Accident detection device, accident detection method and accident detection program

Abstract

To execute highly accurate accident detection.SOLUTION: An accident detection device performs accident detection of a vehicle based on at least one of impact occurring on the vehicle and audio in the vehicle; estimates timing of the next impact and noise based on periodic impact and audio; and suppresses the accident detection of the vehicle within a predetermined period including the timing, or changes a determination condition used for the accident detection of the vehicle.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to an accident detection device, an accident detection method, and an accident detection program. [Background technology]

[0002] Drive recorders, which store vehicle status information (forward footage, vehicle speed, sudden acceleration / deceleration, etc.) before and after a car accident, provide useful information for investigating car collisions and other accidents. Therefore, they are increasingly being installed in transportation vehicles such as trucks, as well as commercial vehicles such as taxis and buses, and are also increasingly being installed in general vehicles. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-000818 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional technologies may not properly detect accidents. For example, accidents may be determined based on the level of impact a vehicle receives and an emergency call may be made. However, conventional technologies may detect an accident as a sudden movement rather than an accident because the level of impact is low. Therefore, with conventional technologies, even though the vehicle occupants may recognize that an accident has occurred, the device may not determine that an accident has occurred, resulting in a situation where an emergency call is not made or the call cannot be connected.

[0005] In order to solve the above-mentioned problems and achieve the objectives, the objective is to appropriately detect accidents. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, the accident detection device of the present invention is characterized by having an accident detection unit that performs accident detection for the vehicle based on at least one of an impact occurring to the vehicle and a sound inside the vehicle, an estimation unit that estimates the timing of the next impact and noise to occur based on the periodic impact and sound, and a judgment control unit that suppresses accident detection for the vehicle within a predetermined period including the timing, or changes the judgment conditions used for accident detection for the vehicle.

[0007] In addition, in order to solve the above-mentioned problems and achieve the object, the accident detection method of the present invention is a method executed by an accident detection device, and is characterized by having an accident detection process that performs accident detection on the vehicle based on at least one of an impact occurring on the vehicle and a sound inside the vehicle, an estimation process that estimates the timing of the next impact and noise to occur based on the periodic impact and sound, and a judgment control process that suppresses accident detection on the vehicle within a predetermined period including the timing, or changes the judgment conditions used for accident detection on the vehicle.

[0008] In addition, in order to solve the above-mentioned problems and achieve the object, the accident detection program of the present invention is characterized in that it causes a computer to execute an accident detection step of detecting an accident in the vehicle based on at least one of an impact occurring in the vehicle and a sound inside the vehicle, an estimation step of estimating the timing of the next impact and noise to occur based on the periodic impact and sound, and a judgment control step of suppressing accident detection in the vehicle within a predetermined period including the timing, or changing the judgment conditions used for accident detection in the vehicle. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of the overall configuration of an accident detection system according to each embodiment. [Figure 2] FIG. 2 is a diagram illustrating a process for detecting an accident using sound in addition to an impact. [Figure 3]FIG. 3 is a diagram illustrating a problem of the accident detection device according to the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of processing performed by the accident detection device according to the first embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a block diagram of the accident detection device according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of impact data of the accident detection device according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of voice data of the accident detection device according to the first embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of audio data after FFT processing in the accident detection device according to the first embodiment. [Figure 9] FIG. 9 is a diagram illustrating processing details of the accident detection device according to the first embodiment. [Figure 10] FIG. 10 is a diagram illustrating the processing contents of the accident detection device according to the first embodiment. [Figure 11] FIG. 11 is a diagram illustrating processing details of the accident detection device according to the first embodiment. [Figure 12] FIG. 12 is a diagram illustrating the processing contents of the accident detection device according to the first embodiment. [Figure 13] FIG. 13 is a diagram illustrating processing details of the accident detection device according to the first embodiment. [Figure 14] FIG. 14 is a diagram illustrating the processing contents of the accident detection device according to the first embodiment. [Figure 15] FIG. 15 is a diagram illustrating an example of a flowchart illustrating the flow of the accident detection process of the accident detection device according to the first embodiment. [Figure 16] FIG. 16 is a diagram illustrating an example of a flowchart illustrating a process of changing a determination condition of the accident detection device according to the first embodiment. [Figure 17] FIG. 17 is a diagram illustrating an example of a flowchart illustrating a process flow for restoring the determination conditions of the accident detection device according to the first embodiment. [Figure 18]FIG. 18 is a diagram illustrating the processing contents of the accident detection device according to the second embodiment. [Figure 19] FIG. 19 is a flowchart illustrating an example of the flow of the accident detection process according to the second embodiment. [Figure 20] FIG. 20 is a hardware configuration diagram showing an example of a computer that realizes the functions of the accident detection devices according to the first and second embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of an accident detection device, an accident detection method, and an accident detection program according to the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to the following embodiments 1 and 2.

[0011] [Embodiment 1] (Overall configuration of the accident detection system) First, the overall configuration of the accident detection system according to the present invention will be described. Fig. 1 is a diagram showing an example of the overall configuration of the accident detection system according to each embodiment. As shown in Fig. 1, the accident detection system according to the present invention has an accident detection device 100 mounted on a vehicle and an external server 300. The accident detection device 100 detects image data, audio data, and impacts while the vehicle is traveling, and appropriately detects a vehicle accident based on the detected content.

[0012] The accident detection device 100 is a device that appropriately detects a vehicle accident by detecting at least one of an impact that occurred on the vehicle and audio data at the time, or by combining the impact and audio data, and is realized by a computer or the like. For example, the accident detection device 100 may be a dedicated navigation device that is built into or mounted on a vehicle. For example, the accident detection device 100 may be composed of a navigation device and a recording device (drive recorder). As one example, the accident detection device 100 may be a composite device in which a navigation device and a recording device that are independent from each other are connected so that they can communicate with each other. As another example, the accident detection device 100 may be a single device that has a navigation function and a recording function.

[0013] The accident detection device 100 may also be configured with a sensor device and a communication device. As one example, the accident detection device 100 may be a composite device in which a sensor device and a notification device that are independent of each other are connected to each other so that they can communicate with each other. As another example, the accident detection device 100 may be a single device that has a sensor function and a notification function.

[0014] Furthermore, a vehicle occupant can connect a predetermined sensor to a portable terminal device (for example, a smartphone, tablet terminal, notebook PC, desktop PC, PDA, etc.) that they use on a daily basis and install a predetermined application, thereby substituting the device as the accident detection device 100. For example, a portable terminal device that is equipped with a predetermined sensor or to which a predetermined sensor is connected can be understood as the accident detection device referred to here. When a portable terminal device is used as the accident detection device 100, it is installed, for example, on the dashboard of the vehicle while driving.

[0015] When the detection processing unit 120 detects that there is a possibility of an accident, the external server device 300 is notified of an event that an accident has occurred. For example, when the external server device 300 is notified of an event that an accident has occurred by the accident detection device 100, the external server device 300 establishes communication between the vehicle occupant and a call center so that the vehicle occupant can make a call to the call center, which is the destination of an emergency call.

[0016] Such an accident detection device 100 detects an accident in a vehicle based on at least one of an impact occurring to the vehicle and a sound inside the vehicle. Figure 2 is a diagram for explaining the details of accident detection.

[0017] 2, when the accident detection device 100 detects an impact to a vehicle, it determines whether the level of the detected impact is equal to or greater than a predetermined value, and if so, it detects an accident. The accident detection device 100 also determines whether the volume of the sound inside the vehicle has changed suddenly within a predetermined time, and if so, it detects an accident.

[0018] Furthermore, when making a more strict accident judgment, the accident detection device 100 can also detect an accident when it determines that the level of impact is equal to or greater than a predetermined value and that there is a sudden change in the volume of the sound inside the vehicle, including the time when the impact equal to or greater than the predetermined value is detected.

[0019] In this way, the accident detection device 100 can properly determine that an accident is an accident when the detected impact level is low and it has been mistakenly determined to be a sudden movement (sudden acceleration, sudden braking, sudden steering, etc.) by analyzing the impact and sound that occurred on the vehicle as well as the audio data before and after the impact was detected.

[0020] Incidentally, when a vehicle passes over the joints of successive bridges or convex pavement designed to prevent speeding, the road surface may generate shocks or noise at regular intervals. When a vehicle travels on such roads, an accident detection device detects accidents using shocks or sounds on the vehicle, and so may periodically detect shocks or sounds above a threshold, resulting in a false detection of an accident.

[0021] Fig. 3 is a diagram illustrating the false detection of accidents due to periodic information. As shown in Fig. 3, there are roads with convex pavements installed at regular intervals, such as convex pavements installed on steep downhill slopes to prevent excessive speeding or the joints of consecutive bridges. When a vehicle passes over such a road, an accident detection device may detect certain impacts and sounds at regular intervals, and may detect an accident at regular intervals even though there is no accident.

[0022] In consideration of these improvements, the accident detection device of embodiment 1 dynamically controls the accident detection method based on impacts and sounds when traveling on roads where impacts and sounds occur periodically, thereby reducing the occurrence of false detections.

[0023] (Processing contents of the accident detection device 100) The processing details of the accident detection device 100 according to the first embodiment will be described. The accident detection device 100 according to the embodiment performs vehicle accident detection based on at least one of an impact occurring on the vehicle and a sound inside the vehicle. The accident detection device 100 then estimates the timing of the next impact and noise to occur based on the periodic impact and sound. Thereafter, the accident detection device 100 suppresses vehicle accident detection within a predetermined period including the timing, or changes the determination conditions used for vehicle accident detection.

[0024] Here, a specific example will be given of the processing contents of the accident detection device 100. Fig. 4 is a diagram illustrating the processing contents of the accident detection device according to the first embodiment. Fig. 4 shows, as an example, a processing example in which accident detection is suppressed or the judgment conditions used for accident detection are changed in response to impacts or noises that occur at regular intervals while traveling on a convex pavement that is provided on a steep downhill slope to prevent excessive speeding.

[0025] For example, when the accident detection device 100 detects an impact or noise that occurs periodically while the vehicle is running, it estimates the timing of the next impact or noise occurrence based on the impact data and sound data that are constantly recorded.The accident detection device 100 then suppresses accident detection based on impact, sound, or impact and sound, and changes the judgment conditions used for accident detection, during a predetermined period including that timing (the judgment control section shown in FIG. 4).

[0026] As a result, the accident detection device 100 dynamically changes the conditions for accident judgment between the normal judgment section and the judgment control section where impacts or sounds above a certain value occur periodically unrelated to accidents, thereby suppressing unnecessary accident detection while appropriately detecting accidents such as sudden movements, thereby reducing erroneous accident judgments.

[0027] (Functional configuration of the accident detection device 100) Next, an example of the functional configuration of the accident detection device 100 according to embodiment 1 will be described. Fig. 5 is a block diagram showing an example of the configuration of the accident detection device according to embodiment 1. As shown in Fig. 5, the accident detection device 100 includes, for example, a storage unit 110, a detection processing unit 120, a camera 130, a microphone 140, a video encoder processing unit 150, an audio encoder processing unit 160, a muxer unit 170, and an acceleration sensor 180.

[0028] Here, the detection processing unit 120, the video encoder processing unit 150, the audio encoder processing unit 160, and the muxer unit 170 are realized by a control unit such as a processor. The control unit such as a processor has an internal memory for storing programs that define various processing procedures and required data, and executes various processes using these. Here, the control unit is, for example, an electronic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). Furthermore, each unit may be realized by a processor.

[0029] The video encoder processing unit 150 is a processing unit that converts analog image data captured by the camera 130 into a digital signal. The audio encoder processing unit 160 is software that converts the format of an audio file of audio data acquired by the microphone 140.

[0030] Acceleration sensor 180 measures the acceleration of the vehicle. For example, acceleration sensor 180 measures acceleration along three axes: X-axis, Y-axis, and Z-axis. Acceleration sensor 180 then outputs information about the measured acceleration of the vehicle to detection processing unit 120.

[0031] The muxer unit 170 combines the imaging data and audio data to output the moving image file 110a. For example, the muxer unit 170 combines the imaging data output from the video encoder processing unit 150 with the audio data output from the audio encoder processing unit 160 to output the moving image file 110a.

[0032] The memory unit 110 stores various programs executed by the detection processing unit 120, data required when the detection processing unit 120 performs processing, video file 110a output by the muxer unit 170, analyzed audio data output by the audio detection unit 120b described later, and the like.

[0033] The detection processing unit 120 detects a vehicle accident from the acquired voice data, measurement data of the acceleration sensor, etc. The detection processing unit 120 has an impact detection unit 120a, a voice detection unit 120b, a windowing unit 120c, an FFT unit 120d, a determination unit 120e, an estimation unit 120f, and a condition change unit 120g.

[0034] The impact detection unit 120a detects an impact that occurs to the vehicle. For example, the impact detection unit 120a classifies the accident based on the value of a resultant vector of Gx, Gy, and Gz, which are accelerations on the X-axis, Y-axis, and Z-axis, respectively, measured by the acceleration sensor 180.

[0035] The classification of accidents based on the value of the resultant vector will be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of classification of impacts detected by the impact detection unit 120a according to the first embodiment. When the value of the resultant vector is a high impact equal to or greater than threshold (1), the impact detection unit 120a detects it as a major accident, and when the value of the resultant vector is an impact less than threshold (1) and equal to or greater than threshold (2), the impact detection unit 120a detects it as a medium or minor accident. Furthermore, when the impact is less than threshold (2), the impact detection unit 120a detects it as a sudden movement.

[0036] The voice detection unit 120b performs a short-time Fourier transform (STFT) on the voice data acquired by the microphone 140 to create analysis data indicating the sum of the amplitudes of all frequency bands of the voice data for each time period, and stores the analysis data in the storage unit 110. For example, the voice detection unit 120b sequentially performs processing on the voice data by a windowing unit 120c and an FFT unit 120d, which will be described later.

[0037] The windowing unit 120c is a processing unit that multiplies input signal data, which is audio data acquired from the microphone 140 or the like, by a window function of a specific analysis frame length on the time axis. For example, the windowing unit 120c extracts frames of a specific time length from the input signal data for each frame period and multiplies the frames by a window function, for example, a Hanning window.

[0038] To reduce information loss due to the window function, the windowing unit 120c can overlap the preceding and following analysis frames at any desired rate. For example, by analyzing a fixed frame length of 512 samples at a fixed interval, every 256 samples, the overlap rate can be set to 50%. The analysis frame obtained in this way is output to the FFT unit 120d.

[0039] The FFT unit 120d is a processing unit that performs a Fast Fourier Transform (FFT). For example, the FFT unit 120d applies an FFT to the analysis frame that has been windowed by the windowing unit 120c. This converts the input signal of the analysis frame into an amplitude spectrum and a phase spectrum.

[0040] Thereafter, FFT unit 120d stores the amplitude spectrum obtained by FFT in storage unit 110. Furthermore, FFT unit 120d calculates the sum of the amplitudes of all frequency bands of the amplitude spectrum obtained by FFT, and stores the sum in storage unit 110. Note that although an example in which FFT is applied has been given here, other algorithms such as Fourier transform and discrete Fourier transform may also be applied to convert from the time domain to the frequency domain.

[0041] Here, the difference between the sound data after FFT analysis in normal times and when a contact sound is generated will be described. Fig. 7 is a diagram showing an example of sound data that has undergone FFT analysis according to embodiment 1. In the example of Fig. 7, an FFT is performed on sound data that includes a contact sound acquired by the microphone 140, and the amplitude value is shown for each frequency.

[0042] As shown in Figure 7, the graph showing the FFT results for normal times when no contact sound is included shows large amplitude values ​​in the low frequency band, indicating that the overall amplitude values ​​are small. On the other hand, the graph showing the FFT results for contact sound also shows large amplitude values ​​in the high frequency band, indicating that the overall amplitude values ​​are large.

[0043] Next, a description will be given of analysis data obtained by calculating the sum of amplitudes of all frequency bands after performing FFT on the audio data including the contact sound shown in Fig. 7. Fig. 8 is a diagram showing an example of audio data after FFT analysis used for accident detection according to embodiment 1. The example of Fig. 8 shows a graph in which the sum of amplitudes of all frequency bands after performing FFT on the audio data including the contact sound shown in Fig. 7 is calculated for each playback time (seconds).

[0044] In the graph shown in Figure 8, the vertical axis represents the sum of the amplitudes (Σ) of all frequency bands, and the horizontal axis represents the playback time (seconds) of the acquired audio data. As shown in Figure 8, the total amplitude value exceeds 600 around 9.7 seconds when the contact sound occurred, while the maximum total amplitude value at other times remains around 300. In other words, over the 16-second playback time, the audio data around 9.7 seconds when the contact sound occurred due to the accident is detected as the volume peak.

[0045] As a result, the FFT unit 120d can create analysis data capable of detecting volume peaks from the audio data acquired by the audio detection unit 120b, which is used by the judgment unit 120e, estimation unit 120f, and condition change unit 120g described below.

[0046] The determination unit 120e detects a vehicle accident based on the impact occurring on the vehicle and the sound inside the vehicle. This corresponds to the accident detection unit of the present invention. For example, the determination unit 120e acquires impact data created based on a resultant vector or moving average of the impact detected by the impact detection unit 120a. The determination unit 120e acquires sound data created based on the sound detected by the sound detection unit 120b. The determination unit 120e detects a vehicle accident by comparing the numerical values ​​of the acquired impact data and sound data with preset impact thresholds and sound thresholds.

[0047] For example, the determination unit 120e suppresses accident detection or changes the determination conditions in response to an instruction from the condition change unit 120g. When the determination unit 120e receives an instruction to suppress accident detection from the condition change unit 120g, the determination unit 120e suppresses the execution of the impact or noise accident detection process described below.

[0048] In addition, when the judgment unit 120e receives an instruction from the condition change unit 120g to change the impact threshold or sound threshold in the judgment conditions for accident detection, it changes the impact threshold or sound threshold conditions 1 to 3 described below to the instructed values.

[0049] Furthermore, when the determination unit 120e receives an instruction from the condition change unit 120g to correct the measured value of impact or noise in the determination conditions for accident detection, the determination unit 120e calculates the subtraction result by subtracting the average value calculated by the condition change unit 120g from the measured value of impact or noise that is equal to or greater than a predetermined value. The determination unit 120e compares the subtraction result with conditions 1 to 3 of the impact threshold or sound threshold described below to perform accident detection.

[0050] Here, the processing of the determination unit 120e will be specifically described. The determination unit 120e has preset impact thresholds, a major accident impact threshold for detecting a major accident and a minor / medium accident impact threshold for detecting a minor / medium accident. The determination unit 120e determines that an accident is a major accident when the composite vector value of the impact data is equal to or greater than the major accident impact threshold. The determination unit 120e determines that an accident is a minor / medium accident when the composite vector value is smaller than the major accident impact threshold and equal to or greater than the minor / medium accident impact threshold.

[0051] Furthermore, when the composite vector value of the impact data is less than the impact threshold for a small to medium accident, the determination unit 120e presets a sudden deceleration impact threshold for detecting sudden deceleration, a sudden acceleration impact threshold for detecting sudden acceleration, a sudden right-hand steering impact threshold for detecting sudden right-hand steering, and a sudden left-hand steering impact threshold for detecting sudden left-hand steering. Hereinafter, the sudden deceleration impact threshold, sudden acceleration impact threshold, sudden right-hand steering impact threshold, and sudden left-hand steering impact threshold are referred to as sudden behavior impact thresholds.

[0052] When the composite vector value of the impact data is less than the small-to-medium accident threshold, the determination unit 120e The moving average of the impact data is compared with the sudden behavior impact threshold to detect sudden behavior such as sudden deceleration, sudden acceleration, sudden right steering, and sudden left steering.

[0053] When detecting a sudden movement due to an impact, the determination unit 120e determines whether the sudden movement is an accident based on the acquired audio data. The determination unit 120e determines whether the sudden movement is an accident by determining whether conditions 1 to 3 described below are satisfied. The determination contents of conditions 1 to 3 will be described below in order.

[0054] (Explanation of condition 1) Condition 1 is a condition for determining whether a volume deviating from normal volume has been detected from audio data after analysis for about 20 seconds including the time point at which an impact was detected. Fig. 9 is a diagram showing an example of the processing content of the accident detection unit according to the first embodiment. As shown in Fig. 9, the determination unit 120e detects the volume peak at around 9.7 seconds, which indicates a contact sound, as audio that may be deviating from normal volume and may indicate a contact.

[0055] Here, a specific example of the determination content of condition 1 by the determination unit 120e will be described. Fig. 10 is a diagram showing an example of the processing content of the accident detection unit according to embodiment 1. Fig. 10 shows an example of the case where the sum of the amplitudes of all frequency bands of audio data is calculated at intervals of 100 ms by FFT, and a sudden change in volume is detected when the calculated sum of amplitudes satisfies the following (1) to (4):

[0056] First, the determination unit 120e performs outlier determination to determine whether the target amplitude is an outlier compared to the immediately preceding sound field (condition 1-(1)). Specifically, the determination unit 120e determines whether the following condition is satisfied: "total amplitude value Σ of the target amplitude for 100 ms > average of amplitude Σ for the immediately preceding 5 seconds + 3σ." Note that σ is the standard deviation.

[0057] Next, the determination unit 120e performs a gradient determination to determine whether the target amplitude is abruptly changing in volume (Condition 1-(2)). Specifically, the determination unit 120e determines whether the following is satisfied: "target amplitude 100 ms Σ - amplitude sum Σ of the immediately preceding amplitude 100 ms > gradient threshold."

[0058] Next, the determination unit 120e performs a contact volume determination to determine whether the target amplitude is equivalent to the contact volume (condition 1-(3)). Specifically, the determination unit 120e determines whether the "total amplitude value Σ of the target amplitude of 100 ms > contact volume threshold" is satisfied. Hereinafter, the contact volume threshold will be referred to as the audio threshold.

[0059] Then, the determination unit 120e performs a detection validity determination to determine whether or not the immediately preceding sound field is detectable (condition 1-(4)). Specifically, the determination unit 120e determines whether or not "amplitude σ for the immediately preceding 5 seconds < threshold value of detection validity σ" is satisfied.

[0060] 10, the determination unit 120e performs determinations on the above-described conditions 1-(1) to 1-(4), and thereby detects the sum of the amplitudes around 9.7 seconds as a volume peak that may be a contact sound that deviates from normal conditions and satisfies all of conditions 1-(1) to 1-(4). In other words, the determination unit 120e determines that condition 1 is satisfied. Note that the order in which the determination unit 120e performs determinations on the above-described conditions 1-(1) to 1-(4) is not particularly limited.

[0061] (Explanation of condition 2) Condition 2 is a condition for determining whether or not a volume peak that satisfies the above-mentioned condition 1 exists between 2 seconds before and 1 second after the point in time when a sudden movement is detected. Fig. 11 is a diagram showing an example of the processing content of the determination unit 120e according to the first embodiment. Fig. 11 shows an example in which a sudden movement is detected at a point in time of 10 seconds of playback time in the audio data.

[0062] As shown in FIG. 11, the judgment unit 120e judges that condition 2 is met because a volume peak that satisfies the above-mentioned condition 1 is detected around 9.7 seconds, between 10 seconds into the playback time when the sudden behavior was detected and the previous 2 seconds.

[0063] (Explanation of condition 3) Condition 3 is a condition for determining whether the vehicle slows down or stops within a certain distance from the point where the sudden movement is detected. The certain distance is the distance at which the vehicle is expected to slow down or stop in the event of a vehicle accident, and is set to, for example, 100 m. Note that the certain distance is not limited to 100 m, but may be 200 m, and can be changed as appropriate based on the results of demonstrations and research.

[0064] The certain distance can be acquired by a GPS (Global Positioning System) sensor (not shown). Note that the method for measuring the distance is not limited to a GPS sensor, and various methods for measuring the distance can be used. For example, the distance may be measured based on parameters acquired from a vehicle speed sensor, or based on an odometer value acquired via a CAN (Controller Area Network).

[0065] For example, the determination unit 120e determines that condition 3 is satisfied when the vehicle speed becomes equal to or lower than a slow speed within 100 meters, which is an example of a certain distance, from the point where the sudden behavior was detected. Explaining this using the example of Fig. 11, the accident detection unit 125 uses the vehicle position at the point 10 seconds into the playback time when the sudden behavior was detected as a reference, and determines that condition 3 is satisfied when the vehicle speed within a certain distance (e.g., 100 meters) from the reference becomes equal to or lower than a threshold value (e.g., 5 km / hour) or when the vehicle speed becomes 0 m / hour.

[0066] Furthermore, Condition 3 is not limited to the distance from the detection of the sudden movement, but can also be the time from the detection of the sudden movement to the vehicle stopping. For example, the determination unit 120e determines that Condition 3 is satisfied if the vehicle 20 stops within a certain time (for example, within 10 seconds) after the detection of the sudden movement. Note that the 10 seconds period exemplified here is merely an example, and the setting can be changed as appropriate. Furthermore, the time can be measured by a general method, such as using time information or a timer in the accident detection device 100 or another in-vehicle device to measure the time from the detection of the sudden movement until the vehicle speed becomes equal to or less than a threshold.

[0067] As described above, when the detection result of the impact detection unit 120a determines that an abrupt movement has occurred, the determination unit 120e additionally determines whether or not all of the above-mentioned conditions 1 to 3 are satisfied. As a result, when all of the above-mentioned conditions 1 to 3 are satisfied, the determination unit 120e determines that contact occurred when the impact was detected, and determines that the driver has determined that it is an accident and has slowed down or stopped the vehicle, thereby properly detecting the impact that was erroneously detected as an abrupt movement as an accident.

[0068] Returning to FIG. 5, the estimation unit 120f estimates the timing of the next impact or noise when impacts or noise occur periodically. This corresponds to the estimation unit of the present invention. For example, the estimation unit 120f acquires impact data created based on a resultant vector or moving average of the impact detected by the impact detection unit 120a. The estimation unit 120f also acquires audio data (including audio data analyzed by the windowing unit 120c and FFT unit 120d) created based on the audio detected by the audio detection unit 120b.

[0069] Then, when it is confirmed from the acquired impact data and sound data that the impact or noise occurs periodically, the estimation unit 120f estimates the timing of the next impact or noise to occur from the impact data and sound data, and creates estimated data.

[0070] For example, the estimation unit 120f determines that the shock or sound is occurring periodically if the acquired shock data and sound data show that the shock or sound is greater than or equal to a certain value and continues for 0.5 seconds or more, and this occurs at least twice at a predetermined interval.The estimation unit then measures the timing of the shock or sound from the acquired shock data and sound data, estimates the timing of the next shock or sound, and creates estimated data.The estimation unit 120f then outputs the created estimated data to the condition change unit 120g, along with the shock data and sound data.

[0071] As another example, the estimation unit 120f estimates the distance on the road surface of the structure that causes the impact and noise, using the traveling speed and the timing of impacts and noises that have already occurred periodically. The estimation unit 120f can also estimate the timing of the occurrence of impacts and noise from the traveling speed and the distance.

[0072] For example, if impacts and noises are already occurring at 1-second intervals while traveling at 40 km / h, the estimation unit 120f estimates that there are bumps on the road surface at intervals of 10 to 11 m. If the vehicle then travels at 50 km / h, the estimation unit 120f estimates that impacts and noises will occur at intervals of 0.7 to 0.8 seconds.

[0073] When periodic impacts or sounds no longer occur, the estimation unit 120f instructs the determination unit 120e to cancel the suppression of accident detection or the change of the determination conditions. For example, after determining that impacts or sounds are occurring periodically, the estimation unit 120f instructs the determination unit 120e to cancel the suppression of accident detection or the change of the determination conditions when it determines from the impact data and the sound data that impacts or sounds of a certain value or more are not occurring at a predetermined interval.

[0074] The condition changing unit 120g calculates the average level of periodically occurring impacts and noises based on the impact data, audio data, and estimation data input from the estimation unit 120f. The condition changing unit 120g corresponds to the judgment control unit of the present invention. For example, the condition changing unit 120g obtains the amplitude of periodically occurring impacts or noises based on the impact data and audio data, and calculates the average level of the obtained noise amplitudes. Similar processing is performed in the case of impacts.

[0075] For example, the condition changing unit 120g obtains the peak amplitude of each noise that occurs at a regular interval from the audio data input from the estimation unit 120f, sums the peak values ​​of the noise, and calculates the average value of the noise amplitude.

[0076] Similarly, the condition change unit 120g obtains the peaks of each impact that occurs at regular intervals from the impact data input from the estimation unit 120f, sums the values ​​of the impact peaks, and calculates the average value of the composite vector value of the impact.

[0077] Then, the condition change unit 120g instructs the judgment unit 120e to suppress accident detection, change the judgment conditions, or suppress accident detection and change the judgment conditions. For example, the condition change unit 120g causes the judgment unit 120e to suppress accident detection of impact, sound, or shock and sound for impact and noise that will occur at the next timing, depending on the average values ​​of the periodically occurring impacts and noises. Alternatively, the condition change unit 120g causes the judgment unit 120e to change the impact condition, sound condition, or impact condition and sound condition of the judgment conditions used for accident detection for impact and noise that will occur at the next timing, depending on the average values ​​of the periodically occurring impacts and noises. Note that here, the section in which the judgment unit 120e suppresses accident detection or changes the judgment conditions is referred to as the judgment control section.

[0078] As described above, the condition change unit 120g can instruct the determination unit 120e to perform one of the following control operations: suppressing accident determination, changing the thresholds for impact and sound, and determining an accident after correcting the measured values ​​of impact and sound. However, the condition change unit 120g is not limited to this, and can dynamically determine the control operation based on the measured impact, sound, etc., and instruct the determination unit 120e to perform the control operation.

[0079] For example, when shocks or noises occur periodically in a driving state where shocks are relatively small, the condition change unit 120g instructs the determination unit 120e to change the shock threshold for determining an accident. For example, when periodic shocks or noises are detected in a state where the difference between the value of the composite vector of the shocks and a preset shock threshold (the first threshold according to the present invention) is close to a predetermined value and less than a predetermined value, the condition change unit 120g instructs the determination unit 120e to change the shock threshold to a value corresponding to the average value of the composite vector. As a result, the determination unit 120e compares the measurement value of the shocks that occurred with the changed shock threshold within the determination control section to perform accident detection.

[0080] Similarly, for audio, if shocks or noise occur periodically while the vehicle is traveling with relatively low noise levels, the condition change unit 120g instructs the determination unit 120e to change the audio threshold for determining an accident. For example, if periodic audio or the like is detected in a state where the difference between the average amplitude of the noise and a preset audio threshold (a second threshold according to the present invention) is close to and less than a predetermined value, the condition change unit 120g instructs the determination unit 120e to change the audio threshold to a value corresponding to the average amplitude. As a result, the determination unit 120e compares the measurement value of the generated noise with the changed audio threshold within the determination control section to detect an accident.

[0081] For example, when shocks or noises occur periodically during driving in a relatively small shock state, the condition change unit 120g instructs the vehicle to correct the shock measurement value and then perform accident determination. For example, when periodic shocks or noises are detected while the difference between the shock resultant vector value and a preset shock threshold value is equal to or greater than a predetermined value and less than an upper threshold value, the condition change unit 120g instructs the vehicle to perform accident detection using the subtraction result obtained by subtracting the average value of the calculated resultant vector value from the measured shock resultant vector value. As a result, the determination unit 120e compares the calculated subtraction result with the shock threshold value to perform accident detection.

[0082] Similarly, for audio, if shocks or noise occur periodically while the audio is relatively quiet while driving, the condition change unit 120g instructs the system to correct the audio measurement value and then perform accident determination. For example, if periodic audio or the like is detected while the difference between the average noise amplitude and a preset audio threshold is equal to or greater than a predetermined value and less than an upper threshold, and they are not close to each other, the condition change unit 120g instructs the system to perform accident detection using the result of subtracting the calculated average noise amplitude from the measured noise amplitude. As a result, the determination unit 120e compares the calculated subtraction result with the audio threshold to perform accident detection.

[0083] Furthermore, the condition change unit 120g instructs the determination unit 120e to suppress accident detection when shocks or noise occur periodically in a driving state where shocks are very large. For example, when a periodic shock or the like is detected in a state where the difference between the value of the composite shock vector and a preset shock threshold value is equal to or greater than an upper threshold, the condition change unit 120g instructs the determination unit 120e to suppress accident detection of shocks.

[0084] Similarly, for audio, the condition change unit 120g instructs the determination unit 120e to suppress accident detection when shocks or noise occur at regular intervals in a driving state where the noise is very loud. For example, when periodic audio or the like is detected in a state where the difference between the average amplitude of the noise and a preset shock threshold is equal to or greater than an upper threshold, the condition change unit 120g instructs the determination unit 120e to suppress accident detection for audio.

[0085] (Example of processing) Next, the process of changing the conditions for accident determination executed by the accident detection device 100 will be described using a specific example.

[0086] First, the assumptions for changing the conditions for accident determination will be described. For example, a vehicle equipped with the accident detection device 100 passes through a road paved with speed limiting pavement while traveling down a steep slope. At this time, the vehicle experiences impact and noise.

[0087] The impact detection unit 120a detects an impact, and the sound detection unit 120b detects noise. The estimation unit 120f then acquires impact data and sound data from the impact detection unit 120a and sound detection unit 120b. While the following description will be given using sound data, similar processing is also performed on the impact data.

[0088] (Example of threshold change) Next, a series of processes performed when the determination unit 120e receives an instruction from the condition change unit 120g to change the impact threshold or the sound threshold in the determination conditions for accident detection will be described.

[0089] The estimation unit 120f checks whether peaks occur periodically in the acquired audio data. For example, assume that the estimation unit 120f acquires the audio data shown in FIG. 12, which shows the sum of the amplitudes of all frequency bands of the audio data by FFT in 0.5-second increments. The estimation unit 120f then checks for peaks of 0.5 seconds or longer at points (A) and (B) during the six seconds from 5.5 seconds to 11.5 seconds. This allows the estimation unit 120f to determine that noise is occurring periodically.

[0090] Next, the estimation unit 120f estimates the timing of the next peak from the timing of the peak occurrence in the acquired voice data. Because it is 3 seconds from the peak at point (A) to the peak at point (B), the estimation unit 120f estimates that the timing of the next noise occurrence will be between 13 and 13.5 seconds, and estimates that noise will occur between 3 and 3.5 seconds thereafter. The estimation unit 120f outputs the estimation result as estimated data together with the voice data to the condition change unit 120g.

[0091] Next, based on the input estimated data and audio data, the condition changing unit 120g acquires a total amplitude value 85, which is the peak at point (A), and a total amplitude value 88, which is the peak at point (B). The condition changing unit 10f sums the acquired total amplitude values ​​85 and 88, which are the peaks of the noise, and calculates a total amplitude value of 86.5, which is the average value.

[0092] The calculated average noise value is a total amplitude value of 86.5, which is greater than or equal to the total amplitude value of 60 of the audio threshold (threshold (A) in FIG. 12) set for the normal determination section. Therefore, in order to deal with the next noise that will occur around 13 seconds, the condition change unit 120g instructs the determination unit 120e to change the audio threshold to a total amplitude value of 90 or greater (threshold (B) in FIG. 12) from 12 seconds onwards so that the total amplitude value of 86.5 of the average noise value is excluded from the detection target. Thereafter, the determination unit 120e performs accident detection using a total amplitude value of 90 or greater for the audio threshold as the noise condition among the accident determination conditions.

[0093] (Example of how to resolve threshold changes) Thereafter, when the estimation unit 120f confirms from the audio data continuously acquired from the audio detection unit 120b that no noise has occurred for 10 seconds, it determines that the occurrence of periodic noise has ended. The estimation unit 120f instructs the determination unit 120e to cancel the noise condition in which the audio threshold was changed to a total amplitude value of 90 or more, and to return the audio threshold set in the normal determination section to a total amplitude value of 60 or more. The determination unit 120e then performs accident detection using a total amplitude value of 60 or more for the audio threshold as a noise condition.

[0094] (Example of measurement value correction) Next, a case where the determination unit 120e receives an instruction from the condition change unit 120g to subtract a noise measurement value will be described. Only the parts that differ from the series of processes when an instruction to change the impact threshold or sound threshold is received will be described.

[0095] When noise equal to or greater than a predetermined value is measured in the judgment control section, the judgment unit 120e performs accident detection by comparing the result of subtracting the average value of the impact or noise calculated by the condition change unit 120g with the audio threshold.

[0096] 13, when audio with a total amplitude value of 175 is measured in the determination control section, the determination unit 120e subtracts the total amplitude value of 86.5, which is the average noise value calculated by the condition change unit 120g, to obtain a subtraction result of 88.5. The determination unit 120e compares the subtraction result of 88.5 with the audio threshold value of 60 to perform accident detection.

[0097] The determination unit 120e may also perform accident determination using audio data for each frequency band. In this case, when audio of a predetermined value or more is detected in the determination control section, the determination unit 120e performs accident detection using the audio data for each frequency band, as shown in Fig. 14. In this case, the average value for each frequency band calculated by the condition change unit 120g is subtracted from the frequency at the time of contact for each frequency band, and the result of the subtraction is compared with the audio threshold to perform accident determination.

[0098] For example, in frequency band XX, the determination unit 120e subtracts the average amplitude 2.8 from the amplitude 6.2 of the frequency at the time of contact to obtain a subtraction result of 3.4, and compares this result with the audio threshold to determine whether an accident has occurred.

[0099] As another example, the determination unit 120e may perform accident determination using impact data in which the average speed of the impact is calculated for each of multiple directional components. In this case, the condition modification unit 120g creates impact data by calculating the average values ​​of directional components such as the x-axis, y-axis, and z-axis. When an impact of a predetermined value or greater is measured in a determination control section in which periodic impacts or sounds are detected, the determination unit 120e subtracts the average value of the impact data created by the condition modification unit 120g from the measured values ​​of the directional components of the impact such as the x-axis, y-axis, and z-axis to calculate the subtraction results for each directional component. The determination unit 120e performs accident determination by comparing the sum of the calculated subtraction results with an impact threshold.

[0100] (Processing flow) Next, the processing of the accident detection device 100 will be described with reference to flowcharts 15 to 17. The steps in the flowcharts shown in the figures may be executed in a different order, and some processing may be added or omitted.

[0101] (Accident detection process flow) An example of the procedure for the accident detection process of the accident detection device 100 will be described using the flowchart showing the flow of the accident detection process shown in Fig. 15. The accident detection device 100 detects an impact or noise while driving. The accident detection device 100 acquires impact data and sound data that are constantly being acquired (S11).

[0102] Next, if the accident detection device 100 cannot acquire the impact data and the audio data (S11: NO), it repeats the acquisition process until it can acquire them. On the other hand, if the accident detection device 100 can acquire the impact data and the audio data (S11: YES), it checks whether the accident detection is continuing (S12).

[0103] If accident detection is not being performed (S12: NO), the accident detection device 100 ends the process. On the other hand, if accident detection is continuing (S12: YES), the accident detection device 100 determines whether the detected impact data or sound data satisfies the accident determination condition (S13).

[0104] Next, if the detected impact data or audio data satisfies the accident determination condition (S13: YES), the accident detection device 100 detects that an accident has occurred (S14) and ends the process. On the other hand, if the detected impact data or audio data does not satisfy the accident determination condition (S13: NO), the accident detection device 100 detects that no accident has occurred (S15) and ends the process.

[0105] (Flow of judgment condition change process) An example of the procedure for changing the determination conditions of the accident detection device 100 will be described using a flowchart shown in Fig. 16, which illustrates the flow of changing the determination conditions in S13 in Fig. 15. The accident detection device 100 detects an impact or noise while driving. The accident detection device 100 acquires impact data and sound data that are constantly being acquired (S21).

[0106] Next, the accident detection device 100 determines whether the detected impact or sound is an impact or noise equal to or greater than a predetermined value (S22). If the detected impact or noise is less than the predetermined value (S22: NO), the accident detection device 100 ends the process. On the other hand, if the detected impact or noise is equal to or greater than the predetermined value (S22: YES), the accident detection device 100 determines whether the impact or noise occurs at a regular interval (S23).

[0107] If the accident detection device 100 determines that the impact or noise does not occur at regular intervals (S23: NO), it maintains the determination condition (S26) and ends the process. On the other hand, if the accident detection device 100 determines that the impact or noise occurs at regular intervals (S23: YES), it estimates the timing of the next impact or noise from the impact data and audio data (S24).

[0108] Thereafter, the accident detection device 100 suppresses accident detection or changes the impact threshold or sound threshold, which are the criteria for determining accident detection, based on the impact or noise occurring at regular intervals (S25), and ends the process.

[0109] (Flow of resetting judgment conditions (returning to original)) 17, a flowchart showing the flow of processing for restoring changed determination conditions to their original state will be used to describe an example of the procedure for processing to restore the determination conditions of the accident detection device 100. The accident detection device 100 acquires impact data and sound data that are constantly acquired (S31).

[0110] If the accident detection device 100 is unable to acquire the impact data and audio data (S31: NO), it repeats the acquisition process until the data is acquired. On the other hand, if the accident detection device 100 is able to acquire the impact data and audio data (S31: YES), it checks whether the judgment conditions have been changed (S32).

[0111] If the accident detection device 100 determines that the accident determination conditions have not changed (S32: NO), the process ends. If the accident detection device 100 determines that the accident determination conditions have changed (S32: YES), the accident detection device 100 determines whether an impact or noise has occurred at a regular interval (S33).

[0112] If the accident detection device 100 determines from the impact data or audio data that impacts or noises occur at regular intervals (S33: YES), it maintains the determination conditions (S34) and ends the process. If the accident detection device 100 determines from the impact data or audio data that impacts or noises do not occur at regular intervals (S33: NO), it returns the determination conditions to their original state (S35) and ends the process.

[0113] (effect) As described above, the accident detection device 100 includes an estimation unit 120f, a condition change unit 120g, and a determination unit 120e. The estimation unit 120f estimates the timing of the next occurrence of an impact or noise when an impact or noise occurs at a regular interval. The condition change unit 120g suppresses accident detection or changes the impact threshold or sound threshold of the determination conditions within a predetermined period including the timing estimated by the estimation unit 120f. The determination unit 120e detects an accident from the impact or noise that has occurred based on the determination conditions.

[0114] As a result, the accident detection device 100 can reduce the influence of shocks or noises that occur at regular intervals, thereby enabling more accurate accident detection, by changing the shock threshold or sound threshold, which are the criteria for preventing or determining accident detection, depending on the degree of shock or noise that occurs at regular intervals.

[0115] Furthermore, when an impact or noise of a predetermined value or greater occurs while the impact threshold or sound threshold, which is a condition for preventing or determining accident detection, is being changed, the accident detection device 100 calculates the average value of the impact or noise occurring at a regular interval, and compares the subtraction result, obtained by subtracting the average value from the impact or noise value, with the impact threshold or sound threshold, thereby enabling more accurate accident detection.

[0116] [Embodiment 2] Incidentally, the above-described accident detection device 100 immediately performs STFT on the voice data acquired during normal driving and stores the analyzed voice data in the memory unit 110, but the accident detection device 100 of the present invention is not limited to this.

[0117] For example, the accident detection device 100 does not perform STFT when acquiring voice data during normal driving, but stores the pre-analysis voice data in the storage unit 110. Then, when the accident detection device 100 determines that an impact that occurred to the vehicle is a sudden movement, it can retroactively acquire the most recent voice data up to the point in time when the impact was detected, and perform STFT on the acquired voice data to create analyzed voice data.

[0118] The following describes the processing details of the accident detection device 100 according to embodiment 2. Fig. 18 is a diagram illustrating the processing details of the accident detection device according to embodiment 2. Fig. 18 shows an example of a case where, regardless of the detection of a sudden movement, voice data is analyzed at the same time as it is acquired to create analyzed voice data (Fig. 18(1)), and a case where, after a sudden movement is detected, the most recent stored voice data is retroactively acquired and analyzed to create analyzed voice data (Fig. 18(2)).

[0119] 18(1), when detecting audio data immediately regardless of whether the detected audio data is a sudden movement, the accident detection device 100 calculates the sum of the amplitudes of the audio data acquired every 100 ms, creates analyzed audio data indicating the sum of the amplitudes of the audio data for a predetermined period of time, and stores the analyzed audio data in the storage unit 110. In this case, the accident detection device 100 repeatedly performs a series of processes from acquiring the audio data to storing the analyzed audio data until detecting a sudden movement.

[0120] When the accident detection device 100 detects a sudden movement, it uses the analyzed audio data stored in the memory unit 110, including the time when the impact was detected, to make judgments based on the above-mentioned conditions 1 to 3, and detects a vehicle accident.

[0121] 18(2), when analyzing audio data retroactively after detecting a sudden movement, the accident detection device 100 repeatedly stores the acquired audio data every 100 ms as is in the storage unit 110. When detecting a sudden movement, the accident detection device 100 retroactively acquires the pre-analysis audio data stored in the storage unit 110 up to the point in time when the sudden movement was detected, creates post-analysis audio data indicating the sum of the amplitudes, and then performs the determinations under conditions 1 to 3 described above to detect a vehicle accident.

[0122] (Processing flow of the accident detection device 100 according to the second embodiment) Next, an example of a processing procedure performed by the accident detection device 100 according to the second embodiment will be described with reference to Fig. 19. Fig. 19 is a flowchart showing an example of the flow of the accident detection processing according to the second embodiment. Note that the steps in the flowchart shown in Fig. 19 may be executed in a different order, and some processing may be added or omitted.

[0123] 19 shows an example in which the accident detection device 100 analyzes the voice data after detecting a sudden movement and determines whether the detected sudden movement is an accident. Note that it is assumed that the accident detection device 100 repeatedly performs the process of acquiring the voice data and storing it in the storage unit 110 before detecting the sudden movement.

[0124] First, the accident detection device 100 determines whether or not a sudden movement has been detected from an impact that has occurred to the vehicle (S301). If a sudden movement has not been detected (S301; No), the accident detection device 100 waits until a sudden movement is detected. On the other hand, if a sudden movement has been detected (S301; Yes), the accident detection device 100 retroactively acquires audio data from the storage unit 110, including the time when the sudden movement was detected (S302). Then, the accident detection device 100 analyzes the retroactively acquired audio data and calculates the sum of the amplitudes of all frequency bands for each time period (S303).

[0125] Then, the accident detection device 100 determines whether or not a sound deviating from normal sounds has been detected in the analyzed sound data including the time when the sudden behavior was detected (Condition 1) (S304). If a sound deviating from normal sounds has been detected in the analyzed sound data (S304; Yes), the accident detection device 100 determines whether or not a sound deviating from normal sounds has been detected near the time when the sudden behavior was detected (Condition 2) (S305). If a sound deviating from normal sounds has been detected near the time when the sudden behavior was detected (S305; Yes), the accident detection device 100 determines whether or not the vehicle slowed down or stopped within 200 m of the sudden behavior detection (Condition 3) (S306).

[0126] If the vehicle slows down or stops within 200 m of the sudden movement detection (S306; Yes), the accident detection device 100 determines that the detected sudden movement is an accident (S307) and ends the process. On the other hand, if no sound deviating from normal is detected in the analyzed sound data (S304; No), if no sound deviating from normal is detected near the time of the sudden movement detection (S305; No), or if the vehicle does not slow down or stop within 200 m of the sudden movement detection (S306; No), the accident detection device 100 determines that the detected sudden movement is not an accident (S308) and ends the process.

[0127] (effect) As described above, after detecting a sudden movement, the accident detection device 100 according to the second embodiment analyzes the voice data including the time point at which the sudden movement was detected. As a result, the accident detection device 100 omits the analysis related to the execution of STFT on the voice data during normal driving when no sudden movement was detected, and analyzes only the voice data used to determine an accident when a sudden movement was detected, thereby reducing the processing load related to the analysis of the voice data and reducing power consumption.

[0128] [Embodiment 3] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments. The present invention may also be implemented in a variety of different forms.

[0129] (Numbers, etc.) The numerical values, graphs, threshold values, etc. (for example, arbitrary numerical values) used in the above embodiments are merely examples and can be changed as desired. Also, in the above embodiments, an example using the amplitude of sound has been described, but this is not limiting, and similar processing can also be performed using sound pressure "decibels (db)." Note that each embodiment can be applied to various vehicles such as private cars, taxis, buses, electric vehicles, hybrid vehicles, motorcycles, and motorcycles.

[0130] [Hardware configuration] The accident detection device 100 according to the first and second embodiments described above is realized, for example, by a computer 1000 configured as shown in FIG. 20. The accident detection device 100 will be described below as an example. FIG. 20 is a hardware configuration diagram showing an example of a computer that realizes the functions of the first and second embodiments and the accident detection device according to the second embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0131] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0132] HDD 1400 stores programs executed by CPU 1100, data used by such programs, etc. Communication interface 1500 receives data from other devices via a predetermined communication network and sends it to CPU 1100, and transmits data generated by CPU 1100 to other devices via a predetermined communication network.

[0133] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0134] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0135] For example, when the computer 1000 functions as the accident detection device 100 according to the first and second embodiments, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to implement the functions of the detection processing unit 120, the video encoder processing unit 150, the audio encoder processing unit 160, and the muxer unit 170. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0136] 〔others〕 Furthermore, among the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0137] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0138] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0139] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the aspects described in the Disclosure of the Invention section, as well as in various modifications and improvements based on the knowledge of those skilled in the art.

[0140] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, a receiving section can be read as receiving means or receiving circuit. [Explanation of symbols]

[0141] 100 Accident detection device 110 Storage section 120 Detection processing unit 120a Impact detection unit 120b Audio detection unit 120c window hanging part 120d FFT section 120e Judgment section 120f Estimation part 120g Condition change section 130 Camera 140 Mike 150 Video encoder processing unit 160 Audio Encoder Processing Unit 170 Muxer section 180 Accelerometer 300 External server device

Claims

1. an accident detection unit that detects an accident in the vehicle based on at least one of an impact occurring to the vehicle and a sound inside the vehicle; an estimation unit that estimates the timing of the next impact and noise to occur based on the periodic impact and the sound; a determination control unit that suppresses accident detection of the vehicle or changes a determination condition used for accident detection of the vehicle within a predetermined period including the timing; An accident detection device comprising:

2. The accident detection unit detecting an accident involving the vehicle when an impact equal to or greater than a first threshold and a sound equal to or greater than a second threshold are detected as the determination conditions; The determination control unit changing the second threshold value among the determination conditions used for detecting an accident of the vehicle within a predetermined period including the timing, according to an average value of the periodically occurring noise; 2. The accident detection device according to claim 1.

3. The accident detection unit detecting an accident involving the vehicle when an impact equal to or greater than a first threshold and a sound equal to or greater than a second threshold are detected as the determination conditions; The determination control unit changing the first threshold value among the determination conditions used for detecting an accident in the vehicle within a predetermined period including the timing, according to an average value of the periodically occurring impacts; 2. The accident detection device according to claim 1.

4. The determination control unit Calculating an average value of the periodically occurring noise; The accident detection unit When the audio having a predetermined value or more is detected within a predetermined period including the timing, the average value is subtracted from the audio to calculate a subtraction result; comparing the subtraction result with a threshold value to perform accident detection for the vehicle; 2. The accident detection device according to claim 1.

5. The determination control unit Calculating an average value of the noise for each frequency band; The accident detection unit calculating a subtraction result for each frequency band by subtracting each average value for each frequency band from the sound for each frequency band; and performing accident detection for the vehicle by comparing the sum of the subtraction results for each frequency band with the threshold value.

5. The accident detection device according to claim 4.

6. The determination control unit Calculating an average value of the periodically occurring impacts; The accident detection unit If the impact is detected to be equal to or greater than a predetermined value within a predetermined period including the timing, the average value is subtracted from the impact to calculate a subtraction result; comparing the subtraction result with a threshold value to perform accident detection for the vehicle; 2. The accident detection device according to claim 1.

7. The determination control unit Calculating an average acceleration of the impact for each of a plurality of directional components; The accident detection unit When the impact having a predetermined value or more is detected within a predetermined period including the timing, subtracting each average acceleration for each of the plurality of directional components from the impact for each of the plurality of directional components, and calculating a subtraction result for each of the directional components; and detecting an accident involving the vehicle by comparing the sum of the subtraction results for each directional component with the threshold value.

7. The accident detection device according to claim 6.

8. The estimation unit estimating a distance on the road surface between a structure that causes the impact and the noise, using the traveling speed of the vehicle and the timing of the impact and the noise that have already occurred; estimating the timing of the next impact and noise to occur based on the estimated distance and the traveling speed; 2. The accident detection device according to claim 1.

9. An accident detection method executed by an accident detection device, an accident detection step of detecting an accident in the vehicle based on at least one of an impact occurring to the vehicle and a sound inside the vehicle; an estimation step of estimating the timing of the next impact and noise based on the periodic impact and sound; a determination control step of suppressing accident detection of the vehicle or changing a determination condition used for accident detection of the vehicle within a predetermined period including the timing; An accident detection method comprising:

10. an accident detection step of detecting an accident in the vehicle based on at least one of an impact occurring to the vehicle and a sound inside the vehicle; an estimation step of estimating timings of the next impact and noise based on the periodic impact and sound; a determination control step of suppressing accident detection of the vehicle or changing a determination condition used for accident detection of the vehicle within a predetermined period including the timing; An accident detection program characterized by causing a computer to execute the above.

Images