration is set to a preset threshold value in the subsequent S220. Judge whether or not it exceeds.

Then, when it is determined in S220 that the acceleration exceeds the threshold value, the process shifts to S230, the primary recording flag and the status explanation request flag are set to "TRUE", respectively, and the near-hat primary determination process is terminated.

If it is not determined in S220 that the acceleration exceeds the threshold value, the hearing hat primary determination process is terminated as it is.
Since the determination process of S220 is for detecting a hilarious hat from a change in the state of the vehicle, it is determined whether or not the absolute value of the acceleration including the deceleration of the vehicle exceeds the threshold value. Further, in S220, it suffices if the hearing hat can be determined from the change in the state of the vehicle that occurs when the hearing hat occurs. For example, the hearing hat may be determined using the vehicle speed or the steering angle of the steering wheel. Further, the threshold value used for the determination of the hiyari hat may be set to a fixed value in advance, or may be arbitrarily set by the operation manager or the like.

Next, the primary recording flag set to "TRUE" in S230 is used in the traveling scene primary recording unit 18 to determine whether or not to record the traveling information in the traveling scene primary recording DB 20.

That is, the traveling scene primary recording unit 18 repeatedly executes the traveling scene primary recording process shown in FIG. 4 at a predetermined cycle, so that the traveling information recorded in the traveling information DB 14 when the primary recording flag is “TRUE”. Is recorded in the driving scene primary recording DB.

As shown in FIG. 4, in the traveling scene primary recording process, first, in S310, it is determined whether or not the primary recording flag is "TRUE". Then, if the primary recording flag is "TRUE", the process proceeds to S320, and if the primary recording flag is not "TRUE", the driving scene primary recording process is terminated.

In S320, travel information for a predetermined period before and after is acquired from the travel information DB 14 with a determination time when the primary determination unit 16 for the hearing hat is determined to have occurred, and the process shifts to S330. In S320, for example, the traveling information from the determination time to 5 seconds before and the traveling information of the longer period until 5 seconds have passed from the determination time or the voice recognition described later is completed are acquired.

Then, in S330, the acquired driving information for a predetermined time is recorded in the driving scene primary recording DB 20 as a driving scene indicating the situation of the hiyari hat, and in the subsequent S340, the primary recording flag is set to "FALSE". , Ends the driving scene primary recording process.

Like the driving information DB 14, the traveling scene primary recording DB 20 is composed of a volatile recording medium, and a recording area capable of recording at least one scene of the hilarious hat situation is secured.

Therefore, when the driving scene is recorded in the driving scene primary recording DB 20 in S330, if the past driving scene is recorded in the driving scene primary recording DB 20, the recorded driving scene is referred to in S320. The latest acquired driving scene is overwritten.

Next, the situation explanation request unit 22 is for prompting the driver to explain the situation of the driving scene when the hearing hat is determined by the hearing hat primary determination unit 16, and is for prompting the driver to explain the situation of the driving scene. Is repeatedly executed at a predetermined cycle.

As shown in FIG. 5, in the status explanation request processing, in S410, it is determined whether or not the status explanation request flag is "TRUE", and if the status explanation request flag is "TRUE", the process proceeds to S420. , Otherwise, the status explanation request processing is terminated.

In S420, the voice recognition flag is set to "TRUE", the process shifts to S430, and the request statement generation process is executed.
This request sentence generation process is a process for generating a request sentence for prompting the driver to explain the situation based on the driving information when the hiyari hat primary determination unit 16 determines the hiyari hat. For example, the procedure shown in FIG. Is executed by.

That is, in the request sentence generation process, S432 determines whether or not an object exists around the vehicle based on the traveling information, and if an object exists around the vehicle, the process shifts to S434 and the vehicle becomes a vehicle. Get the attributes of the closest object. That is, in S434, it is estimated that the object closest to the vehicle is the causative object that causes the hiyari hat, and the attribute of the object is acquired.

Then, in the subsequent S436, a request statement for asking the driver whether or not the driver is about to collide with the object is determined based on the attribute of the object acquired in S434, and the request statement generation process is terminated.

Further, in S432, when it is determined that there is no object around the vehicle, it shifts to S438 and determines a request sentence for asking the driver whether or not it is about to collide with an object outside the measurement range. Ends the request statement generation process.

For example, in S438, since the object is not recognized, a request statement for asking the driver "what happened?" Is generated. Also, in S436, the attribute of the object closest to the vehicle is recognized, so based on that attribute, for example, "There was a person in front, did you almost hit that person?" Generate a request statement.

By generating the request statement in this way, it is possible to generate a request statement for the driver to positively explain the cause of the hiyari hat, for example, "No. A person came out from the side." It will be like.

In other words, if you are about to collide with a person who has jumped out from the side of the vehicle and the primary judgment unit 16 of the hiyari hat determines that it is a hiyari hat, the driver is uniformly asked "what happened?" , "I almost hit a person" may be answered.

However, in such an answer, if the person who jumped out from the side of the vehicle is not shown in the video while the vehicle is running when browsing after the vehicle is running, the operation manager is shown in the video while the vehicle is running. It is judged that the driver is about to hit the person, and the driver overlooks the fact that the pedestrian jumping out from the side is hard to notice.

However, if the cause of the hiyari hat is estimated and the request sentence is generated based on the estimation result as in the present embodiment, the cause of the hiyari hat can be identified more accurately at the time of browsing and the driving guidance is properly implemented. become able to.

In S434, the object closest to the vehicle is estimated as the object that causes the hiyari hat. For example, the object with the fastest approach speed is estimated as the object that causes the hiyari hat, and the attribute of the object is determined. You may try to get it. In addition, the type of object, the distance, the relative velocity, and the like may be comprehensively determined to estimate the object that causes the hiyari hat.

Next, when the request sentence is generated in S430, the process proceeds to S440, the generated request sentence is voice-synthesized, and the voice is output from the speaker to request the driver to explain the situation. ..

Then, in the subsequent S450, since the request for the status explanation is completed, the status explanation request flag is set to "FALSE" and the status explanation request processing is terminated.
The output of the request text may be, for example, displaying the request text on the windshield of the vehicle to prompt the driver to explain the situation, and both the voice output and the display prompt the situation explanation. You may do so.

Next, the voice recognition unit 24 recognizes the voice uttered by the driver in response to the request from the situation explanation request unit 22, and outputs the utterance word as the recognition result as text data representing the utterance content. For example, the voice recognition process shown in FIG. 7 is repeatedly executed at a predetermined cycle.

As shown in FIG. 7, in the voice recognition process, first, in S510, it is determined whether or not the voice recognition flag is "TRUE", and if the voice recognition flag is "TRUE", the process shifts to S520, and so on. If not, the voice recognition process is terminated.

In S520, it is determined whether or not a predetermined time: t seconds or more has elapsed since the voice recognition flag was set to "TRUE" and the voice recognition in S530 and S540 was started. Then, if the predetermined time: t seconds or more has not elapsed, the process proceeds to S530, and if the predetermined time: t seconds or more has elapsed, the process proceeds to S550.

In S530, the voice inside and outside the vehicle input from the microphone is measured, and in the following S540, the maximum likelihood word is output as the voice recognition result, and the process proceeds to S520. That is, in S530 and S540, the acoustic model 26 and the language model 28 shown in FIG. 1 are used to perform speech recognition using the most probable phoneme / word string as the recognition result.

The acoustic model 26 and the language model 28 are, for example, hidden Markov models, which are recorded in advance in a non-volatile memory. In addition, the dictionary included in the language model may be a general spoken language, and is composed of, for example, hiyari hat-related words such as "intersection" and "bicycle" and negative words such as "nothing" and "cause of mind". It may be only a word for secondary determination to be made. Then, if the dictionary of the language model is limited to the words related to the hiyari hat and the negative words, the words necessary for the secondary judgment of the hiyari hat, which will be described later, can be recognized more accurately.

On the other hand, in S550, since a predetermined time: t seconds or more has elapsed after the start of voice recognition, the voice recognition flag is set to "FALSE" and the voice recognition is terminated. Then, in the subsequent S560, the hiyari hat secondary determination flag is set to "TRUE", and the voice recognition process is terminated.

Next, the hiyari hat secondary determination unit 32 is for determining whether or not the hiyari hat actually occurred from the spoken words of the driver voice-recognized by the voice recognition unit 24, for example, in FIG. The following hiyari hat secondary determination process is repeatedly executed at a predetermined cycle.

As shown in FIG. 8, in the near-hat secondary determination process, in S610, it is determined whether or not the near-hat secondary determination flag is “TRUE”, and if the near-hat secondary determination flag is “TRUE”, the process proceeds to S620. If not, the secondary determination process for the hiyari hat is terminated.

In S620, the hiyari hat secondary determination score calculation process for calculating the score used for the secondary determination of the hiyari hat is executed by the procedure shown in FIG.
As shown in FIG. 9, in the hiyari hat secondary determination score calculation process, in S622, the value of the acceleration used for the primary determination of the hiyari hat by the hiyari hat primary determination unit 16 is acquired as the score 1.

Further, in the following S624, the voice recognition unit 24 obtains the ratio of the hiyari hat-related words and the negative words contained in the spoken words recognized by voice during a predetermined time: t seconds, and the difference in the ratios of these words is scored. Calculate as 2.

Finally, in S626, the weighted sum of the score 1 and the score 2 is obtained by weighting and adding the score 1 acquired in S622 and the score 2 calculated in S624, and this is set as the secondary determination score. ..

The hiyari hat-related words and the negative words are preset and recorded in the non-volatile memory as the hiyari hat-related word dictionary 34 and the negative word dictionary 36, as in the acoustic model 26 and the language model 28.

In this way, when the secondary judgment score is calculated by the hiyari hat secondary judgment score calculation process, the process proceeds to S630, and it is determined whether or not the calculated secondary judgment score is equal to or higher than the preset threshold value. do.

That is, in S630, by comparing the secondary judgment score and the threshold value, whether or not the ratio of the hiyari hat-related words is higher than the ratio of the negative words in the spoken words recognized by voice by a preset ratio or more. By determining, it is determined whether or not a hiyari hat has occurred.

Further, since the value of the acceleration used for the primary determination by the hearing hat primary determination unit 16 is also weighted and added to the secondary determination score, the hearing hat can be accurately determined in S630.

That is, for example, when the acceleration exceeds the threshold value and the driver explains that it is not like a hiyari hat, the larger the acceleration, the easier it is for S630 to determine the hiyari hat, so that the judgment accuracy of the hiyari hat can be improved. can.

If it is determined in S630 that the secondary determination score of the hiyari hat is equal to or higher than the threshold value, the process proceeds to S640, and if not, the process proceeds to S650. Further, in S640, the secondary recording flag of the hiyari hat is set to "TRUE", and the process shifts to S650.

Then, in S650, the hearing hat secondary determination flag is set to "FALSE", and the hearing hat secondary determination process is terminated.
Next, the running scene secondary recording unit 38 acquires the determined running scene from the running scene primary recording DB 20 when the hiyari hat secondary determination unit 32 determines that a hiyari hat has occurred, and the running scene secondary recording unit 38 acquires the determined running scene from the running scene primary recording DB 20. It is for recording in the recording DB 40.

That is, the traveling scene secondary recording unit 38 functions as the scene recording unit of the present disclosure by repeatedly executing the traveling scene secondary recording process shown in FIG. 10 at a predetermined cycle.
As shown in FIG. 10, in the traveling scene secondary recording process, first, in S710, it is determined whether or not the secondary recording flag is "TRUE". Then, if the secondary recording flag is "TRUE", the process proceeds to S720, and if the secondary recording flag is not "TRUE", the driving scene secondary recording process is terminated.

In S720, the running scene in which the hearing hat is determined to have occurred is acquired from the running scene primary recording DB 20 by the hearing hat secondary determination unit 32, and the process proceeds to S730. Then, in S730, the voice recognition result used for determining the hearing hat is acquired from the hearing hat secondary determination unit 32, and the acquired voice recognition result and the traveling scene acquired in S720 are stored in the traveling scene secondary recording DB 40. Record.

The traveling scene secondary recording DB 40 is configured with a non-volatile recording medium so that the traveling scene of the hiyari hat can be maintained even if the power supply to the traveling recording device 10 is cut off after the vehicle travels.

Then, when the driving scene is recorded in the driving scene secondary recording DB 40 together with the voice recognition result in S730, the process shifts to S740, the secondary recording flag is set to "FALSE", and the driving scene secondary recording process is performed. To finish.

As described above, in the vehicle travel recording device 10 of the present embodiment, the travel information recording unit 12 acquires the travel information including the image around the vehicle and records it in the travel information DB 14 while the vehicle is traveling.

Then, when the hiyari hat primary determination unit 16 determines the hiyari hat while the vehicle is running, the situation explanation request unit 22 requests the occupant such as the driver to explain the situation, and the voice recognition unit 24 utters the occupant in response to the request. Recognize the content of the utterance.

Then, the hiyari hat secondary determination unit 32 secondarily determines the hiyari hat based on the utterance content, and when the hiyari hat secondary determination unit 32 also determines the hiyari hat, the running information at that time is used as the running scene of the hiyari hat. It is recorded in the scene secondary recording DB 40.

Therefore, according to the traveling recording device 10 of the present embodiment, the hilarious hat can be determined in two stages based on the acceleration of the vehicle and the utterance content of the occupant, and the occurrence of the hilarious hat can be detected with high accuracy.

Further, the driving scene recorded in the driving scene secondary recording DB 40 is composed of driving information such as vehicle behavior, image around the vehicle, vehicle position, sound inside and outside the vehicle, attributes of surrounding objects, driver ID, and the like. ing. Then, in addition to this driving scene, text data which is a recognition result by the voice recognition unit 24 is also recorded in the traveling scene secondary recording DB 40.

Therefore, according to the travel recording device 10 of the present embodiment, after the vehicle has traveled, the cause of the hiyari hat is identified by browsing the travel scene recorded in the travel scene secondary recording DB 40 via the browsing device 50. , Can provide driving guidance to the driver.

Further, when browsing the driving scene, the cause of the hearing hat can be classified by using the text data which is the voice recognition result for each driving scene of the hearing hat, and the hearing hat scene in which the driver is likely to occur can be easily identified. Therefore, if the vehicle travel recording device 10 of the present embodiment is used, it is possible to more appropriately provide driving guidance to the driver.

Next, the viewing device 50 used by the vehicle operation manager to view the traveling scene recorded in the traveling scene secondary recording DB 40 will be described.
As shown in FIG. 1, the browsing device 50 displays a driving scene extraction unit 52 that extracts a driving scene according to a query specified by the operation manager from the driving scene secondary recording DB 40, and the extracted driving scene on the display. A traveling scene display unit 54 is provided.

The driving scene extraction unit 52 and the driving scene display unit 54 are realized by the computer constituting the viewing device 50 executing the driving scene extraction / display processing shown in FIG.
That is, in the driving scene extraction / display processing, in S810, the processing as the driving scene extraction unit 52 that extracts the driving scenes that match the query specified by the operation manager from the driving scene secondary recording DB 40 is executed.

The query specified by the operation manager may include, for example, a driver ID, a spoken word, an acceleration, the presence / absence of a peripheral object, a distance from the peripheral object, a type of the peripheral object, and the like.
Next, in S820, it is determined whether the display form of the traveling scene is a list display or an individual display. The determination of this display form is carried out according to the display command from the operation manager, and shifts to S830 in the case of list display and shifts to S840 in the case of individual display.

In S830, the query used to extract the driving scene in S810, the number of the extracted driving scenes, the utterance words given to the extracted driving scenes, their occurrence frequency, and the like are displayed in a list on the display.

Therefore, for example, in S810, when the driving scene of a specific driver is extracted by using the driver ID, for example, "people" 60%, "bicycle" 20%, "intersection" by the list display. The spoken word and its frequency of occurrence will be displayed, such as 80%.

In this case, the operation manager can determine from the list display screen that the driver specified by the driver ID is "easy to collide with a person at an intersection", and can properly provide driving guidance to the driver. It will be like.

Further, in S840, one traveling scene to be displayed is selected from the traveling scenes extracted in S810, and the process shifts to S850.
Then, in S850, the driver ID, the vehicle behavior, the image, the position, the peripheral object attribute, the voice, and the spoken word are displayed on the display according to various information included in the selected driving scene. The sound is output from the speaker.

As a result, the operation manager can quickly grasp the outline of the driving scene from the spoken word displayed in the text on the display, and can detect the cause of the hiyari hat without watching the video of the driving scene to the end. It will be possible to identify.

Although the embodiment for carrying out the present invention has been described above, the present invention is not limited to the above-described embodiment and can be variously modified and carried out.
For example, in the above embodiment, the voice recognition unit 24 has been described as recognizing the utterance language uttered by the occupant in the processing of S530 and S540. The accident voice may be recognized.

In this way, even if the driver cannot explain the situation or lie that it is not a hiyari hat, the hiyari hat can be detected.
Further, the voice recognition in the voice recognition unit 24 may be started before the situation explanation request unit 22 finishes the situation explanation request, for example, immediately after the hearing hat is determined by the hearing hat primary determination unit 16. ..

By doing so, the driver can recognize the content of the utterance even if the driver starts the utterance without waiting for the request.
Further, although the voice recognition in the voice recognition unit 24 has been described as being performed for t seconds after the situation explanation request, this time may be a fixed time such as 10 seconds or set according to the silent section. You may.

That is, for example, voice recognition may be completed when the silent state continues for 3 seconds or longer. By doing so, even if the explanation by the driver is long, the utterance content can be recognized until the end of the explanation.

In this case, the silent section may be determined to be a section in which the amplitude of the audio signal is less than a certain threshold value or the number of zero crossings is less than the threshold value.
Next, in the above embodiment, the travel recording device 10 is composed of an electronic control device configured by a microcomputer, and each part shown in FIG. 1 is realized by the CPU executing a program. Explained as.

However, each part constituting the traveling recording device 10 may be partially or wholly realized by using hardware in which a logic circuit, an analog circuit, or the like is combined. The same applies to the traveling scene extraction unit 52 and the traveling scene display unit 54 of the browsing device 50.

Further, a plurality of functions possessed by one component in the above embodiment may be realized by a plurality of components, or one function possessed by one component may be realized by a plurality of components. Further, a plurality of functions possessed by the plurality of components may be realized by one component, or one function realized by the plurality of components may be realized by one component. Further, a part of the configuration of the above embodiment may be omitted. Further, at least a part of the configuration of the above embodiment may be added or replaced with the configuration of the other above embodiment. It should be noted that all aspects included in the technical idea specified only by the wording described in the claims are embodiments of the present invention.

10 ... Driving recording device, 12 ... Driving information recording unit, 14 ... Driving information DB, 16 ... Hiyari hat primary judgment unit, 22 ... Situation explanation request unit, 24 ... Voice recognition unit, 32 ... Hiyari hat secondary judgment unit, 38 ... Driving Scene secondary recording unit, 40 ... Driving scene secondary recording DB, 50 ... Viewing device, 52 ... Driving scene extraction unit, 54 ... Driving scene display unit.

Claims (10)

A driving information recording unit (12, 14) that acquires and records driving information including images around the vehicle while the vehicle is driving, and
The request unit (22), which requests the occupants to explain the situation when a predetermined state change occurs while the vehicle is running,
A voice recognition unit (24) that recognizes the utterance content uttered by the occupant in response to the request of the request unit.
Based on the utterance content of the occupant recognized by the voice recognition unit, the hiyari hat determination unit (32) for determining whether the driving information recorded in the driving information recording unit is a hiyari hat scene,
The running information determined to be a hiyari hat scene by the hiyari hat determination unit and the utterance content used by the hiyari hat determination unit to determine the hiyari hat scene are stored in the non-volatile recording medium (40). The scene recording unit (38) to record and
Equipped with
When recording the utterance content on the non-volatile recording medium, the scene recording unit is configured to record the text data of the utterance content recognized by the voice recognition unit on the non-volatile recording medium. The vehicle's travel recording device. The traveling information recording unit acquires and records the situation of an object existing around the vehicle as one of the traveling information, and records the situation.
The request unit determines the content of the request based on the situation of the object recorded in the travel information recording unit.
The vehicle travel recording device according to claim 1 , which is configured as such. The traveling recording device according to claim 2 , wherein the request unit estimates the causative object of the hiyari hat from the situation of the object, and determines the content of the request based on the estimation result. The travel recording device according to claim 3 , wherein the request unit is configured to estimate a peripheral object closest to the own vehicle as a causative object of a hiyari hat. The traveling recording device according to any one of claims 1 to 4 , wherein the voice recognized by the voice recognition unit as the utterance content of the occupant is limited to words related to the hiyari hat and negative words. It is provided with a primary determination unit (16) for determining whether or not the travel information recorded in the travel information recording unit is a hiyari hat scene based on a change in the state of the vehicle while the vehicle is traveling.
Any one of claims 1 to 5 , wherein the request unit is configured to request the occupant to explain the situation when the primary determination unit determines that the traveling information is a hilarious hat scene. The traveling recording device described in the section. The hiyari hat determination unit obtains a score representing the hiyari hat-likeness based on the utterance content of the occupant recognized by the voice recognition unit, and the primary determination unit determines the hiyari hat scene from the change in the state of the vehicle. The driving recording device according to claim 6 , wherein it is configured to determine whether or not the driving information recorded in the traveling information recording unit is a hilarious hat scene based on a weighted sum obtained by weighting and adding the score used for the calculation. .. As information on the hiyari hat that occurred while the vehicle was running, the information on the hiyari hat was acquired from the recording medium in which the running information including the image around the vehicle and the text data showing the utterance contents of the occupants were recorded, and the hiyari hat scene was browsed. It is a browsing device (50),
An extraction unit (52) that extracts information on a hiyari hat corresponding to a query specified from the outside from the recording medium (40), and an extraction unit (52).
A display unit (54) that displays a hiyari hat scene based on the information of the hiyari hat extracted by the extraction unit, and a display unit (54).
Equipped with
The display unit is a browsing device configured to be able to display a list of the utterance content and the frequency of occurrence of the utterance content based on the text data of the utterance content included in the information of the hiyari hat extracted by the extraction unit. As information on the hiyari hat that occurred while the vehicle was running, the information on the hiyari hat was acquired from the recording medium in which the running information including the image around the vehicle and the text data showing the utterance contents of the occupants were recorded, and the hiyari hat scene was browsed. It ’s a browsing device,
An extraction unit that extracts information on the hiyari hat corresponding to a query specified from the outside from the recording medium, and an extraction unit.
A display unit that displays a hiyari hat scene based on the information of the hiyari hat extracted by the extraction unit, and a display unit that displays the hiyari hat scene.
Equipped with
The extraction unit is a browsing device configured to be able to extract information including text data of utterance contents corresponding to the query by designating the query. As information on the hiyari hat that occurred while the vehicle was running, the information on the hiyari hat was acquired from the recording medium in which the running information including the image around the vehicle and the text data showing the utterance contents of the occupants were recorded, and the hiyari hat scene was browsed. It ’s a browsing device,
An extraction unit that extracts information on the hiyari hat corresponding to a query specified from the outside from the recording medium, and an extraction unit.
A display unit that displays a hiyari hat scene based on the information of the hiyari hat extracted by the extraction unit, and a display unit that displays the hiyari hat scene.
Equipped with
The display unit is a browsing device configured to be able to display the utterance content based on the text data included in the information when displaying the hiyari hat scene from the information of the hiyari hat extracted by the extraction unit.

Images