Recording control device and recording control method

The recording control device dynamically adjusts recording periods based on object detection to capture useful event data, addressing the inefficiencies of fixed period recording and enhancing traffic incident analysis.

JP2024169570AActive Publication Date: 2024-12-05JVC KENWOOD CORP
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2024161067
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-12-05
Estimated Expiration
2040-09-25

AI Technical Summary

Technical Problem

Existing recording technologies struggle to dynamically adjust the period of event video recording in dynamic environments, leading to the inability to capture useful content for understanding traffic troubles and inefficient use of storage capacity.

Method used

A recording control device and method that acquires and analyzes imaging data to detect predetermined objects, such as vehicle license plates, and records relevant data before and after an event occurs, adjusting the recording period based on object detection to include useful content.

Benefits of technology

Effectively records useful content for understanding traffic situations while minimizing data volume, allowing for efficient storage utilization and capturing critical information like vehicle details and witness identities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024169570000001_ABST
    Figure 2024169570000001_ABST
Patent Text Reader

Abstract

To provide a recording control device and a recording control method that can record a useful content for grasping a situation of traffic trouble while suppressing an amount of recorded data.SOLUTION: A recording control device 100 includes: an imaging data acquisition unit 110 that acquires imaging data from an imaging device 200; an event detection unit 130 that detects occurrence of an event; an imaging data analysis unit 120 that analyzes the imaging data and detects a predetermined object included in the imaging data; and a recording control unit 140 that stores first imaging data which is imaging data including a time point at which the event occurs, and a predetermined number of second imaging data selected according to priority from among a plurality of second imaging data which is image capturing data including a time point at which the object is detected within a predetermined range from the time point of event occurrence in association with each other, as event recording data.SELECTED DRAWING: Figure 7
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a recording control device and a recording control method. [Background technology]

[0002] Like a dashcam, it records the video at the time an event occurs as an event video. For example, in such a technology, when an event such as a traffic accident occurs, When an event occurs, video footage from the time period before and after the event is recorded. Generally, a fixed period is used for the duration of the movie. However, there are some movies whose duration is limited by a fixed period. When images do not provide useful information for understanding the situation of traffic accidents and other traffic troubles There is.

[0003] In this regard, Patent Document 1 discloses a method for analyzing and processing the period when there is movement in the image captured by the camera. The present invention discloses a technology for analyzing a period of time by a video processing means and determining that period as the time period of the event video. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2003-69987 A Summary of the Invention [Problem to be solved by the invention]

[0005] According to the technology disclosed in Patent Document 1, the period of the event video to be recorded is dynamically set. However, the technology described in Patent Document 1 is unable to detect periods of motion in the video. In order to capture the period of an event, it is necessary to capture an appropriate event image in a dynamic environment such as on a road. In other words, it is not possible to record the movement of cars and people, or the swaying of trees and other objects caused by the wind. In dynamic environments, it is difficult to obtain appropriate event images, making it difficult to grasp the situation of traffic troubles. Therefore, it is not possible to record information that is useful for understanding the situation of traffic accidents. There is a demand for technology that can record the contents of events. There is also a demand for efficient use of limited storage capacity.

[0006] The object of the present invention is to reduce the amount of recorded data while understanding the situation of traffic troubles. To provide a recording control device and a recording control method capable of recording useful content. do. [Means for solving the problem]

[0007] The recording control device according to the first aspect of the present invention is a recording data acquisition device that acquires image data from an image capture device. An acquisition unit, an event detection unit that detects the occurrence of an event, and an event detection unit that analyzes the photographed data and a photographing data analysis unit that detects a predetermined object captured in the photographing data; The first photographing data is the photographing data including the point and within a predetermined range from the event occurrence time point. The second photographing data is associated with the photographing data including the detection time of the object, and an event is generated. and a recording control unit for storing the recorded data as the target data, When the object is detected, a priority image is selected from the plurality of second photographing data corresponding to the detected object. A predetermined number of the second photographing data selected according to the priority order is associated with the first photographing data. The events are linked together and stored as the event record data.

[0008] In the recording control method according to the second aspect, photographed data is acquired from an imaging device, and a recording Detecting the occurrence of an incident, analyzing the photographic data, and detecting a predetermined object captured in the photographic data; The first photographing data is the photographing data including the time point at which the event occurred, and the time point at which the event occurred The second photographing data is the photographing data including the detection time of the object within a predetermined range from the point. The recorded data is stored as event record data in association with the target object. When the object is detected, a priority image is selected from the plurality of second photographing data corresponding to the detected object. A predetermined number of the second photographing data selected according to the priority order is associated with the first photographing data. The events are linked together and stored as the event record data. Effect of the Invention

[0009] According to the present invention, it is possible to grasp the situation of a traffic trouble while suppressing the amount of data to be recorded. It is possible to provide a recording control device and a recording control method capable of recording useful content. Cut. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a schematic diagram illustrating an example of a configuration of a recording system according to an embodiment. [Diagram 2] 1 is a block diagram showing an example of a hardware configuration of a recording control device according to an embodiment; [Diagram 3] FIG. 11 is a schematic diagram illustrating an event recording according to a comparative example. [Figure 4] 5 is a schematic diagram illustrating storage of event record data in the embodiment. FIG. [Diagram 5] 5 is a schematic diagram illustrating storage of event record data in the embodiment. FIG. [Figure 6] 5 is a flowchart showing an example of the operation of the recording control device according to the embodiment; [Figure 7]5 is a schematic diagram illustrating storage of event record data in the embodiment. FIG. [Figure 8] 5 is a schematic diagram illustrating storage of event record data in the embodiment. FIG. [Figure 9] 5 is a flowchart showing an example of the operation of the recording control device according to the embodiment; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Therefore, the following description and drawings are omitted and simplified as appropriate. In the drawings, the same elements are denoted by the same reference numerals, and duplicated explanations are omitted as necessary. is.

[0012] <Embodiment 1> FIG. 1 is a schematic diagram showing an example of the configuration of a recording system 10 according to an embodiment. The system 10 includes a recording control device 100, an imaging device 200, a recording unit 300, and an acceleration sensor. Includes Sensa 400.

[0013] In this embodiment, the recording system 10 is, for example, a system mounted on a vehicle. In this case, the recording system 10 is also called a drive recorder. For example, it is an automobile that runs on four or more wheels, but it may also be a motorcycle.

[0014] The imaging device 200 is, for example, a camera. The imaging device 200 captures an image of the surroundings of the vehicle. The image capturing device 200 generates image capturing data, which is data of a captured image. It may be a camera that takes pictures of the front or the rear of the vehicle. Alternatively, the imaging device 200 may be a camera that captures an image of the side of the vehicle. Also, one imaging device 200 may be configured to capture images in all directions of the vehicle. The imaging device 200 outputs captured image data to the recording control device 100.

[0015] The recording unit 300 is a storage device that stores the photographed data. Memory cards including flash memory, SSDs (Solid State Drives) or HDDs (Hard Drives) Disk Drives and other non-volatile memory and DDR (Double-Data-Rate Synchronous Dynamic The recording unit 300 is a storage device configured with a volatile memory such as a random access memory (Random Access Memory). The recording unit 300 records the captured image data under the control of the recording control device 100. Along with the shadow data, audio data collected by a microphone (not shown) included in the recording system 10 is In this embodiment, the recording unit 300 may also record audio data. The recording unit 300 is mounted on the vehicle together with the recording control device 100. For example, the recording unit 300 may be a device connected to a mobile phone such as a smartphone. It may be a mobile terminal or an external server.

[0016] The recording section 300 includes a normal recording section 310 and an event recording section 320. 310 is composed of a non-volatile memory and a volatile memory, and temporarily stores data in the volatile memory. The normal recording unit 310 records the captured data in a manner that allows it to be overwritten. In other words, when the storage capacity of the normal recording unit 310 is insufficient, for example, old photographed data is The data is deleted in order from the beginning, and new photographed data can be stored in the freed memory area. The event recording unit 320 is composed of a non-volatile memory. The shadow data is recorded as event record data. This is the photographic data related to the event, and overwriting is prohibited. Even if time has passed, the recorded data will remain in the hard disk unless the user intentionally deletes it. The normal recording unit 310 is a recording area that is predetermined as an overwritable storage area. The event recording unit 320 may be a storage area that is previously defined as a storage area that is prohibited from being overwritten. However, there is no provision for such a storage area. A flag indicating overwrite prohibition is set for data that should not be overwritten. In this case, the recording unit 300 may prohibit overwriting by adding the following: The non-volatile memory of the normal recording unit 310 and the non-volatile memory of the event recording unit 320 are shared. Good too.

[0017] The acceleration sensor 400 is, for example, a three-axis acceleration sensor, and detects the acceleration of the vehicle. The acceleration sensor 400 is installed at a desired location on the vehicle. The acceleration sensor 400 may be built in the recording control device 100. The acceleration applied to the event detector 110 is detected by the event detector 110 of the recording control device 100. The acceleration sensor 400 is a one-axis or It may be a two-axis acceleration sensor.

[0018] The recording control device 100 includes a shooting data acquisition section 110, a shooting data analysis section 120, and an event The recording control device 100 has an event detection unit 130 and a recording control unit 140. The process may be realized, for example, by executing a program. In this case, the recording control device 10 0 has a hardware configuration as shown in FIG. 2, in which a processor 150 By reading and executing software (computer programs) from memory 151 , a photographing data acquisition unit 110, a photographing data analysis unit 120, an event detection unit 130, and a recording unit The control unit 140 performs processing.

[0019] The memory 151 is, for example, a combination of a volatile memory and a non-volatile memory. The memory 151 may include software that includes one or more instructions to be executed by the processor 150. software (computer program), and data used for various processes of the recording control device 100. It is used to store data, etc.

[0020] The processor 150 may be, for example, a microprocessor or MPU (Micro Processor). ssor Unit) or CPU (Central Processing Unit) ), etc. Processor 150 may include multiple processors.

[0021] As shown in FIG. 2, the recording control device 100 is connected to a network in order to communicate with other devices. The network interface 152 may include: For example, it may include a network interface card (NIC).

[0022] In this way, the recording control device 100 may have the functionality of a computer. The above-mentioned program may be stored on various types of non-transitory computer-readable media (e.g., n-transitory computer readable medium) The non-transitory computer-readable medium may be stored on a non-transitory computer-readable medium and provided to a computer. The term refers to various types of tangible storage media. Examples of non-transitory computer readable media include magnetic recording media (e.g., flexi hard disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g. magneto-optical Disk), CD-ROM (Read Only Memory), CD-R, CD-R / W, semiconductor memory (e.g., mask ROM, PROM (Programmable Read Only Memory) M), EPROM (Erasable PROM), Flash ROM, RAM (Ran The program also includes various types of Transitory computer readable medium The temporary computer may be provided with the Examples of data-readable media include electrical signals, optical signals, and electromagnetic waves. The body transmits the program to the computer via wired communication paths such as electric wires and optical fibers, or wireless communication paths. This can be supplied to the computer.

[0023] The following describes the imaging data acquisition unit 110, imaging data analysis unit 120, event detection unit 130, and The process of the recording control unit 140 will now be described.

[0024] The image capturing data acquisition unit 110 acquires image capturing data from the image capturing device 200. That is, The image capturing data acquisition unit 110 acquires image capturing data, which is data of a video captured by the image capturing device 200. Get it.

[0025] The event detection unit 130 detects the occurrence of an event. Specifically, this refers to traffic trouble. Traffic trouble includes not only traffic accidents but also sudden stops. In this embodiment, the event detection unit 130 detects dangerous driving such as acceleration and sudden acceleration. The acceleration of the vehicle in which the recording control device 100 is installed is obtained from the acceleration sensor 400. Based on the acceleration, it is detected whether an event has occurred. Specifically, the event detection unit 1 30 determines that an event has occurred when acceleration equal to or greater than a predetermined threshold is detected.

[0026] The event detection unit 130 may detect the occurrence of an event by other methods. For example, when a switch (not shown) provided on the recording control device 100 is operated, In this case, the user may determine that a vent has occurred. In this case, the recording system 10 operates the switch. 0 may be provided instead of the acceleration sensor 400. The occurrence of an event may be detected based on vehicle control information such as the above.

[0027] When the event detection unit 130 detects the occurrence of an event, it stores the captured image data in the event record database. The event record command signal is output to the record control unit 140 to command the recording control unit 140 to store the event as event data. The event recording command signal may include the time when the occurrence of the event was detected.

[0028] In order to save the scenes in which a specific object is captured as event record data, The data analysis unit 120 analyzes the photographic data and detects a predetermined object captured in the photographic data. When there are multiple image capturing devices 200, the image capturing data analysis unit 120 The imaging data analysis unit 120 performs analysis on each of the imaging data 200. When an object is detected, the camera will display time information indicating when the object was captured in the image. The image capturing data analysis unit 120 notifies the recording control unit 140 of the detected target object. If the photograph is taken, it is necessary to indicate for each object at what time it was captured on the image. The time information may be notified to the recording control unit 140.

[0029] In this embodiment, the predetermined object is a license plate of a vehicle. Not only does it provide footage of the event, but also footage showing the vehicle's license plate number. The data will be stored as a record. This vehicle is used by witnesses of traffic accidents, There is a possibility that the vehicle in question is the vehicle in which the other party in the traffic accident is riding. By storing the video of the vehicle as event record data, it is possible to It can provide clues to identify witnesses or people involved in traffic accidents. It is possible to record information that is useful for understanding the situation of communication troubles.

[0030] The photographing data analysis unit 120 analyzes the photographing data using a known image recognition process. The license plate of the vehicle captured in the image data is detected. In the above, a license plate that is larger than a predetermined size may be detected. Here, the predetermined size is, for example, a size that allows the photographed data analysis unit 120 to recognize the license plate. If the number plate is captured at a size larger than the specified size, the number plate is A vehicle with a number plate is a vehicle that is within a certain distance from the image capture device 200. For this reason, such vehicles are not considered to be vehicles in which the parties or witnesses of traffic accidents are riding. Therefore, it is considered that there is a relatively high possibility that the image is larger than the specified size. By detecting license plates, it is possible to grasp the situation of traffic accidents more easily. Useful content can be recorded.

[0031] The photographing data analysis unit 120 analyzes the photographing data of the video that was photographed before the occurrence of the event. The camera may analyze the data captured on the video after the event occurred. Alternatively, the analysis may be performed on both the input and output signals. In this embodiment, the event recording instruction signal is also output to the imaging data analysis unit 120. When the image capturing data analysis unit 120 receives the event recording instruction signal, the image capturing data analysis unit 120 detects an event. For example, the photographing data analysis unit 120 analyzes the photographing data around the event detection time. Analyze the imaging data for a specified analysis period (e.g., 10 minutes) starting from the timing. The analysis period is set to a value longer than the normal period for event record data (e.g., 30 seconds). It is not necessary to set the analysis period. However, this In this case, the event in which the vehicle was photographed far away from the event detection timing is This means that witnesses to the traffic accident or those involved in the traffic accident may be able to keep track of the incident. Event record data showing vehicles unlikely to be those in which the driver was riding may be saved. do.

[0032] The recording control unit 140 records the shooting data of the video captured by the imaging device 200. When there are multiple image capture devices 200, the recording unit 300 controls the image capture device 200 to record the image. The control unit 140 records the image capture data of each of the image capture devices 200 .

[0033] The recording control unit 140 receives an event recording instruction signal from the event detection unit 130. If not, the photographed data continues to be recorded in the normal recording unit 310. That is, the recording control unit 140 If no event is detected, the image data acquired by the image data acquisition unit 110 is The shadow data is recorded in the normal recording section 310 in an overwritable manner. The continuous recording of the data is called loop recording or normal recording. 0 is the number of times that the event detection unit 130 outputs an event recording command signal to record the captured image data. The event is recorded in the event recording unit 320. That is, the recording control unit 140 In this case, the shooting data including the video at the time of the event is saved as event recording data. For example, the recording control unit 140 may record the captured data regardless of the presence or absence of an event recording instruction signal. The data is recorded in a normal manner, that is, in a loop, and when an event is detected, the normal recording unit 310 Among the stored photographic data, photographic data for a period that should be saved as event record data is The event record data is stored by copying it to the event recording unit 320. At this time, copying may be performed from the volatile memory of the normal recording unit 310 to the event recording unit 320. In addition, the data may be copied from the non-volatile memory of the normal recording unit 310 to the event recording unit 320. Note that saving video as event record data is called event recording.

[0034] During event recording, the recording control unit 140 selects the video to be stored as event recording data. The period is set so as to include the time point when the photographing data analysis unit 120 detects a predetermined object. For example, the photographing data analysis unit 120 adjusts the size of a large object that is equal to or larger than a predetermined size in the image. When detecting a license plate that is captured in the event record, the recording control unit 140 The period of time during which the image is saved as data is the number of times the image is displayed at a size equal to or larger than this specified size. The period is adjusted so as to include the time point when the bar plate is detected. The time information notified from the data analysis unit 120, i.e., the time at which the predetermined object was captured in the image The video is saved as event record data based on the time information indicating whether the video was captured in the event. Determine the time range.

[0035] FIG. 3 is a schematic diagram for explaining an event record according to a comparative example. Assume that an event is detected at tE. In this case, in the event recording according to the comparative example, The photographed data from time tP1 to time tP2 is saved as event record data. Here, the time tP1 is a predetermined time P1 back from the time tE when the event was detected. The time tP2 is a predetermined time from the time tE when the event was detected. The time when the predetermined time P2 has elapsed. Here, the predetermined times P1 and P2 are, for example, several tens of seconds. When such an event is recorded, the event is recorded for a certain period of time, i.e. P1 The photographic data for the period defined as the sum of P1 and P2 is saved as event record data. However, the data captured during this period is not enough to understand the situation of traffic accidents. It doesn't necessarily contain any useful information.

[0036] In contrast, as described above, in this embodiment, the recording control unit 140 The period of time that the image is stored as data is determined based on the time when a specific object, such as a license plate, is detected. The period is adjusted to include the period of traffic accidents. Event record data including the above content can be saved.

[0037] For example, by analyzing the video data taken before the event occurred, When a certain object is detected, the recording control unit 140 sets the event recording data as shown in FIG. The period of video stored as data is the period of detection of the object in question that occurred before the event occurred. FIG. 4 shows how event record data is stored in this embodiment. FIG. 4 is a schematic diagram for explaining the example of the event at time tE. In other words, it is assumed that the recording control unit 140 is performing normal recording, i.e., loop recording. During the shooting, the event detection unit 130 detects an event at time tE. The data analysis unit 120 analyzes the image at time t1, which is the time before the event occurs, and detects an object. In this case, the recording control unit 140 performs the above-mentioned process from time t1 to time t2. The photographed data up to time tP2 is stored as event record data. The start point of the vent record data image is time t1, and the end point is time tP2. The recording control unit 140 may set the start point to a time point a predetermined time before the time t1. In FIG. 4, the time t1 at which the object is detected is before the time tP1. It may be the same as or later than that.

[0038] By adjusting the start point, the period of the image is adjusted to include the time point when a given object was detected. Therefore, it is possible to keep event record data that contains useful information for understanding the situation of traffic accidents. In particular, the detection time of a vehicle captured before the occurrence of an event can be stored. By storing event record data including Evidence footage can be preserved.

[0039] In addition, by analyzing the video data taken after the occurrence of the event, When the object is detected, as shown in FIG. 5, the recording control unit 140 stores the event record data. The period of the video that is saved as data is the detection of the object in question that occurred after the event occurred. FIG. 5 shows how event record data is stored in this embodiment. FIG. 5 is a schematic diagram for explaining the operation of the event detection unit 100 at time tE. In other words, the recording control unit 140 is performing normal recording, i.e., loop recording. During this, the event detection unit 130 detects an event at time tE. The data analysis unit 120 analyzes the image at time t2, which is the time after the event occurs, and finds that the object is not present in the image. In this case, the recording control unit 140 performs the process from the above-mentioned time tP1 to the time The photographed data up to time t2 is stored as event record data. The start point of the image of the recorded data is time tP1, and the end point is time t2. The control unit 140 may set the end point to a time point a predetermined time later than the time t2. In FIG. 5, the time t2 at which the object is detected is after the time tP2. It may be the same or it may be earlier.

[0040] By adjusting the end point, the period of the image is adjusted to include the time point when a given object was detected. Therefore, it is possible to keep event record data that contains useful information for understanding the situation of traffic accidents. In particular, for example, the detection time of a vehicle captured after the occurrence of an event can be stored. By storing event record data to include In addition, it is possible to store video that identifies the parties involved in a dispute after an event is detected. It is also useful for identifying people who witnessed incidents such as a fire or a robbery.

[0041] The recording control unit 140 detects the time when an object was detected before the occurrence of the event, Event recording includes both the time of detection of an object that occurred after the event occurred. For example, the above-mentioned video data from time t1 to time t2 may be stored. Event record data including:

[0042] Next, an example of the operation of the recording control device 100 will be described. An example of the operation of the recording control device 100 will now be described with reference to FIG. An example of the work will be described.

[0043] In step S100, the recording control unit 140 of the recording control device 100 starts normal recording. Normal recording starts when the engine or power of the vehicle in which the recording control device 100 is installed is turned on. That is, the recording control unit 140 controls the image data acquisition unit 1 The photographic data acquired by the camera 10 is continuously recorded in the normal recording unit 310.

[0044] Then, in step S101, the recording control unit 140 detects that the event detection unit 130 It is determined whether an event is detected. If an event is detected, the process proceeds to step S10. 2, and if no event is detected, the process proceeds to step S106.

[0045] In step S102, the photographing data analysis unit 120 calculates the time when the event was detected. The imaging data analysis unit 120 analyzes the imaging data of the event detection type as described above. The video may be analyzed from the period preceding the event detection timing, or from the period following the event detection timing. The image may be analyzed, or both may be analyzed.

[0046] In step S103, the recording control unit 140 detects that the photographing data analysis unit 120 has In other words, the recording control unit 140 determines whether a specific object is detected. It is determined whether the time shown in the image has been specified by the photographing data analysis unit 120. If the time at which the object is captured in the video is identified, the process proceeds to step S104. If not, the process proceeds to step S105.

[0047] In step S104, the recording control unit 140 determines the start point of the video of the event recording data. Or, the end point is adjusted according to the detection result by the photographing data analysis unit 120. As described above, the recording control unit 140 adjusts the start point or end point of an event to improve the event recording speed. The period of the image to be stored as the recorded data includes the time point at which the object was detected. After S104, the process proceeds to step S105.

[0048] In step S105, the recording control unit 140 stores the event record data in the event record In step S104, the recording control unit 140 stores the start point If the start or end point is adjusted, the video of the event recording data is On the other hand, if the process of step S104 is skipped, that is, If the answer is No in step S103, the recording control unit 140 The start and end points specified by P1 and P2 are used to estimate the duration of the video of the event record data. After step S105, the process proceeds to step S106.

[0049] In step S106, the recording control unit 140 turns off the vehicle engine, the power supply, etc. It is judged whether an operation to end normal recording such as the above has been performed. If not, the process returns to S101. In this case, the recording control unit 140 ends normal recording.

[0050] The first embodiment has been described above. According to this embodiment, the recording control unit 140: Event recording includes not only video footage of the event, but also footage of vehicle license plates For this reason, the vehicle in which the witness of the traffic accident was riding, or the traffic It is possible to record the vehicle in which the other party in the trouble is riding. It is possible to record information that is useful for understanding the situation of communication troubles.

[0051] In the above embodiment, the license plate of a vehicle is detected as the predetermined object. However, the vehicle itself may be detected as the predetermined object by analysis using image recognition processing. Also, other characteristic features of the vehicle besides the license plate may be detected.

[0052] <Embodiment 2> Next, a second embodiment will be described. The following describes the differences from the first embodiment. In this embodiment, the same configuration and processing are appropriately omitted. This embodiment differs from the first embodiment in that unit 120 detects a person as a predetermined object.

[0053] That is, in this embodiment, the photographing data analysis unit 120 uses a known image recognition process. The photographed data is then analyzed to detect people who appear in the photographed data. In this embodiment, not only the video at the time of the event occurrence but also the video in which a person is captured is stored as event record data. This person is either a witness to the traffic accident or a party involved in the traffic accident. For this reason, it is necessary to save the video of such a person as event record data. By preserving the information, it becomes possible to identify witnesses to traffic accidents or parties involved in traffic accidents. In other words, it records information that is useful for understanding the situation of traffic troubles. It can be recorded.

[0054] The photographic data analysis section 120 may detect a person's face. This makes it easier to identify people in the video, making it easier to understand the situation of traffic accidents. This will provide more useful information for your research.

[0055] The second embodiment has been described above. According to this embodiment, the recording control unit 140: Not only the video of the event occurrence, but also the video of people in it is saved as event recording data. This makes it possible to record information that is useful for understanding the situation of traffic accidents. It is also possible to combine the first and second embodiments. As specific objects, people and vehicle license plates may be detected.

[0056] Although the first and second embodiments have been described above, Therefore, the following modifications are also possible.

[0057] For example, the photographing data analysis unit 120 detects a plurality of predetermined objects and The time information indicating when the object was captured in the video is sent to the recording control unit 140. When the recording control unit 140 detects the detected file, the recording control unit 140 may perform the following control. The recording control unit 140 determines the period of the video to be stored as the event record data based on the time when the object is in a predetermined state. The predetermined number may be adjusted to include any number equal to or greater than 2. In this way, a video containing multiple objects can be treated as event record data. For example, the occurrence of a traffic accident can be identified from the video of the event record data. When searching for a suspect, it is important to collect witnesses and the license plate numbers of vehicles they may be driving. It is preferable that the number of objects corresponding to the number of candidates for the target is large. By storing the footage, it is possible to obtain more useful footage for understanding the situation of traffic accidents. This can be done.

[0058] <Embodiment 3> In the embodiment described above, the recording control unit 140 determines the time when an event occurs and the time when an object is detected. A series of shooting data for a series of images including both the time and date is regarded as event record data. In contrast, in this embodiment, the recording control unit 140 performs the following steps to store the The period of the video to be stored as vent record data is set to include the time point at which the object was detected. In this embodiment, the recording control unit 140 adjusts the period including the time point when the event occurred. Detection of a target object within a predetermined range from the first photographic data, which is photographic data, and the time when the event occurs The second photographic data is associated with the second photographic data including the time point, and the second photographic data is stored as event record data. Here, the predetermined range is, for example, from the time when the event occurs to the time when the object is detected. In this embodiment, for example, as shown in FIG. The control unit 140 detects the photographic data 20 for a first predetermined period including the time point when the event occurs and the object. The photographing data 21 for a second predetermined period including the time of departure is associated with the photographing data 21 for a second predetermined period including the time of departure and stored as event record data. Here, the photographing data 20 corresponds to the first photographing data described above, and the photographing data 2 1 corresponds to the second shooting data described above.

[0059] In the example shown in FIG. 7, it is assumed that an event is detected at time tE. Assume that an object is detected in the image of 1. In this case, the recording control unit 140 performs the following operations from time tP1 to The shooting data for the period up to time tP2 and the shooting data for the period from time tP3 to time tP4 The data is stored as event record data. Here, the time tP1 is the time when the event is detected. The time tP2 is a time that is a predetermined time P1 back from the time tE when the event The time is the time when a predetermined time P2 has elapsed from the time tE when the event was detected. P3 is a time that is a predetermined time P3 back from time t1. This is the time when a predetermined time P4 has elapsed from time t1. By creating a video of the time an event occurs and the time an object is detected, While storing the captured data from time tP4 to time tP1, it is possible to omit storing the captured data from time tP4 to time tP1. This makes it possible to reduce consumption of storage capacity. According to the report, the amount of recorded data is reduced while providing useful information for understanding the situation of traffic accidents. It is possible to record the detection of an object before an event occurs. However, the same is true for detecting an object after an event has occurred.

[0060] In FIG. 7, an example is shown in which one object is detected, but if multiple objects are detected, In this case, a plurality of second photographing data corresponding to the detected object is associated with the first photographing data. The event record data may be saved with the same name. Figure 8 shows the case where multiple objects are detected. FIG. 8 is a diagram showing an example of how event record data is stored when time tE At time t1, t2, and t3, an event is detected, and the object is In this case, the recording control unit 140 records the object corresponding to the object detected at time t1. Shooting data 21a corresponding to the object detected at time t1, shooting data 21b corresponding to the object detected at time t2, and The photographing data 21c corresponding to the object detected at time t3 is set to correspond to the time when the event occurred. The photographed data 20 is associated with the photographed data 20 to be recorded, and these are stored as one event record data. In this way, when multiple objects are detected, the recording control unit 140 performs the following operations for each of the detected objects. The second photographing data corresponding to each of the first photographing data is associated with the first photographing data to create an event record data. The data may be saved as

[0061] In the example shown in FIG. 8, all the second photographing data corresponding to the detected object is Although the second image data is associated with the first image data, not all of the second image data is necessarily associated with the first image data. In this case, the second imaging data to be associated with the first imaging data may not be associated with the second imaging data. That is, the recording control unit 140 may select the data according to the priority order. When multiple objects are detected, the second image data corresponding to the detected objects are selected in order of priority. A predetermined number of the second photographing data selected according to the rank is associated with the first photographing data to generate an event. For example, the recording control unit 140 may store the event record data when the event occurs. A higher priority is given to the second image data, which corresponds to an object detected closer to the target point. That is, the recording control unit 140 may assign a priority to the object depending on the time of detection of the object. This will increase the likelihood of witnessing the event. Priority can be given to recording high-ranking individuals or vehicles carrying such individuals. For example, the recording control unit 140 may select the second photographing data corresponding to a closer object. In this case, for example, the imaging data analysis unit 12 In addition to detecting the object, the 0 also determines the distance to the object. If the object is a human face, the recording control unit 140 assigns a priority order according to the orientation of the detected face. In this case, for example, the photographing data analysis unit 120 may determine, in addition to detecting the face, Furthermore, the direction of the detected face is determined. Then, the recording control unit 140 refers to the result of this determination. For example, the closer the detected face is to the front, the more the recording control unit 140 detects the face. A higher priority may be given to the second image data at the time of output. When the user faces forward toward the camera 100, the user is looking toward the vehicle in which the image capture device 200 is mounted. This is why priority is given to recording people who are more likely to have witnessed the event. In addition, if the detected face is a frontal face, the person of the detected face can be identified. It also has the advantage of being cheap.

[0062] By the way, in order to reduce the consumption of storage capacity, the second photographed data is the following data: For example, the second photographed data may be a still image at the time when the object is detected. In other words, a still image of the video in which the object was detected is saved as event record data. Also, for example, the second photographing data may have a frame rate higher than that of the first photographing data. The first captured data may be a low-compression moving image, or a moving image compressed at a higher compression rate than the first captured data. In this way, the recording control unit 140 may record a still image, a first image, and a second image as the second photographing data. A video having a lower frame rate than the first captured data, or a video having a higher compression rate than the second captured data. You may also store videos compressed at this rate.

[0063] Next, an example of the operation of the recording control device 100 of this embodiment will be described. 9 is a flowchart showing an example of the operation of the recording control device 100 according to the embodiment. The flowchart shown above mainly differs in that step S104 is replaced by step S114. This is different from the flowchart shown in FIG. 6. The differences will be explained below.

[0064] In the flowchart shown in FIG. 9, the photographing data analysis unit 120 detects a predetermined object. If so (Yes in step S103), the process proceeds to step S114.

[0065] In step S114, the recording control unit 140 records the captured image data including the time point when the event occurred. A first photographing data and a second photographing data including a detection time of an object are photographed. The image is extracted from a series of photographed data. After step S114, the process proceeds to step S105. Migrate.

[0066] When the process moves from step S114 to step S105, Then, the recording control unit 140 records the first shooting data and the second shooting data extracted in step S114. The event recorder 32 associates the shadow data with the event record data. 0. The image data is associated with each other by creating file names that contain a common name. The association may be performed by adding the same to each piece of photography data, or the photography data to be associated may be added to the same piece of photography data. Alternatively, the second image data may be stored in the same folder as the first image data. The new data may be stored in association with the new photographed data as second photographed data.

[0067] On the other hand, if the process of step S114 is skipped, that is, if the process of step S1 If the answer is No in step S103, in step S105, the recording control unit 140 Only this data is stored in the event recording unit 320 as event record data.

[0068] The third embodiment has been described above. According to this embodiment, the recording control unit 140: Photograph data taken at the time an event occurs and separate data taken at the time an object is detected The data to be recorded is then associated with the event record data. It is possible to record useful information for understanding the situation of traffic troubles while keeping the amount of data low. .

[0069] Although the first to third embodiments have been described above, Therefore, the following modifications are also possible.

[0070] In the above-described embodiment, the detection range of the object to be stored as the event record data is as follows: It was a predetermined period (for example, 10 minutes) starting from the event detection timing. The detection range was a uniform time. However, this detection range was changed to the event detection timing. For example, the recording control unit 140 may define the distance from the vehicle position of the vehicle. If an object exists within a certain distance (e.g. 100m) from the point where the event occurred, The recorded video may be stored as event record data. When the vehicle is located a specified distance away from the vehicle's position at the time the event occurred Based on the object detected from the shooting data during the period from the point of the event to the time of the event, Event record data may be stored. The time when the vehicle is present at a position a predetermined distance away" is called the "range definition time" The above-mentioned range definition time is, for example, a time before the event occurs, but The range definition time may be a time before the event occurs. For example, if the distance from a point 100m before the event occurrence point to the event occurrence point is The images of objects detected from the captured data while the vehicle is moving are used as event record data. Similarly, if the range point is after the event has occurred, For example, the vehicle moving from the point of occurrence to a distance of 100 m can be used to capture the image. The video of the detected object can be saved as event record data. For example, the recording control unit 140 may determine whether the vehicle is a recording system. 10 and GPS (Global Positioning System), If there is time series data showing the location information for each time, the range definition time is as follows: In this case, the recording control unit 140 refers to the time series data and identifies the time when the event occurred. Identifying the time when the vehicle was present at a position a predetermined distance away from the vehicle's position at the raw time The range definition time point may also be specified by other methods. For example, the recording control unit 140 may define a range using the vehicle speed information when the event occurs. In this case, the recording control unit 140 may determine the vehicle speed and the time when the event occurred. , and the above-mentioned predetermined distance, the vehicle position at the time of the occurrence of the event is a predetermined distance away. The range definition time may be determined by estimating the time when the vehicle was present at the remote location. In this way, the detected events from the image data during the period from the time the range was specified to the time the event occurred are By storing event record data based on the objects detected, the area around the event occurrence point can be Event record data can be created that focuses on objects on the edges.

[0071] In the above embodiment, after detecting an event, the photographing data analysis unit 120 The photographed data around the time when the event occurred was analyzed. In this case, for example, the imaging data analysis unit 120 indicates at what point in time the object was captured in the image each time an object was detected. The time information is notified to the recording control unit 140. Then, the recording control unit 140 detects an event. Then, based on the time information from the photographing data analysis unit 120, the image of the event record data is Determine the period of the image.

[0072] In the above-described embodiment, the recording system 10 is a system mounted on a vehicle. Although the recording system 10 has been described above, it is not necessary that the recording system 10 is mounted on a vehicle. The device 200 may be a surveillance camera that captures images of a road such as an intersection. In this case, the recording system 10 does not require the acceleration sensor 400, and instead, The event detection unit 130 detects an event by analyzing the captured data using, for example, image recognition processing. For example, by analyzing the captured image data, it is possible to detect collisions between objects such as vehicles. Alternatively, the event detection unit 130 may detect the occurrence of an event by outputting a The image capturing device 200 analyzes sounds around the road to be captured and detects the occurrence of an event. For example, the occurrence of an event may be detected by detecting a collision sound of a predetermined volume or greater. stomach.

[0073] The present invention is not limited to the above-described embodiments and their modifications. Modifications can be made as appropriate without departing from the spirit of the invention.

[0074] A part or all of the above-described embodiments can be described as follows, but is not limited to the following: I can't. (Appendix 1) an imaging data acquisition unit that acquires imaging data from an imaging device; an event detection unit that detects the occurrence of an event; The photographing data is analyzed to detect a predetermined object captured in the photographing data. A data analysis unit; The first photographing data is the photographing data including the time point of the event, and the event occurrence time The second imaging data is the imaging data including the detection time of the object within a predetermined range from the detection time. A recording control unit that associates the event data with the event data and stores it as event record data. A recording control device having the above configuration. (Appendix 2) When a plurality of objects are detected, the recording control unit The second photographing data and the first photographing data are associated with each other to record the event. Save as recorded data 2. A recording control device as described in appendix 1. (Appendix 3) When a plurality of objects are detected, the recording control unit A predetermined number of the second photographing data are selected according to a priority order from among the plurality of the second photographing data. The photographing data and the first photographing data are associated with each other and stored as the event record data. R 2. A recording control device as described in appendix 1. (Appendix 4) The recording control unit records, as the second photographing data, a still image, a video having a lower frame rate than the first captured data, or a video compressed at a higher compression rate than the first captured data. Save the video 4. A recording control device according to claim 1 , (Appendix 5) The recording control unit detects the event occurring within a predetermined distance range from the vehicle position at the time of the event occurrence. Detecting from the photographic data during the period from when the vehicle entered to when the event occurred and storing the event record data based on the object. 5. A recording control device according to claim 1 . (Appendix 6) Acquire photographic data from an imaging device; Detects the occurrence of an event, Analyzing the photographic data to detect a predetermined object captured in the photographic data; The first photographing data is the photographing data including the time point of the event, and the event occurrence time The second imaging data is the imaging data including the detection time of the object within a predetermined range from the detection time. data and save it as event record data Recording control method. (Appendix 7) An imaging data acquisition step of acquiring imaging data from an imaging device; an event detection step of detecting an occurrence of an event; The photographing data is analyzed to detect a predetermined object captured in the photographing data. a data analysis step; The first photographing data is the photographing data including the time point of the event, and the event occurrence time The second imaging data is the imaging data including the detection time of the object within a predetermined range from the detection time. a recording control step for associating the event data with the event data and storing the data as event record data; A program that causes a computer to execute the following. [Explanation of symbols]

[0075] 10. Recording System 20 Shooting data 21 Shooting data 100 Recording control device 110 Shooting data acquisition unit 120 Shooting Data Analysis Section 130 Event detection unit 140 Recording control section 150 processors 151 Memory 152 Network Interface 200 Imaging device 300 Recording Department 310 Normal Recording Section 320 Event Recording Department 400 Accelerometer

Claims

1. an imaging data acquisition unit that acquires imaging data from an imaging device; an event detection unit that detects the occurrence of an event; The photographing data is analyzed to detect a predetermined object captured in the photographing data. A data analysis unit; The first photographing data is the photographing data including the time point of the event, and the event occurrence time The second image data is the image data including the detection time of the object within a predetermined range from the detection time. a recording control unit that associates the event data with the event record data and stores the event record data; When a plurality of objects are detected, the recording control unit A predetermined number of the second photographing data are selected according to a priority order from among the plurality of the second photographing data. storing the shadow data and the first photographing data as the event record data in association with each other; Recording control device.

2. When a plurality of objects are detected, the recording control unit A predetermined number of the second photographing data are selected according to a priority order from among the plurality of the second photographing data. The photographing data and the first photographing data are associated with each other and stored as the event record data. R, The recording control device according to claim 1 .

3. The recording control unit records a still image as the second photographing data, a video having a lower frame rate than the first captured data, or a video compressed at a higher compression rate than the first captured data. Save the video 3. The recording control device according to claim 1 or 2.

4. Acquire photographic data from an imaging device; Detects the occurrence of an event, Analyzing the photographic data to detect a predetermined object captured in the photographic data; The first photographing data is the photographing data including the time point of the event, and the event occurrence time The second photographing data includes the detection time of the object within a predetermined range from the detection time of the second photographing data. The data is associated with the event and saved as event record data. When a plurality of objects are detected, the recorded data includes the object corresponding to the detected object. A predetermined number of the second photographing data are selected according to a priority order from among the plurality of the second photographing data. The photographing data and the first photographing data are associated with each other and stored as the event record data. R, Recording control method.

Citation Information

Patent Citations

  • Video editing program, and video editing device

    JP2010232814A

  • Image recording device, image recording method, and image recording program

    JP2019028760A

  • Image recording device, image recording method, and image recording program

    JP2019028761A

  • Search support device, search support method and search support system

    JP2019036872A

  • Drive recorder, display control method, and program

    JP2019191639A