Vehicle accident detection device

Abstract

A vehicle accident detecting device (2) comprises: a sound source position estimating unit (S210 to S250, S1110 to S1180); a vehicle body exterior determining unit (S260 to S330, S1190 to S1220); and a collision determining unit (S410, S450, S460, S480, S520 to S550). The sound source position estimating unit is configured to estimate an estimated sound source position, which is the position of a sound source, on the basis of the detection results of a plurality of sound detecting units (31 to 34) installed in the vehicle and configured to detect sound. The vehicle body exterior determining unit is configured to determine whether the estimated sound source position is on the vehicle body exterior of the vehicle. The collision determining unit is configured to determine that a collision accident has occurred if the vehicle body exterior determining unit determines that the estimated sound source position is on the vehicle body exterior.

Description

Cross-reference to related applications

[0001] This international application claims the benefit of Japanese Patent Application No. 2023-127856, filed with the Japan Patent Office on August 4, 2023, the entire disclosure of which is incorporated herein by reference.

Technical Field

[0002] The present disclosure relates to a vehicle accident detection device that detects collision accidents in a vehicle.

Background Art

[0003] Patent Document 1 describes a sound detection device that detects surrounding objects by obtaining the phase correlation of sound signals collected by two or more sound collection units, and determines whether a surrounding object is approaching or departing based on the degree of phase fluctuation.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

[0005] As a result of the inventors' detailed examination, it has been found that the technique described in Patent Document 1 has a problem that a collision accident in a vehicle cannot be detected because the distance to the sound source (i.e., the sound source) cannot be calculated.

[0006] The present disclosure detects a collision accident in a vehicle.

[0007] One aspect of the present disclosure is a vehicle accident detection device including a sound source position estimation unit, a vehicle outer contour determination unit, and a collision determination unit.

[0008] The sound source position estimation unit is configured to estimate a sound source estimation position, which is the position of the sound source, based on the detection results of a plurality of sound detection units configured to detect sound and installed in the vehicle.

[0009] The vehicle body exterior determination unit is configured to determine whether or not the estimated sound source location is on the exterior of the vehicle body.

[0010] The collision detection unit is configured to determine that a collision has occurred when the vehicle body exterior detection unit determines that the estimated sound source location is on the vehicle body exterior.

[0011] The vehicle accident detection device of this disclosure, configured in this manner, can detect collision accidents in a vehicle using a plurality of sound detection units installed in the vehicle. [Brief explanation of the drawing]

[0012] [Figure 1] This is a block diagram showing the configuration of the accident information collection system. [Figure 2] This is a block diagram showing the configuration of a vehicle accident detection system. [Figure 3] This is a diagram illustrating the sound source location estimation method of the first embodiment. [Figure 4] This is a functional block diagram showing the functional configuration of the vehicle accident detection device according to the first embodiment. [Figure 5] This flowchart shows the accident detection process of the first embodiment. [Figure 6] This is a flowchart showing the sound source location estimation process of the first embodiment. [Figure 7] This is a diagram illustrating the first external determination criterion. [Figure 8] This is a diagram illustrating the second external determination criterion. [Figure 9] This is a flowchart showing the collision detection process of the first embodiment. [Figure 10] This is a flowchart showing the process for determining specific operations. [Figure 11] This is a flowchart showing the filter setting process. [Figure 12] This figure illustrates the sound source location estimation method of the second embodiment. [Figure 13]It is a functional block diagram showing the functional configuration of the vehicle accident detection device according to the second embodiment. [Figure 14] It is a flowchart showing the accident detection process according to the second embodiment. [Figure 15] It is a flowchart showing the sound source position estimation process according to the second embodiment. [Figure 16] It is a diagram for explaining the sound source position estimation method according to the third embodiment. [Figure 17] It is a functional block diagram showing the functional configuration of the vehicle accident detection device according to the third embodiment. [Figure 18] It is a flowchart showing the accident detection process according to the third embodiment. [Figure 19] It is a flowchart showing the collision determination process according to the third embodiment. [Figure 20] It is a diagram for explaining the sound source position estimation method according to another embodiment. [Mode for Carrying Out the Invention]

[0013] [First Embodiment] The first embodiment of the present disclosure will be described below with reference to the drawings.

[0014] As shown in FIG. 1, the accident information collection system 1 of the present embodiment includes a plurality of vehicle accident detection devices 2 and an accident information server 3.

[0015] The vehicle accident detection device 2 is mounted on a vehicle and has a function of performing data communication with the accident information server 3 via a wide area wireless communication network NW.

[0016] The accident information server 3 acquires accident information, which will be described later, from the vehicle accident detection device 2 via the wide area wireless communication network NW. The accident information server 3 includes an accident information storage unit 4 that stores accident information.

[0017] As shown in Figure 2, the vehicle accident detection device 2 comprises a control unit 11, a CAN communication unit 12, a storage unit 13, and a communication unit 14. CAN stands for Controller Area Network. CAN is a registered trademark.

[0018] The control unit 11 is an electronic control unit centered around a microcomputer equipped with a CPU 21, ROM 22, RAM 23, etc. The various functions of the microcomputer are realized by the CPU 21 executing a program stored in a non-transitional physical recording medium. In this example, ROM 22 corresponds to the non-transitional physical recording medium that stores the program. Furthermore, the execution of this program executes the method corresponding to the program. Note that some or all of the functions executed by the CPU 21 may be configured hardware-wise by one or more ICs, etc. Also, the number of microcomputers that make up the control unit 11 may be one or more.

[0019] The CAN communication unit 12 is connected to multiple ECUs via communication lines to enable data communication and transmits and receives data according to the CAN communication protocol. Specifically, the multiple ECUs connected to the CAN communication unit 12 include an engine ECU for engine control, a brake ECU for brake control, a steering ECU for steering control, a suspension ECU for suspension control, and an ECU for controlling the on / off state of the lights. In Figure 2, only ECU111, ECU112, and ECU113 are shown as ECUs connected to the CAN communication unit 12.

[0020] The memory unit 13 is a memory device for storing various types of data.

[0021] The communications unit 14 communicates data with the accident information server 3 via the wide-area wireless communication network NW.

[0022] As shown in Figure 3, microphones 31, 32, 33, and 34 are installed in the vehicle. Microphones 31, 32, 33, and 34 receive sound waves as input and convert them into electrical signals (hereinafter referred to as sound wave electrical signals) that indicate the time change in the amplitude of the input sound waves, and output them.

[0023] In this embodiment, microphone 31 is installed, for example, on the left side of the dashboard; microphone 32 is installed, for example, on the right side of the dashboard; microphone 33 is installed, for example, at the rear of the cargo area; and microphone 34 is positioned, for example, in the center of the ceiling. Microphones 31, 32, and 33 are installed so as to be located on the same horizontal plane as each other.

[0024] Microphones 31-34 are positioned at different locations. As a result, there is a difference in the phase of the sound waves detected by microphones 31-34, which detect sound waves generated by sound source SS1. This difference in sound wave phase can be considered as the difference in distance from sound source SS1 to microphones 31-34. The sound wave electrical signals ES1, ES2, ES3, and ES4 in Figure 3 are the signals output by microphones 31, 32, 33, and 34 when they detect sound waves generated by sound source SS1, respectively.

[0025] Therefore, for the pair of microphones 31 and 32, a curve L1 (hereinafter referred to as the distance difference curve) can be calculated based on the difference in distance to the sound source SS1, passing over multiple points where the difference in distance to the sound source SS1 is equal. Similarly, for the pair of microphones 32 and 33, a distance difference curve L2 can be calculated based on the difference in distance to the sound source SS1. Furthermore, for the pair of microphones 31 and 33, a distance difference curve L3 can be calculated based on the difference in distance to the sound source SS1. Typically, two distance difference curves are calculated for a pair consisting of two microphones, which are curves that pass over multiple points where the difference in distance to the sound source SS1 is equal. Of the two distance difference curves for a pair, the one estimated to pass through the sound source SS1 can be selected by identifying which of the two microphones detected the sound wave at an earlier timing.

[0026] The vehicle accident detection device 2 then estimates the two-dimensional position (hereinafter referred to as the two-dimensional position) of the sound source SS1 by the point where two pairs of distance difference curves (for example, distance difference curves L1 and L2) intersect, or by the region enclosed by three pairs of distance difference curves (i.e., distance difference curves L1, L2, and L3).

[0027] Furthermore, if there are no measurement errors in the distance difference curves L1, L2, and L3, the distance difference curves L1, L2, and L3 intersect at the position of the sound source SS1. In this case, the vehicle accident detection device 2 can estimate the intersection point of the three distance difference curves L1, L2, and L3 as a two-dimensional position at the sound source SS1.

[0028] Based on a similar approach, by using microphone 34 in addition to microphones 31, 32, and 33, the vehicle accident detection device 2 can estimate the three-dimensional position (hereinafter referred to as the three-dimensional position) of the sound source SS1.

[0029] Furthermore, if the position of the sound source SS1 can be estimated, the distance from microphones 31-34 to the sound source SS1 can also be estimated, allowing the vehicle accident detection device 2 to estimate the timing of the detected sound wave generation.

[0030] As shown in Figure 4, the vehicle accident detection device 2 comprises a vehicle information acquisition unit 41, a sound acquisition unit 42, a sound analysis unit 43, a video acquisition unit 44, a video analysis unit 45, an accident detection control unit 46, a collision determination unit 47, and an upload unit 48, as functional blocks realized by the CPU 21 executing a program stored in the ROM 22.

[0031] The vehicle information acquisition unit 41 constantly acquires vehicle information from multiple ECUs via the CAN communication unit 12, as indicated by arrow A1. The vehicle information includes, for example, vehicle speed, engine speed, steering wheel angle, brake opening angle, parking brake on / off status, shift position, window on / off status, door lock / unlock status, and turn signal on / off status.

[0032] The vehicle information acquisition unit 41 also continuously acquires acceleration information, which indicates the acceleration detected by the acceleration sensor 35 mounted on the vehicle, as shown by arrow A2.

[0033] The sound acquisition unit 42 continuously acquires sound wave electrical signals from microphones 31 to 34, as indicated by arrows A3, A4, A5, and A6. Based on the sound waves indicated by the acquired sound wave electrical signals, the sound acquisition unit 42 detects sounds that may have been generated by an object colliding with the vehicle (hereinafter referred to as "collision candidate sounds").

[0034] When the sound acquisition unit 42 detects a candidate collision sound, it outputs sound wave data showing the time change in the amplitude of the sound wave corresponding to the candidate collision sound to the sound analysis unit 43, as indicated by arrow A7.

[0035] The sound analysis unit 43 estimates the location of the collision candidate sound source and the timing of the collision candidate sound's occurrence by analyzing the sound waves indicated by the sound wave data acquired from the sound acquisition unit 42.

[0036] As indicated by arrow A8, the sound analysis unit 43 notifies the sound acquisition unit 42 of the location of the collision candidate sound source and the timing of the collision candidate sound's generation.

[0037] When the sound acquisition unit 42 detects a potential collision sound, it notifies the accident detection control unit 46 of the location of the sound source of the potential collision sound, the timing of the occurrence of the potential collision sound, and the waveform of the potential collision sound, as indicated by arrow A9.

[0038] The video acquisition unit 44 continuously acquires video data generated by cameras 36 and 37 mounted on the vehicle, as indicated by arrows A10 and A11. The cameras 36 and 37 are installed so as to be able to capture at least the outside of the vehicle.

[0039] The video acquisition unit 44 outputs the acquired video data to the video analysis unit 45, as indicated by arrow A12.

[0040] The video analysis unit 45 analyzes the video data acquired from the video acquisition unit 44 and determines whether or not an object has come into contact with the vehicle. As indicated by arrow A13, the video analysis unit 45 notifies the video acquisition unit 44 of the determination result regarding the presence or absence of an object that has come into contact with the vehicle.

[0041] When the accident detection control unit 46 receives notification of a potential collision sound from the sound acquisition unit 42, it acquires vehicle information, acceleration information, and video data at the timing of the generation of the potential collision sound, as indicated by arrows A14 and A15.

[0042] After acquiring vehicle information, acceleration information, and video data, the accident detection control unit 46 outputs a collision determination request to the collision determination unit 47, as indicated by arrow A16.

[0043] When the collision determination unit 47 receives a collision determination request from the accident detection control unit 46, it obtains vehicle body information from the vehicle body information storage unit 49, as indicated by arrow A17. The vehicle body information is information indicating the coordinate position of the vehicle body's outer casing.

[0044] The collision determination unit 47 determines whether or not an object has collided with the vehicle based on vehicle information, acceleration information, video data, and vehicle body information.

[0045] The collision determination unit 47 notifies the accident detection control unit 46 of the determination result, which determines whether or not an object has collided with the vehicle, as indicated by arrow A18.

[0046] Based on the judgment result obtained from the collision judgment unit 47, the accident detection control unit 46 generates accident information, including acquired vehicle information and video data, when an object collides with the vehicle. As indicated by arrow A19, the accident detection control unit 46 stores the generated accident information in the temporary storage unit 50.

[0047] After storing accident information in the temporary storage unit 50, the accident detection control unit 46 outputs an upload instruction to the upload unit 48, as indicated by arrow A20.

[0048] When the upload unit 48 receives an upload instruction from the accident detection control unit 46, it retrieves accident information from the temporary storage unit 50, as indicated by arrow A21. The upload unit 48 then uploads the retrieved accident information to the accident information server 3. As a result, the accident information server 3 stores the uploaded accident information in the accident information storage unit 4.

[0049] Next, the procedure for the accident detection process performed by the control unit 11 will be described. The accident detection process is a process that is repeatedly performed while the vehicle accident detection device 2 is in operation. In this embodiment, for the sake of simplicity, we will show a configuration in which accidents are detected using microphones 31, 32, and 33.

[0050] When the accident detection process is executed, the CPU 21 of the control unit 11 detects a potential collision sound in S10, as shown in Figure 5. Specifically, the CPU 21 determines that a potential collision sound has been detected if the amplitude of the sound wave indicated by the sound wave electrical signal acquired from microphones 31 to 33 is equal to or greater than a preset collision sound determination value. Note that the CPU 21 may perform filtering from the sound wave waveform to exclude sounds that are not likely to be collision sounds before determining whether or not the amplitude of the sound wave is equal to or greater than the collision sound determination value.

[0051] In S20, CPU21 determines whether or not a collision candidate sound has been detected based on the detection results from S10. If no collision candidate sound has been detected, CPU21 terminates the accident detection process.

[0052] On the other hand, if a collision candidate sound is detected, the CPU 21 executes the sound source location estimation process described later in S30. In the sound source location estimation process, the CPU 21 estimates the location of the sound source of the collision candidate sound (hereinafter referred to as the estimated sound source location) and the timing of the occurrence of the collision candidate sound (hereinafter referred to as the sound occurrence timing).

[0053] CPU21 acquires vehicle information near the sound generation timing in S40. Near the sound generation timing refers to the time range from a predetermined acquisition time before the sound generation timing (e.g., 1 second before) to a predetermined acquisition time after the sound generation timing (e.g., 1 second after).

[0054] CPU21 acquires acceleration information near the sound generation timing in S50.

[0055] CPU21 acquires video data near the sound generation timing using S60.

[0056] In S70, CPU21 executes the collision detection process described later. In the collision detection process, CPU21 determines whether or not an object has collided with the vehicle.

[0057] In S80, CPU21 determines whether a collision has occurred based on the result of S70. If no collision has occurred, CPU21 terminates the accident detection process.

[0058] On the other hand, if a collision occurs, the CPU 21 generates the above-mentioned accident information in S90 and stores the generated accident information in the temporary storage unit 50.

[0059] CPU21 retrieves the accident information generated by S90 from the temporary storage unit 50 using S100, and uploads the retrieved accident information to the accident information server 3.

[0060] Once the processing of S100 is complete, CPU21 terminates the accident detection process.

[0061] Next, we will explain the procedure for the sound source location estimation process performed in S30.

[0062] When the sound source location estimation process is executed, the CPU 21 determines in S210 whether or not the above distance difference curve has been calculated for all pairs of microphones 31, 32, and 33, as shown in Figure 6. In this embodiment, all pairs are the pair of microphone 31 and microphone 32, the pair of microphone 32 and microphone 33, and the pair of microphone 31 and microphone 33.

[0063] If there are any pairs for which the distance difference curve has not been calculated, CPU21 selects one of the pairs for which the distance difference curve has not been calculated in S220, and calculates the phase difference between the two sound waves detected by the two microphones that make up the selected pair.

[0064] CPU21, in S230, calculates the difference in distance from the sound source to the two microphones that make up the selected pair, based on the phase difference calculated in S220.

[0065] In S240, CPU21 calculates an equation representing a distance difference curve that passes over multiple points where the distance difference from the two microphones constituting the selected pair to the sound source is equal, based on the distance difference calculated in S230, and then proceeds to S210.

[0066] If distance difference curves are calculated for all pairs in S210, CPU21 estimates the coordinate position where the distance difference curves for all pairs are closest as the sound source estimation position in S250.

[0067] In S260, the CPU 21 determines whether the above vehicle information is stored in the vehicle information storage unit 49. If the vehicle information is stored, the CPU 21 retrieves the vehicle information from the vehicle information storage unit 49 in S270.

[0068] CPU21 determines in S280 whether the first outer enclosure determination condition is met.

[0069] As shown in Figure 7, the vehicle body information includes coordinate position information of multiple points (hereinafter referred to as outer body points) P1, P2, ..., P29, P30 set on the surface of the outer body VS.

[0070] The first boundary determination condition is that both the following boundary point determination condition and boundary line determination condition are met.

[0071] The boundary point determination condition is that the distance between the estimated sound source position estimated in S250 and the nearest boundary point to this estimated sound source position is less than or equal to a predetermined boundary point determination distance.

[0072] The boundary line determination condition is that the distance between the estimated sound source position estimated in S250 and the boundary line closest to the estimated sound source position among multiple boundary lines connecting two adjacent boundary points is less than or equal to a predetermined boundary line determination distance.

[0073] For example, the outer boundary point determination condition is met when the distance d between the sound source SS2 shown in Figure 7 and the outer boundary point P21 closest to the sound source SS2 is less than or equal to the outer boundary point determination distance.

[0074] Furthermore, the boundary line determination condition is met when the distance h between the sound source SS2 shown in Figure 7 and the boundary line SL1 connecting boundary points P20 and P21 is less than or equal to the boundary line determination distance.

[0075] As shown in Figure 6, if the first outer shell determination condition is met in S280, the CPU 21 determines in S290 that the sound source estimated position in S250 is near the vehicle body outer shell, and terminates the sound source position estimation process.

[0076] On the other hand, if the first outer enclosure determination condition is not met in S280, the CPU 21 determines in S300 that the sound source estimated location in S250 is not near the vehicle body enclosure, and terminates the sound source location estimation process.

[0077] If no vehicle information is stored in S260, the CPU 21 determines in S310 whether the second outer enclosure determination condition is met.

[0078] The second outer boundary determination condition is that all of the following distance determination conditions—the first, second, and third—are met.

[0079] The first distance determination condition is that distance ΔA is X1 to X2 times distance AB, distance ΔB is X3 to X4 times distance AB, and distance ΔA is X5 to X6 times distance ΔB.

[0080] The second distance determination condition is that distance ΔB is Y1 to Y2 times distance BC, distance ΔC is Y3 to Y4 times distance BC, and distance ΔB is Y5 to Y6 times distance ΔC.

[0081] The third distance determination condition is that distance ΔC is Z1 to Z2 times distance CA, distance ΔA is Z3 to Z4 times distance CA, and distance ΔC is Z5 to Z6 times distance ΔA.

[0082] As shown in Figure 8, distance ΔA is the distance between microphone 31 and sound source SS2. Distance ΔB is the distance between microphone 32 and sound source SS2. Distance ΔC is the distance between microphone 33 and sound source SS2. Distance AB is the distance between microphone 31 and microphone 32. Distance BC is the distance between microphone 32 and microphone 33. Distance CA is the distance between microphone 33 and microphone 31.

[0083] The first distance determination condition is that when a triangle is formed with the positions of microphone 31, microphone 32, and sound source SS2 as vertices, the lengths of the three sides constituting the triangle fall within a certain range. The above X1 to X6 are set so that the lengths of the three sides constituting the triangle fall within a certain range.

[0084] The second distance determination condition is that when a triangle is formed with the positions of microphone 32, microphone 33, and sound source SS2 as its vertices, the lengths of the three sides constituting the triangle fall within a certain range. The above Y1 to Y6 are set so that the lengths of the three sides constituting the triangle fall within a certain range.

[0085] The third distance determination condition is that when a triangle is formed with the positions of microphone 33, microphone 31, and sound source SS2 as its vertices, the lengths of the three sides constituting the triangle fall within a certain range. The above Z1 to Z6 are set so that the lengths of the three sides constituting the triangle fall within a certain range.

[0086] As shown in Figure 6, if the second outer casing determination condition is met in S310, the CPU 21 determines in S320 that the sound source estimated position in S250 is near the vehicle body outer casing, and terminates the sound source position estimation process.

[0087] On the other hand, if the second outer casing determination condition is not met in S310, the CPU 21 determines in S330 that the sound source estimated location in S250 is not near the vehicle body outer casing, and terminates the sound source location estimation process.

[0088] Next, we will explain the procedure for collision detection processing performed in S70.

[0089] When collision detection processing is executed, the CPU 21 determines in S410 whether the estimated sound source location is near the vehicle body, as shown in Figure 9. If the estimated sound source location is not near the vehicle body, the CPU 21 proceeds to S490.

[0090] On the other hand, if the estimated sound source location is near the vehicle's outer shell, the CPU 21 acquires acceleration information near the sound generation timing in S420.

[0091] CPU21 acquires video data near the sound generation timing in S430 and analyzes the acquired video data to determine whether or not an object came into contact with the vehicle near the estimated sound source location.

[0092] CPU21 acquires vehicle information near the sound generation timing in S440.

[0093] In S450, CPU21 determines whether the acceleration information obtained in S420 is equal to or greater than a preset collision detection acceleration. If the acceleration is less than the collision detection acceleration, CPU21 proceeds to S490.

[0094] On the other hand, if the acceleration is greater than or equal to the collision detection acceleration, the CPU 21, in S460, determines, based on the determination result in S430, whether or not there is video footage of an object that came into contact with the vehicle near the estimated sound source location in the video data acquired in S430.

[0095] If there is no video footage of an object that has come into contact with the vehicle near the estimated sound source location, the CPU 21 proceeds to S490. On the other hand, if there is video footage of an object that has come into contact with the vehicle near the estimated sound source location, the CPU 21 executes the specific operation determination process described later in S470.

[0096] In S480, CPU21 determines whether a specific operation described later is in progress, based on the result of the determination in S470. If a specific operation is in progress, CPU21 proceeds to S490.

[0097] When the process transitions to S490, CPU21 determines that the collision candidate sound detected in S10 is not caused by a collision and terminates the collision detection process.

[0098] If no specific operation is currently being performed in S480, CPU21 executes the filter setting process described later in S500.

[0099] CPU21 analyzes the waveform of the sound wave after performing the filter setting process in S500 at S510 to determine whether or not it has the characteristics of a collision sound and whether or not it has the characteristics of a non-collision sound.

[0100] In S520, CPU21 determines, based on the judgment result in S510, whether or not the sound waves near the sound generation timing have the characteristics of a non-collision sound. If the characteristics of a non-collision sound are present, CPU21 proceeds to S550. Examples of non-collision sounds include vehicle operation sounds generated by actions performed by the driver inside the vehicle (for example, the sound of operating the handbrake) and speech.

[0101] On the other hand, if there are no non-collision sound characteristics, CPU 21, in S530, determines whether or not the sound waves near the sound generation timing have collision sound characteristics based on the judgment result in S510. If there are no collision sound characteristics, CPU 21 proceeds to S550. On the other hand, if there are collision sound characteristics, CPU 21 proceeds to S540.

[0102] When the process transitions to S540, CPU21 determines that the collision candidate sound detected in S10 is caused by a collision and terminates the collision detection process.

[0103] When the process transitions to S550, CPU21 determines that the collision candidate sound detected in S10 is not caused by a collision and terminates the collision detection process.

[0104] Next, the procedure for the specific operation determination process executed in S470 will be explained.

[0105] When the specific operation determination process is executed, the CPU 21, as shown in Figure 10, determines in S610 whether it is the timing to switch the parking brake based on vehicle information near the sound generation timing. If it is the timing to switch the parking brake, the CPU 21 proceeds to S660. On the other hand, if it is not the timing to switch the parking brake, the CPU 21, in S620, determines whether it is the timing to switch the gear shift based on vehicle information near the sound generation timing.

[0106] If it is time to switch gears, CPU21 switches to S660. On the other hand, if it is not time to switch gears, CPU21, in S630, determines whether or not it is time to switch windows based on vehicle information near the sound generation timing.

[0107] If it is time for a window switch, CPU21 switches to S660. On the other hand, if it is not time for a window switch, CPU21, in S640, determines whether or not it is time for a door lock switch based on vehicle information near the sound generation timing.

[0108] If it is time for a door lock switch, CPU21 switches to S660. On the other hand, if it is not time for a door lock switch, CPU21 switches to S650.

[0109] When the system switches to S650, CPU21 determines that the driver is not performing a specific operation and terminates the specific operation determination process.

[0110] When the system switches to S660, CPU21 determines that the driver is performing a specific operation and terminates the specific operation determination process.

[0111] Next, we will explain the procedure for the filter setting process performed on the S500.

[0112] When the filter setting process is executed, the CPU 21 determines in S710 whether the vehicle is backing up or not based on vehicle information near the sound generation timing, as shown in Figure 11. If the vehicle is not backing up, the CPU 21 proceeds to S730. On the other hand, if the vehicle is backing up, the CPU 21 performs a filter process in S720 to exclude the backing up warning sound from the sound wave data near the sound generation timing, and then proceeds to S730.

[0113] When the process moves to S730, the CPU 21 determines whether the vehicle's turn signal is activated based on vehicle information near the sound generation timing. If the vehicle's turn signal is not activated, the CPU 21 moves to S750. On the other hand, if the vehicle's turn signal is activated, the CPU 21 performs a filter process in S740 to exclude the turn signal sound from the sound wave data near the sound generation timing, and then moves to S750.

[0114] When the process moves to S750, the CPU 21 determines whether the driver has operated the parking brake based on vehicle information near the sound generation timing. If the driver has not operated the parking brake, the CPU 21 moves to S770. On the other hand, if the driver has operated the parking brake, the CPU 21 performs a filter process in S760 to exclude the parking brake switching sound from the sound wave data near the sound generation timing, and then moves to S770.

[0115] When the process moves to S770, the CPU 21 determines whether the driver opened or closed the window based on vehicle information near the sound generation timing. If the driver did not open or close the window, the CPU 21 moves to S790. On the other hand, if the driver did open or close the window, the CPU 21 performs a filter process in S780 to exclude the window opening / closing sound from the sound wave data near the sound generation timing, and then moves to S790.

[0116] When the process moves to S790, the CPU 21 determines whether the driver has locked the doors based on vehicle information near the sound generation timing. If the driver has not locked the doors, the CPU 21 moves to S810. On the other hand, if the driver has locked the doors, the CPU 21 performs a filter process in S800 to exclude door lock opening and closing sounds from the sound wave data near the sound generation timing, and then moves to S810.

[0117] When the process transitions to S810, the CPU 21 determines whether the estimated sound source location is near the driver's head and whether it is near the vehicle's speakers. If the estimated sound source location is neither near the driver's head nor near the vehicle's speakers, the CPU 21 terminates the filter setting process.

[0118] On the other hand, if the estimated sound source location is near the driver's head or near the vehicle's speaker, the CPU 21 performs a filter process in S820 to exclude speech from the sound wave data near the sound generation timing, and then terminates the filter setting process.

[0119] The order in which the processes S720, S740, S760, S780, S800, and S820 are performed is not particularly limited.

[0120] The vehicle accident detection device 2 configured in this way is configured to estimate the location of a sound source (i.e., the estimated sound source location) based on the detection results of a plurality of microphones 31 to 34 that are installed on the vehicle and configured to detect sound. Specifically, the vehicle accident detection device 2 is configured to estimate the estimated sound source location based on the difference in phase of the sound waves detected by each of the plurality of microphones 31 to 34 (i.e., the difference in sound detection timing). The vehicle accident detection device 2 is configured to determine whether or not the estimated sound source location is on the exterior of the vehicle body. If the vehicle accident detection device 2 determines that the estimated sound source location is on the exterior of the vehicle body, it is configured to determine that a collision has occurred.

[0121] Such a vehicle accident detection device 2 can detect collision accidents in a vehicle using multiple microphones 31 to 34 installed in the vehicle.

[0122] Furthermore, the vehicle accident detection device 2 is configured to determine that the estimated sound source location is on the vehicle body outer casing when a preset first outer casing determination condition or a second outer casing determination condition, which indicates that the estimated sound source location is near the vehicle body outer casing, is met. The first outer casing determination condition is set based on vehicle body information to indicate that the estimated sound source location is near the vehicle body outer casing. The second outer casing determination condition is set based on multiple distances from each of the multiple microphones 31 to 33 to the estimated sound source location.

[0123] The vehicle accident detection device 2 further includes a sound analysis unit 43 configured to analyze the waveforms of sounds detected by multiple microphones 31-33. When the vehicle accident detection device 2 determines that the estimated sound source location is on the exterior of the vehicle body, it is configured to determine that a collision has occurred based on the analysis results of the sound analysis unit 43, if the sounds detected by the multiple microphones 31-33 have collision sound characteristics that have been set in advance as characteristics of collision sounds. Because such a vehicle accident detection device 2 makes a determination based on collision sound characteristics, it can improve the accuracy of collision accident determination.

[0124] Furthermore, when the vehicle accident detection device 2 determines that the estimated sound source location is on the exterior of the vehicle body, it is configured to determine that a collision has occurred if, based on the analysis results from the sound analysis unit 43, the sounds detected by the multiple microphones 31-33 do not possess the non-collision sound characteristics that have been set in advance as characteristics of non-collision sounds. Since such a vehicle accident detection device 2 makes a determination based on non-collision sound characteristics, the accuracy of collision accident determination can be improved.

[0125] Furthermore, the vehicle accident detection device 2 is configured to apply a filter to the sounds detected by the multiple microphones 31 to 33 to remove non-collision sounds. Such a vehicle accident detection device 2 can suppress situations in which a collision sound is mistakenly determined to have occurred due to the presence of non-collision sounds, thereby improving the accuracy of collision accident detection.

[0126] Furthermore, the vehicle accident detection device 2 is configured to determine whether or not the vehicle driver has performed a pre-set specific operation. If the vehicle accident detection device 2 determines that the estimated sound source location is on the exterior of the vehicle body, and further determines that the driver has performed the specific operation, it is configured to determine that no collision has occurred. Such a vehicle accident detection device 2 can suppress situations in which a collision sound is incorrectly determined to have occurred due to the driver performing a specific operation, thereby improving the accuracy of collision accident detection.

[0127] Furthermore, the vehicle accident detection device 2 is configured to determine that no collision has occurred if it determines that the estimated sound source location is on the exterior of the vehicle body, and if the acceleration at the sound generation timing is less than a preset collision detection acceleration. Since such a vehicle accident detection device 2 makes its determination based on acceleration, it can improve the accuracy of collision detection.

[0128] The vehicle accident detection device 2 further includes a video analysis unit 45 configured to estimate the collision sound source location, which is the location where an object collided with the vehicle, by analyzing video data generated by cameras 36 and 37 mounted on the vehicle and configured to capture at least the outside of the vehicle. When the vehicle accident detection device 2 determines that the estimated sound source location is on the exterior of the vehicle body, it is further configured to determine, based on the analysis results of the video analysis unit 45, that no collision accident occurred if no object collided with the vehicle at the time the sound was generated at the sound source. Because such a vehicle accident detection device 2 makes its determination based on video data, it can improve the accuracy of collision accident detection.

[0129] Furthermore, multiple microphones 31-34 are installed inside the vehicle. This eliminates the need for protective measures for microphones 31-34, and also allows microphones 31-34 to be used for other purposes.

[0130] In the embodiments described above, microphones 31 to 34 correspond to sound detection units, S210 to S250 correspond to processing as a sound source position estimation unit, S260 to S330 correspond to processing as a vehicle body outer frame determination unit, and S410, S450, S460, S480, S520 to S550 correspond to processing as a collision determination unit.

[0131] Furthermore, cameras 36 and 37 correspond to the shooting unit, S710 to S820 correspond to the processing as an exclusion unit, and S610 to S660 correspond to the processing as a specific operation determination unit.

[0132] [Second Embodiment] A second embodiment of this disclosure is described below with reference to the drawings. Note that the second embodiment will describe parts that differ from the first embodiment. Common components will be denoted by the same reference numerals.

[0133] The accident information collection system 1 of the second embodiment differs from the first embodiment in that the microphone 32 is omitted and the microphone 31 is installed in the center of the dashboard, as shown in Figure 12.

[0134] The vehicle accident detection device 2 of the second embodiment estimates the timing at which sound is generated at a sound source (i.e., sound generation timing) by detecting information other than sound (in this embodiment, for example, acceleration).

[0135] Microphones 31 and 33 detect sound waves generated by sound source SS1 with a delay from the time the sound waves were generated by sound source SS1. This time difference can be considered as the distance from sound source SS1.

[0136] Therefore, for each of the microphones 31 and 33, it is possible to calculate circles CL1 and CL3 that pass over multiple points where the distance to the sound source SS1 is equal, based on the distance from the sound source SS1 (hereinafter referred to as distance circles).

[0137] Furthermore, for the pair of microphones 31 and 33, a distance difference curve L11 can be calculated to estimate the position of the sound source SS1 based on the difference in distance from the sound source SS1.

[0138] The vehicle accident detection device 2 then estimates the two-dimensional position of the sound source SS1 as the point where the distance circle CL1 and the distance difference curve L11 intersect, or the point where the distance circle CL2 and the distance difference curve L11 intersect, or the region enclosed by the distance circle CL1, the distance circle CL2, and the distance difference curve L11.

[0139] Furthermore, if there are no measurement errors in the distance circles CL1, CL2 and the distance difference curve L11, the distance circles CL1, CL2 and the distance difference curve L11 intersect at the position of the sound source SS1. In this case, the vehicle accident detection device 2 can estimate the intersection point of the distance circles CL1, CL2 and the distance difference curve L11 as a two-dimensional position at the sound source SS1.

[0140] Based on a similar approach, by using microphone 34 in addition to microphones 31 and 33, the vehicle accident detection device 2 can estimate the three-dimensional position of the sound source SS1.

[0141] As shown in Figure 13, the vehicle accident detection device 2 of the second embodiment includes a vehicle information acquisition unit 41, a sound acquisition unit 42, a sound analysis unit 43, a video acquisition unit 44, a video analysis unit 45, an accident detection control unit 46, a collision determination unit 47, and an upload unit 48 as functional blocks realized by the CPU 21 executing a program stored in the ROM 22.

[0142] As indicated by arrow A31, the vehicle information acquisition unit 41 constantly acquires vehicle information from multiple ECUs via the CAN communication unit 12.

[0143] The vehicle information acquisition unit 41 also continuously acquires acceleration information, which indicates the acceleration detected by the acceleration sensor 35 mounted on the vehicle, as shown by arrow A32.

[0144] The sound acquisition unit 42 continuously acquires sound wave electrical signals from microphones 31 and 33, as indicated by arrows A33 and A34.

[0145] The video acquisition unit 44 continuously acquires video data generated by cameras 36 and 37 mounted on the vehicle, as indicated by arrows A35 and A36.

[0146] As indicated by arrow A37, the accident detection control unit 46 acquires vehicle information from the vehicle information acquisition unit 41 at the moment when the acceleration exceeds a threshold.

[0147] As indicated by arrow A38, the accident detection control unit 46 acquires video data from the video acquisition unit 44 at the moment when the acceleration exceeds the threshold.

[0148] As indicated by arrow A39, the accident detection control unit 46 acquires sound wave data from the sound acquisition unit 42 at the moment when the acceleration exceeds a threshold.

[0149] After acquiring vehicle information, video data, and sound wave data, the accident detection control unit 46 outputs a collision determination request to the collision determination unit 47, as indicated by arrow A40.

[0150] When the collision determination unit 47 receives a collision determination request from the accident detection control unit 46, it outputs a sound source location estimation request to the sound analysis unit 43, as indicated by arrow A41.

[0151] When the sound analysis unit 43 receives a request for sound source location estimation from the collision determination unit 47, it estimates the location of the sound source based on the timing when the acceleration exceeds a threshold and the timing when the sound acquisition unit 42 detects a sound wave. The sound analysis unit 43 then notifies the collision determination unit 47 of the estimated sound source location, as indicated by arrow A42.

[0152] When the collision determination unit 47 receives a collision determination request from the accident detection control unit 46, it outputs a contact determination request to the video analysis unit 45, as indicated by arrow A43.

[0153] When the video analysis unit 45 receives a collision determination request from the collision determination unit 47, it analyzes the video data at the moment when the acceleration exceeds a threshold and determines whether or not an object has come into contact with the vehicle. As shown by arrow A44, the video analysis unit 45 notifies the collision determination unit 47 of the determination result regarding the presence or absence of an object that came into contact with the vehicle.

[0154] When the collision determination unit 47 receives a collision determination request from the accident detection control unit 46, it obtains vehicle body information from the vehicle body information storage unit 49, as indicated by arrow A45.

[0155] The collision determination unit 47 determines whether or not an object has collided with the vehicle based on the estimated sound source position obtained from the sound analysis unit 43, the determination result obtained from the video analysis unit 45, and the vehicle body information obtained from the vehicle body information storage unit 49.

[0156] The collision determination unit 47 notifies the accident detection control unit 46 of the determination result, which determines whether or not an object has collided with the vehicle, as indicated by arrow A46.

[0157] The accident detection control unit 46 generates accident information, including acquired vehicle information and video data, based on the judgment result obtained from the collision judgment unit 47, when an object collides with the vehicle. As indicated by arrow A47, the accident detection control unit 46 stores the generated accident information in the temporary storage unit 50.

[0158] After storing accident information in the temporary storage unit 50, the accident detection control unit 46 outputs an upload instruction to the upload unit 48, as indicated by arrow A48.

[0159] When the upload unit 48 receives an upload instruction from the accident detection control unit 46, it retrieves accident information from the temporary storage unit 50, as indicated by arrow A49. The upload unit 48 then uploads the retrieved accident information to the accident information server 3.

[0160] Next, the procedure for accident detection processing in the second embodiment will be described. In this embodiment, for the sake of simplicity, we will show a configuration in which accidents are detected using microphones 31 and 33.

[0161] When the accident detection process of the second embodiment is executed, the CPU 21 of the control unit 11 determines in S910 whether the detected acceleration is equal to or greater than a preset collision detection acceleration, as shown in Figure 14. If the acceleration is less than the collision detection acceleration, the CPU 21 terminates the accident detection process.

[0162] On the other hand, if the acceleration is greater than or equal to the collision detection acceleration, the CPU 21 uses S920 to acquire vehicle information near the time when the acceleration became greater than or equal to the collision detection acceleration (hereinafter referred to as the acceleration generation timing). The vicinity of the acceleration generation timing is, for example, the time range from a predetermined acquisition time before the acceleration generation timing (for example, 1 second before) to a predetermined acquisition time after the acceleration generation timing (for example, 1 second after).

[0163] CPU21 uses S930 to acquire video data near the timing of acceleration generation.

[0164] CPU21 acquires sound wave data near the timing of acceleration generation using S940.

[0165] CPU21 performs the sound source location estimation process described later using S950.

[0166] CPU21 performs collision detection processing on S960 in the same way as S70.

[0167] CPU21 determines in S970 whether a collision has occurred based on the judgment result of S960. If no collision has occurred, CPU21 terminates the accident detection process.

[0168] On the other hand, if a collision occurs, the CPU 21 generates the above-mentioned accident information in the S980 and stores the generated accident information in the temporary storage unit 50.

[0169] CPU21 retrieves the accident information generated by S980 from the temporary storage unit 50 using S990, and uploads the retrieved accident information to the accident information server 3.

[0170] Once the S990 process is complete, the CPU21 terminates the accident detection process.

[0171] Next, we will explain the procedure for sound source location estimation processing performed by S950.

[0172] When the sound source position estimation process of the second embodiment is executed, the CPU 21 determines in S1110, as shown in Figure 15, whether or not the above distance circles have been calculated for each of the microphones 31 and 33.

[0173] If the distance circle has not been calculated, CPU 21 calculates the timing of sound wave detection (hereinafter referred to as sound wave detection timing) for microphones 31 and 33 in S1120.

[0174] In S1130, CPU21 calculates the distance between microphones 31 and 33 and the sound source based on the time difference between the acceleration generation timing and the sound wave detection timing for each microphone 31 and 33.

[0175] In S1140, CPU21 calculates an equation for distance circles that pass over multiple points equal in distance to the sound source for each of microphones 31 and 33, based on the distance calculated in S1130, and then proceeds to S1110.

[0176] If a distance circle is calculated in S1110, the CPU 21 calculates the phase difference between the two sound waves detected by microphones 31 and 33 in S1150.

[0177] CPU21 calculates the difference in distance from microphones 31 and 33 to the sound source in S1160, based on the phase difference calculated in S1150.

[0178] In S1170, CPU21 calculates an equation representing a distance difference curve that passes over multiple points where the distance difference from microphones 31 and 33 to the sound source is equal, based on the distance calculated in S1160.

[0179] CPU21, in S1180, estimates the sound source location as the coordinate position where the two distance difference curves and one distance difference curve are closest together.

[0180] CPU 21 acquires vehicle information from vehicle information storage unit 49 in S1190.

[0181] CPU21, in S1200, determines whether the first outer casing determination condition is met, in the same manner as S280.

[0182] If the first outer casing determination condition is met, the CPU 21 determines in S1210 that the estimated sound source location estimated in S1180 is near the vehicle body casing, and terminates the sound source location estimation process.

[0183] On the other hand, if the first outer casing determination condition is not met, the CPU 21 determines in S1220 that the estimated sound source location estimated in S1180 is not near the vehicle body outer casing, and terminates the sound source location estimation process.

[0184] The vehicle accident detection device 2 configured in this way is set up to detect the timing when the acceleration detected by the acceleration sensor 35 mounted on the vehicle becomes equal to or greater than the collision detection acceleration (i.e., the acceleration generation timing) as the sound generation timing when sound is generated by the sound source.

[0185] The vehicle accident detection device 2 is configured to estimate the sound source location based on the difference between the sound generation timing and the two sound detection timings at which microphones 31 and 33 each detected sound. The vehicle accident detection device 2 is configured to determine whether or not the estimated sound source location is on the vehicle body exterior. If the vehicle accident detection device 2 determines that the estimated sound source location is on the vehicle body exterior, it is configured to determine that a collision has occurred.

[0186] Such a vehicle accident detection device 2 can detect collision accidents in a vehicle using multiple microphones 31 and 33 installed in the vehicle.

[0187] Furthermore, the vehicle accident detection device 2 is configured to estimate the sound source location based on the difference between two sound detection timings, each detected by one of the two microphones 31 and 33. This allows the vehicle accident detection device 2 to improve the accuracy of sound source location estimation.

[0188] In the embodiments described above, S1110 to S1180 correspond to processing as a sound source position estimation unit, S1190 to S1220 correspond to processing as a vehicle body outer shell determination unit, and S910 corresponds to processing as a sound generation timing detection unit.

[0189] [Third Embodiment] A third embodiment of this disclosure is described below with reference to the drawings. Note that the third embodiment will describe parts that differ from the first embodiment. Common components will be denoted by the same reference numerals.

[0190] The accident information collection system 1 of the third embodiment differs from the first embodiment in that the microphone 32 is omitted and the microphone 31 is installed in the center of the dashboard, as shown in Figure 16. The camera 36 is installed, for example, above the center of the dashboard and photographs the rear of the vehicle. The camera 37 is installed, for example, above the rear of the cargo area of ​​the vehicle and photographs the front of the vehicle.

[0191] The vehicle accident detection device 2 of the third embodiment determines whether or not an object has come into contact with the vehicle by analyzing the video data captured by cameras 36 and 37. If an object has come into contact with the vehicle, the vehicle accident detection device 2 estimates the position where the object came into contact with the vehicle as the sound source estimation position and the timing of the object's contact with the vehicle as the sound generation timing. If the above-mentioned first enclosure determination condition is met for the estimated sound source position, the vehicle accident detection device 2 determines that the estimated sound source position is near the vehicle's outer enclosure.

[0192] As shown in Figure 17, the vehicle accident detection device 2 comprises a vehicle information acquisition unit 41, a sound acquisition unit 42, a sound analysis unit 43, a video acquisition unit 44, a video analysis unit 45, an accident detection control unit 46, a collision determination unit 47, and an upload unit 48, as functional blocks realized by the CPU 21 executing a program stored in the ROM 22.

[0193] As indicated by arrow A51, the vehicle information acquisition unit 41 constantly acquires vehicle information from multiple ECUs via the CAN communication unit 12.

[0194] The vehicle information acquisition unit 41 also continuously acquires acceleration information, which indicates the acceleration detected by the acceleration sensor 35 mounted on the vehicle, as shown by arrow A52.

[0195] The sound acquisition unit 42 continuously acquires sound wave electrical signals from microphones 31 and 33, as indicated by arrows A53 and A54.

[0196] The video acquisition unit 44 continuously acquires video data generated by cameras 36 and 37 mounted on the vehicle, as indicated by arrows A55 and A56.

[0197] The video acquisition unit 44 outputs the acquired video data to the video analysis unit 45, as indicated by arrow A57.

[0198] The video analysis unit 45 analyzes the video data acquired by the video acquisition unit 44 and determines whether or not an object has come into contact with the vehicle. If the video analysis unit 45 determines that an object has come into contact with the vehicle, it notifies the video acquisition unit 44 of the timing of the contact when the object came into contact with the vehicle, as indicated by arrow A58.

[0199] The video acquisition unit 44 notifies the accident detection control unit 46 of the contact timing, as indicated by arrow A59.

[0200] When the accident detection control unit 46 receives notification of the contact timing from the video acquisition unit 44, it acquires vehicle information, acceleration information, and sound wave data at the time of contact, as indicated by arrows A60 and A61.

[0201] After acquiring vehicle information, acceleration information, and sound wave data, the accident detection control unit 46 outputs a collision determination request to the collision determination unit 47, as indicated by arrow A62.

[0202] When the collision determination unit 47 receives a collision determination request from the accident detection control unit 46, it obtains vehicle body information from the vehicle body information storage unit 49, as indicated by arrow A63.

[0203] The collision determination unit 47 outputs a contact position provision request to the video analysis unit 45, as indicated by arrow A64, requesting the provision of the contact position where the object came into contact with the vehicle.

[0204] When the video analysis unit 45 receives a request from the collision determination unit 47 to provide the contact position, it notifies the collision determination unit 47 of the contact position, as indicated by arrow A65.

[0205] As indicated by arrow A66, the collision detection unit 47 outputs a sound wave analysis request to the sound analysis unit 43, requesting analysis of the characteristics of the sound wave waveform at the time of contact.

[0206] When the sound analysis unit 43 receives a sound wave analysis request from the collision determination unit 47, it outputs a sound wave data provision request to the sound acquisition unit 42, as indicated by arrow A67, requesting the provision of sound wave data at the contact timing.

[0207] When the sound acquisition unit 42 receives a request for sound wave data from the sound analysis unit 43, it outputs the sound wave data at the contact timing to the sound analysis unit 43, as indicated by arrow A68.

[0208] When the sound analysis unit 43 acquires sound wave data from the sound acquisition unit 42, it analyzes the characteristics of the sound wave waveform and notifies the collision determination unit 47 of the analysis results of the sound wave data, as shown by arrow A69.

[0209] The collision determination unit 47 determines whether or not an object has collided with the vehicle based on vehicle information, acceleration information, contact position, vehicle body information, and the characteristics of the sound wave waveform. As indicated by arrow A70, the collision determination unit 47 notifies the accident detection control unit 46 of the determination result of whether or not an object has collided with the vehicle.

[0210] The accident detection control unit 46 generates accident information, including acquired vehicle information and video data, based on the judgment result obtained from the collision judgment unit 47, when an object collides with the vehicle. As indicated by arrow A71, the accident detection control unit 46 stores the generated accident information in the temporary storage unit 50.

[0211] After storing accident information in the temporary storage unit 50, the accident detection control unit 46 outputs an upload instruction to the upload unit 48, as indicated by arrow A72.

[0212] When the upload unit 48 receives an upload instruction from the accident detection control unit 46, it retrieves accident information from the temporary storage unit 50, as indicated by arrow A73. The upload unit 48 then uploads the retrieved accident information to the accident information server 3.

[0213] Next, the procedure for accident detection processing in the third embodiment will be described.

[0214] When the accident detection process of the third embodiment is executed, the CPU 21 of the control unit 11 analyzes the video data generated by the cameras 36 and 37 in S1310, as shown in Figure 18, to determine whether or not there is an object that has come into contact with the vehicle. If there is no object that has come into contact with the vehicle, the CPU 21 terminates the accident detection process.

[0215] On the other hand, if an object has come into contact with the vehicle, the CPU 21, in S1320, identifies the timing of the contact and the location of the contact based on video data (hereinafter referred to as contact video data) of the situation in which the object came into contact with the vehicle.

[0216] CPU21 acquires vehicle information near the contact timing in S1330. Near the contact timing is, for example, the time range from a predetermined acquisition time before the contact timing (e.g., 1 second before) to a predetermined acquisition time after the contact timing (e.g., 1 second after).

[0217] CPU21 acquires video data near the contact timing using S1340.

[0218] CPU21 acquires sound wave data near the contact timing using S1350.

[0219] In S1360, CPU21 estimates the contact location identified in S1320 as the collision sound source location.

[0220] CPU21 executes the collision detection process described later in S1370.

[0221] In S1380, CPU21 determines whether a collision has occurred based on the result of S1370. If no collision has occurred, CPU21 terminates the accident detection process.

[0222] On the other hand, if a collision occurs, the CPU 21 generates the above-mentioned accident information in S1390 and stores the generated accident information in the temporary storage unit 50.

[0223] CPU 21, in S1400, retrieves the accident information generated in S1390 from the temporary storage unit 50 and uploads the retrieved accident information to the accident information server 3.

[0224] Once the S1400 process is complete, CPU21 terminates the accident detection process.

[0225] Next, we will explain the procedure for collision detection processing performed in S1370.

[0226] When the collision detection process of the third embodiment is executed, the CPU 21 determines in S1510 whether the collision sound source location is near the vehicle body outer shell, as shown in Figure 19. Specifically, the CPU 21 determines whether the first outer shell determination condition is met, in the same manner as in S1200 in the second embodiment. If the first outer shell determination condition is met, the CPU 21 determines that the collision sound source location is near the vehicle body outer shell; if the first outer shell determination condition is not met, the CPU 21 determines that the collision sound source location is not near the vehicle body outer shell.

[0227] If the collision sound source is not located near the vehicle's outer shell, CPU 21 proceeds to S1600.

[0228] On the other hand, if the collision sound source is located near the vehicle's outer shell, the CPU 21 acquires acceleration information near the time of contact in S1520.

[0229] In S1530, CPU21 determines whether the acceleration information obtained in S1520 is equal to or greater than a pre-set collision detection acceleration. If the acceleration is less than the collision detection acceleration, CPU21 proceeds to S1600.

[0230] On the other hand, if the acceleration is greater than or equal to the collision detection acceleration, the CPU 21 executes a specific operation determination process in S1540, in the same manner as in S470.

[0231] In S1550, CPU21 determines whether a specific operation is in progress based on the result of the determination in S1540. If a specific operation is in progress, CPU21 proceeds to S1600.

[0232] On the other hand, if no specific operation is in progress, CPU21 executes the filter setting process in S1560 in the same manner as S500.

[0233] CPU21, in S1570, analyzes the waveform of the sound wave after performing the filter setting process in S1560 to determine whether or not it has the characteristics of a collision sound and whether or not it has the characteristics of a non-collision sound.

[0234] In S1580, CPU21 determines, based on the judgment result in S1570, whether or not the sound waves near the contact timing have the characteristics of a non-collision sound. If the characteristics of a non-collision sound are present, CPU21 proceeds to S1600.

[0235] On the other hand, if there are no non-collision sound characteristics, CPU 21, in S1590, determines whether or not the sound waves near the contact timing have collision sound characteristics based on the judgment result in S1570. If there are no collision sound characteristics, CPU 21 proceeds to S1600. On the other hand, if there are collision sound characteristics, CPU 21 proceeds to S1610.

[0236] When the process switches to S1600, CPU21 determines that no collision has occurred and terminates the collision detection process.

[0237] When the process transitions to S1610, CPU21 determines that a collision has occurred and terminates the collision detection process.

[0238] Although one embodiment of the present disclosure has been described above, the present disclosure is not limited to the above embodiment and can be implemented in various modified forms.

[0239] [Example 1] In the second embodiment described above, a method was shown in which the point where the distance circle CL1 and the distance difference curve L11 intersect, or the point where the distance circle CL2 and the distance difference curve L11 intersect, or the region enclosed by the distance circle CL1, the distance circle CL2, and the distance difference curve L11, is estimated as the two-dimensional position of the sound source SS1.

[0240] However, as shown in Figure 20, microphones 31 and 33 detect sound waves generated by the sound source with a delay compared to the timing of the sound wave generation. This time difference can be considered as the distance from the sound source. Therefore, for each of microphones 31 and 33, distance circles CL1 and CL3 can be calculated to estimate the position of the sound source based on the distance from the sound source.

[0241] When estimating the sound source position using only distance circles CL1 and CL3, the two intersection points IP1 and IP2 of distance circle CL1 and distance circle CL3 become candidate sound source locations. In cases where there are two candidate sound source locations, the system may determine that the sound source is located on the vehicle body if either the following first or second collision determination condition is met. The first collision determination condition is that both candidates are located on the vehicle body. The second collision determination condition is that one of the candidates is located on the vehicle body, and the waveform of the sound wave detected by microphones 31 and 33 has the characteristics of a typical collision sound.

[0242] [Differentiation 2] In the above embodiment, the sound analysis unit 43, video analysis unit 45, accident detection control unit 46, and collision determination unit 47 are shown mounted on the vehicle. However, the accident information server 3 may also be equipped with the sound analysis unit 43, video analysis unit 45, accident detection control unit 46, and collision determination unit 47.

[0243] [Difference 3] In the second embodiment described above, a configuration was shown in which the timing of sound generation is detected based on the acceleration detected by an acceleration sensor 35 mounted on the vehicle. However, the timing of sound generation may also be detected based on video data generated by cameras 36 and 37 mounted on the vehicle and configured to capture at least the outside of the vehicle.

[0244] [Differentiation Example 4] In the above embodiment, a configuration was shown in which it is determined that the estimated sound source location is on the vehicle body outer shell when the preset first and second outer shell determination conditions, which indicate that the estimated sound source location is near the vehicle body outer shell, are met. However, instead of the estimated sound source location, the collision sound source location estimated by the video analysis unit 45 may be used to determine whether or not the first and second outer shell determination conditions are met. In this case, the video analysis unit 45 estimates the collision sound source location where an object collided with the vehicle based on the video data generated by the cameras 36 and 37.

[0245] [Difference 5] In the above embodiment, a configuration was shown in which it is determined whether or not the sound waves near the sound generation timing have the characteristics of a non-collision sound. However, the sound analysis unit 43 may also be configured to determine whether or not the sound detected by the multiple microphones 31-34 is a voice when the estimated sound source position is near the driver's head or near a speaker mounted in the vehicle.

[0246] The control unit 11 and its method described herein may be implemented by a dedicated computer provided by configuring a processor and memory programmed to perform one or more functions embodied by a computer program. Alternatively, the control unit 11 and its method described herein may be implemented by a dedicated computer provided by configuring a processor by one or more dedicated hardware logic circuits. Alternatively, the control unit 11 and its method described herein may be implemented by one or more dedicated computers configured by a combination of a processor and memory programmed to perform one or more functions and a processor configured by one or more hardware logic circuits. Furthermore, the computer program may be stored as instructions executed by the computer on a computer-readable non-transitional tangible recording medium. The method for implementing the functions of each part included in the control unit 11 does not necessarily need to include software, and all of its functions may be implemented using one or more hardware components.

[0247] Multiple functions of one component in the above embodiment may be realized by multiple components, or one function of one component may be realized by multiple components. Furthermore, multiple functions of multiple components may be realized by one component, or one function realized by multiple components may be realized by one component. Also, some parts of the configuration of the above embodiment may be omitted. Furthermore, at least some parts of the configuration of the above embodiment may be added to or replaced with the configuration of other above embodiments.

[0248] In addition to the vehicle accident detection device 2 described above, this disclosure can also be implemented in various forms, such as a system comprising the vehicle accident detection device 2, a program for causing a computer to function as the vehicle accident detection device 2, a non-transitional physical recording medium such as a semiconductor memory on which this program is recorded, and a vehicle accident detection method. [Technical concepts disclosed in this specification] [Item 1] A sound source location estimation unit (S210~S250, S1110~S1180) is configured to estimate the sound source location, which is the position of the sound source, based on the detection results of a plurality of sound detection units (31~34) installed in the vehicle and configured to detect sound, A vehicle body outer shell determination unit (S260~S330, S1190~S1220) is configured to determine whether or not the estimated sound source location is on the outer shell of the vehicle body, A collision determination unit (S410, S450, S460, S480, S520~S550) is configured to determine that a collision has occurred when the vehicle body outer frame determination unit determines that the estimated sound source location is on the vehicle body outer frame. A vehicle accident detection device (2) equipped with the following:

[0249] [Item 2] The vehicle accident detection device described in item 1, The sound source location estimation unit (S210~S250) is configured to estimate the sound source location based on the difference in sound detection timings in which each of the three or more sound detection units detects sound, in a vehicle accident detection device.

[0250] [Item 3] A vehicle accident detection device as described in item 2, The sound source position estimation unit is configured to estimate the two-dimensional position of the sound source as the estimated sound source position using three or more sound detection units in a vehicle accident detection device.

[0251] [Item 4] A vehicle accident detection device as described in item 2, The sound source position estimation unit is configured to estimate the three-dimensional position of the sound source as the estimated sound source position using four or more sound detection units in a vehicle accident detection device.

[0252] [Item 5] The vehicle accident detection device described in item 1, The sound generation timing detection unit (S910) is further configured to detect the timing at which sound is generated by the sound source, The sound source location estimation unit (S1110~S1180) is configured to estimate the sound source location based on the difference between the sound generation timing detected by the sound generation timing detection unit and two or more sound detection timings in which each of the two or more sound detection units detects sound.

[0253] [Item 6] A vehicle accident detection device as described in item 5, The sound source position estimation unit is configured to estimate the two-dimensional position of the sound source as the estimated sound source position using two or more sound detection units in a vehicle accident detection device.

[0254] [Item 7] A vehicle accident detection device as described in item 5, The sound source position estimation unit is configured to estimate the three-dimensional position of the sound source as the estimated sound source position using three or more sound detection units in a vehicle accident detection device.

[0255] [Item 8] A vehicle accident detection device described in any one of items 5 to 7, The sound generation timing detection unit is configured to detect the sound generation timing based on the acceleration detected by an acceleration sensor mounted on the vehicle, in a vehicle accident detection device.

[0256] [Item 9] A vehicle accident detection device described in any one of items 5 to 7, The sound generation timing detection unit is a vehicle accident detection device configured to detect the sound generation timing based on video data generated by imaging units (36, 37) mounted on the vehicle and configured to capture at least the outside of the vehicle.

[0257] [Item 10] A vehicle accident detection device described in any one of items 5 to 9, The sound source location estimation unit is further configured to estimate the sound source location based on the difference between two or more sound detection timings in which each of the two or more sound detection units detects sound, in a vehicle accident detection device.

[0258] [Item 11] A vehicle accident detection device described in any one of items 1 to 10, The vehicle accident detection device is configured such that the vehicle body outer shell determination unit determines that the sound source estimated position is on the vehicle body outer shell when a preset outer shell determination condition is met, indicating that the sound source estimated position is near the vehicle body outer shell.

[0259] [Item 12] A vehicle accident detection device as described in item 11, The vehicle accident detection device sets the outer shell determination conditions based on a plurality of distances from each of the plurality of sound detection units to the estimated sound source position.

[0260] [Item 13] A vehicle accident detection device as described in item 11, The vehicle body information storage unit (49) is configured to store vehicle body information indicating multiple coordinate positions on the outer shell of the vehicle body, The vehicle accident detection device is configured such that the outer shell determination condition indicates, based on the vehicle body information, that the estimated sound source location is near the outer shell of the vehicle body.

[0261] [Item 14] The vehicle accident detection device described in item 11, further, By analyzing the video data generated by the imaging unit (36, 37) mounted on the vehicle and configured to at least image the exterior of the vehicle, a video analysis unit (45) configured to estimate the collision sound source position, which is the position where an object has collided with the vehicle, and a vehicle body information storage unit (49) configured to store vehicle body information indicating a plurality of coordinate positions on the vehicle exterior. A vehicle accident detection device in which the outer contour determination condition is set based on the vehicle body information to indicate that the collision sound source position is near the vehicle outer contour.

[0262] [Item 15] The vehicle accident detection device according to any one of Items 1 to 14, further comprising a sound analysis unit (43) configured to analyze the waveforms of the sounds detected by the plurality of sound detection units, wherein when the vehicle outer contour determination unit determines that the sound source estimation position is on the vehicle outer contour, the collision determination unit further determines that the collision accident has occurred based on the analysis result by the sound analysis unit and when the sounds detected by the plurality of sound detection units have a collision sound feature preset as a feature of a collision sound.

[0263] [Item 16] The vehicle accident detection device according to any one of Items 1 to 15, further comprising a sound analysis unit (43) configured to analyze the waveforms of the sounds detected by the plurality of sound detection units, wherein when the vehicle outer contour determination unit determines that the sound source estimation position is on the vehicle outer contour, the collision determination unit further determines that the collision accident has occurred based on the analysis result by the sound analysis unit and when the sounds detected by the plurality of sound detection units do not have a non - collision sound feature preset as a feature of a non - collision sound.

[0264] [Item 17] The vehicle accident detection device according to Item 16, The non-collision sound vehicle accident detection device includes vehicle operation sounds generated when the driver of the vehicle operates.

[0265] [Item 18] The vehicle accident detection device according to Item 16 or Item 17, The non-collision sound vehicle accident detection device includes voices.

[0266] [Item 19] The vehicle accident detection device according to Item 18, The sound analysis unit is configured to determine whether the sounds detected by the plurality of sound detection units are voices when the estimated sound source position is near the head of the driver of the vehicle or near the speaker mounted on the vehicle.

[0267] [Item 20] The vehicle accident detection device according to any one of Items 15 to 19, The vehicle accident detection device further includes an external removal unit (S710 to S820) configured to perform a filter process for removing non-collision sounds on the sounds detected by the plurality of sound detection units.

[0268] [Item 21] The vehicle accident detection device according to any one of Items 1 to 20, The vehicle accident detection device further includes a specific operation determination unit (S610 to S660) configured to determine whether the driver of the vehicle has performed a preset specific operation, When the vehicle outer shell determination unit determines that the estimated sound source position is on the vehicle outer shell, the collision determination unit is further configured to determine that no collision accident has occurred when the driver has performed the specific operation based on the determination result by the specific operation determination unit.

[0269] [Item 22] The vehicle accident detection device according to any one of Items 1 to 21, The collision determination unit is configured to determine that a collision has not occurred if the vehicle body outer shell determination unit determines that the estimated sound source position is on the vehicle body outer shell, and further determines that the acceleration at the sound generation timing when sound is generated by the sound source is less than a preset collision determination acceleration.

[0270] [Item 23] A vehicle accident detection device described in any one of items 1 to 22, The vehicle further comprises a video analysis unit (45) configured to estimate the collision sound source location, which is the location where an object collided with the vehicle, by analyzing video data generated by a camera unit (36, 37) mounted on the vehicle and configured to capture at least the outside of the vehicle, The collision determination unit is configured to determine, based on the analysis results of the video analysis unit, that no collision accident has occurred if the vehicle body outer frame determination unit determines that the estimated sound source position is on the vehicle body outer frame, and if no object has collided with the vehicle at the sound generation timing when the sound was generated by the sound source.

[0271] [Item 24] A vehicle accident detection device described in any one of items 1 to 23, The multiple sound detection units are part of a vehicle accident detection device installed inside the vehicle.

Claims

1. A sound source location estimation unit (S210-S250, S1110-S1180) is configured to estimate the sound source location, which is the position of the sound source, based on the detection results of a plurality of sound detection units (31-34) installed in the vehicle and configured to detect sound, A vehicle body outer shell determination unit (S260-S330, S1190-S1220) is configured to determine whether or not the estimated sound source location is on the outer shell of the vehicle body, A collision determination unit (S410, S450, S460, S480, S520-S550) is configured to determine that a collision has occurred when the vehicle body outer frame determination unit determines that the estimated sound source location is on the vehicle body outer frame. Equipped with, The system further includes a sound analysis unit (43) configured to analyze the waveforms of sounds detected by multiple sound detection units, The collision determination unit is configured such that, when the vehicle body outer shell determination unit determines that the estimated sound source location is on the vehicle body outer shell, the unit further determines that a collision has occurred if, based on the analysis results from the sound analysis unit, the sounds detected by the multiple sound detection units do not have the non-collision sound characteristics that have been set in advance as characteristics of non-collision sounds. The aforementioned non-collision sounds include speech, The sound analysis unit is configured to determine whether the sound detected by the plurality of sound detection units is a voice when the estimated sound source location is near the head of the vehicle driver or near a speaker mounted in the vehicle. (Vehicle accident detection device (2))

2. A vehicle accident detection device according to claim 1, The sound source location estimation unit (S210 to S250) is configured to estimate the sound source location based on the difference in sound detection timings in which each of the three or more sound detection units detects sound, in a vehicle accident detection device.

3. A vehicle accident detection device according to claim 2, The sound source position estimation unit is configured to estimate the two-dimensional position of the sound source as the estimated sound source position using three or more sound detection units in a vehicle accident detection device.

4. A vehicle accident detection device according to claim 2, The sound source position estimation unit is configured to estimate the three-dimensional position of the sound source as the estimated sound source position using four or more sound detection units in a vehicle accident detection device.

5. A vehicle accident detection device according to claim 1, The system further includes a sound generation timing detection unit (S910) configured to detect the sound generation timing at which sound is generated by the sound source, The sound source location estimation unit (S1110 to S1180) is configured to estimate the sound source location based on the difference between the sound generation timing detected by the sound generation timing detection unit and two or more sound detection timings in which each of the two or more sound detection units detects sound.

6. A vehicle accident detection device according to claim 5, The sound source position estimation unit is configured to estimate the two-dimensional position of the sound source as the estimated sound source position using two or more sound detection units in a vehicle accident detection device.

7. A vehicle accident detection device according to claim 5, The sound source position estimation unit is configured to estimate the three-dimensional position of the sound source as the estimated sound source position using three or more sound detection units in a vehicle accident detection device.

8. A vehicle accident detection device according to any one of claims 5 to 7, The sound generation timing detection unit is configured to detect the sound generation timing based on the acceleration detected by an acceleration sensor mounted on the vehicle, in a vehicle accident detection device.

9. A vehicle accident detection device according to any one of claims 5 to 7, The sound generation timing detection unit is a vehicle accident detection device configured to detect the sound generation timing based on video data generated by imaging units (36, 37) mounted on the vehicle and configured to capture at least the outside of the vehicle.

10. A vehicle accident detection device according to any one of claims 5 to 7, The sound source location estimation unit is further configured to estimate the sound source location based on the difference between two or more sound detection timings in which each of the two or more sound detection units detects sound, in a vehicle accident detection device.

11. A vehicle accident detection device according to any one of claims 1 to 7, The vehicle accident detection device is configured such that the vehicle body outer shell determination unit determines that the sound source estimated position is on the vehicle body outer shell when a preset outer shell determination condition indicating that the sound source estimated position is near the vehicle body outer shell is met.

12. A vehicle accident detection device according to claim 11, The vehicle accident detection device sets the outer shell determination conditions based on a plurality of distances from each of the plurality of sound detection units to the estimated sound source position.

13. A vehicle accident detection device according to claim 11, The vehicle body information storage unit (49) is configured to store vehicle body information indicating a plurality of coordinate positions on the outer shell of the vehicle body, The vehicle accident detection device is configured such that the outer shell determination condition indicates, based on the vehicle body information, that the estimated sound source location is near the outer shell of the vehicle body.

14. A vehicle accident detection device according to claim 11, further, A video analysis unit (45) is configured to estimate the collision sound source location, which is the location where an object collided with the vehicle, by analyzing video data generated by a camera unit (36, 37) mounted on the vehicle and configured to capture at least the outside of the vehicle, The vehicle includes a vehicle information storage unit (49) configured to store vehicle information indicating a plurality of coordinate positions on the outer shell of the vehicle body, The vehicle accident detection device is configured such that the outer shell determination condition indicates, based on the vehicle body information, that the collision sound source location is near the outer shell of the vehicle body.

15. A vehicle accident detection device according to any one of claims 1 to 7, The vehicle further includes a specific operation determination unit (S610 to S660) configured to determine whether the driver of the vehicle has performed a predetermined specific operation, The collision determination unit is configured to determine that a collision accident has not occurred if the vehicle body outer shell determination unit determines that the estimated sound source location is on the vehicle body outer shell, and further determines, based on the determination result by the specific operation determination unit, the driver has performed the specific operation.

16. A vehicle accident detection device according to any one of claims 1 to 7, The collision determination unit is configured to determine that a collision has not occurred if the vehicle body outer shell determination unit determines that the estimated sound source position is on the vehicle body outer shell, and further determines that the acceleration at the sound generation timing when sound is generated by the sound source is less than a preset collision determination acceleration.

17. A vehicle accident detection device according to any one of claims 1 to 7, The vehicle further comprises a video analysis unit (45) configured to estimate the location of the collision sound source, which is the location where an object collided with the vehicle, by analyzing video data generated by a camera unit (36, 37) mounted on the vehicle and configured to capture at least the outside of the vehicle, The collision determination unit is configured to determine, based on the analysis results of the video analysis unit, that no collision accident has occurred if the vehicle body outer frame determination unit determines that the estimated sound source position is on the vehicle body outer frame, and if no object has collided with the vehicle at the sound generation timing when the sound was generated by the sound source.

18. A vehicle accident detection device according to any one of claims 1 to 7, The multiple sound detection units are part of a vehicle accident detection device installed inside the vehicle.

Images