Determination device, determination method, and determination program

Abstract

This determination device 10 mounted on a vehicle is characterized by including: a first detection unit 12a that detects that a collision has occurred to the vehicle; a second detection unit 12b that detects a voice inside the vehicle; and a determination unit 12d that determines an accident of the vehicle on the basis of detection results of the first detection unit 12a and the second detection unit 12b, the determination unit 12d determining that an accident has occurred when the first detection unit 12a detects a collision of a predetermined value or more and the second detection unit 12b detects a sudden change in the volume of the voice within a predetermined period including the timing at which the collision was detected.

Description

Determination device, determination method, and determination program

[0001] The present invention relates to a determination device, a determination method, and a determination program.

[0002] Drive recorders, which store vehicle status information (forward video, 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, and commercial vehicles such as taxis and buses, and are also increasingly being installed in general vehicles.

[0003] Japanese Patent Application Laid-Open No. 2022-000818

[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 object, the device aims to perform appropriate detection of accidents.

[0006] The present invention provides a determination device to be mounted on a vehicle, the determination device having a first detection unit that detects an impact occurring to the vehicle, a second detection unit that detects sound inside the vehicle, and a determination unit that determines an accident involving the vehicle based on the detection results of the first detection unit and the second detection unit, wherein the determination unit determines that an accident has occurred when the first detection unit detects an impact equal to or greater than a predetermined value and the second detection unit detects a sudden change in the volume of the sound within a predetermined period including the time when the impact was detected.

[0007] FIG. 1 is a diagram illustrating an example of the overall configuration of a system according to a first embodiment. FIG. 2 is a diagram illustrating an example of a problem in a general accident determination process. FIG. 3 is a diagram illustrating processing details of a determination device according to the first embodiment. FIG. 4 is a diagram illustrating an example of a block diagram of a determination device according to the first embodiment. FIG. 5 is a diagram illustrating an example of a classification of an impact detected by an impact detection unit according to the first embodiment. FIG. 6 is a diagram illustrating an example of audio data subjected to FFT analysis according to the first embodiment. FIG. 7 is a diagram illustrating an example of audio data subjected to FFT analysis according to the first embodiment. FIG. 8 is a diagram illustrating an example of a determination condition according to the first embodiment. FIG. 9 is a diagram illustrating an example of a determination condition according to the first embodiment. FIG. 10 is a diagram illustrating an example of a determination condition according to the first embodiment. FIG. 11 is a diagram illustrating an example of an effect of the determination device according to the first embodiment. FIG. 12 is a flowchart illustrating an example of a determination processing procedure according to the first embodiment. FIG. 13 is a flowchart illustrating an example of a determination processing procedure according to the first embodiment. FIG. 14 is a diagram illustrating an example of a determination condition according to the first embodiment. FIG. 15 is a diagram illustrating an example of a problem in a general accident notification process. FIG. 16 is a diagram illustrating processing details of a determination device according to a second embodiment. FIG. 17 is a diagram illustrating an example of a block diagram of a determination device according to the second embodiment. FIG. 18 is a diagram showing an example of a setting change screen according to the second embodiment. FIG. 19 is a diagram illustrating an example of a setting change of the impact and sound thresholds according to the second embodiment. FIG. 20 is a diagram illustrating an example of a setting change according to the second embodiment. FIG. 21 is a diagram illustrating an example of a comparison target displayed by the setting change unit according to the second embodiment. FIG. 22 is a flowchart illustrating an example of a processing flow in the determination device according to the second embodiment. FIG. 23 is a diagram illustrating an example of a problem in a general accident notification process. FIG. 24 is a diagram illustrating processing details of the determination device according to the third embodiment. FIG. 25 is a diagram illustrating an example of a block diagram of the determination device according to the third embodiment. FIG. 26 is a diagram illustrating an example of the accuracy determined by the determination unit according to the third embodiment. FIG. 27 is a diagram illustrating an example of a notification executed by the communication processing unit according to the third embodiment. FIG. 28 is a diagram illustrating an example of a notification executed by the communication processing unit according to the third embodiment. FIG. 29 is a diagram illustrating an example of processing by the determination unit according to the third embodiment.Fig. 30 is a flowchart illustrating an example of an accident notification processing procedure according to embodiment 3. Fig. 31 is a flowchart illustrating an example of an accident notification processing procedure according to embodiment 3. Fig. 32 is a diagram illustrating an example of a hardware configuration.

[0008] The following describes in detail embodiments of the notification device, notification method, and notification program disclosed herein with reference to the accompanying drawings. Note that the present invention is not limited to these embodiments. Furthermore, the embodiments can be combined as appropriate within a consistent range.

[0009] <Embodiment 1> (Overall Configuration) A determination device according to embodiment 1 will be described. FIG. 1 is a diagram illustrating an example of the overall configuration of a system according to embodiment 1. As shown in FIG. 1, the system according to embodiment 1 includes a vehicle 20, a determination device 10 mounted on the vehicle 20, and an external server device 7. As shown in FIG. 1, the system detects image data, audio data, and impacts while the vehicle 20 is traveling, and determines whether an accident has occurred based on the detected data. Note that the number of determination devices 10 and vehicles 20 is not limited to that shown in FIG. 1.

[0010] The determination device 10 is a device that determines whether or not the vehicle 20 has been involved in an accident. For example, the determination device 10 is an example of a computer device that determines whether or not an accident has occurred by combining the impact received by the vehicle 20 with audio data within the vehicle 20. For example, the determination device 10 may be a dedicated navigation device that is built into or mounted on the vehicle 20. The determination device 10 may also be configured with a navigation device and a recording device (drive recorder). As one example, the determination device 10 may be a composite device in which a navigation device and a recording device that are independent of each other are connected to each other so that they can communicate with each other. As another example, the determination device 10 may be a single device that has a navigation function and a recording function.

[0011] The determination device 10 may also be configured with a sensor device and a communication device. As an example, the determination device 10 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 determination device 10 may be a single device that has a sensor function and a notification function.

[0012] Furthermore, an occupant of the vehicle 20 can connect a predetermined sensor to a portable terminal device (e.g., a smartphone, a tablet terminal, a notebook PC, a desktop PC, a PDA, or the like) that they use on a daily basis and install a predetermined application, thereby substituting the determination device 10. For example, a portable terminal device that is equipped with a predetermined sensor or to which a predetermined sensor is connected can be considered as the vehicle 20 referred to here. When the portable terminal device is used as the determination device 10, it is installed, for example, on the dashboard of the vehicle 20 while driving.

[0013] When the determination device 10 detects that there is a possibility of an accident, the external server device 7 is notified of an event that an accident has occurred by the determination device 10. For example, when the external server device 7 is notified of an event that an accident has occurred by the determination device 10, the external server device 7 establishes a call between the occupant of the vehicle 20 and a call center so that the occupant of the vehicle 20 can make a call with the call center that is the destination of an emergency call.

[0014] (Problems with General Accident Determination Processing) Here, problems with general accident determination processing (hereinafter, sometimes simply referred to as "accident determination processing") will be described. The accident determination processing executed by a determination device mounted on a general vehicle may not properly detect an accident. For example, when a vehicle receives an impact, if the level of the impact is analyzed to determine whether or not it is an accident, the impact may not be detected as an accident because the level of the impact is low, and instead may be detected as a sudden movement. As a result, although the occupant driving the vehicle recognizes that there is an accident, the accident determination device does not determine that there is an accident, so an accident report is not sent to the external server device 7, and a call to the call center is not made. In addition, there may be cases where an erroneous determination is made that an accident has occurred when no accident has actually occurred.

[0015] This will be explained in detail using Figure 2. Figure 2 is a diagram illustrating the problems with general accident determination processing. Figure 2 shows accident classifications based on the impact level determined by the accident determination processing, and a determination is made as to whether or not an accident has occurred based on the impact level shown in Figure 2.

[0016] For example, in a typical accident determination process, if an impact equal to or greater than a first threshold is detected and a vehicle collides with a wall, it is determined to be a large impact. Furthermore, if an accident determination device detects an impact that is less than the first threshold and equal to or greater than a second threshold and a vehicle collides with another vehicle in a chain reaction accident, it is determined to be a medium or small impact. If the impact is large, medium, or small, it is determined that an accident has occurred, and a report is sent to the external server device 7.

[0017] On the other hand, in a typical accident determination process, when an impact such as sudden steering, sudden braking, or sudden acceleration is detected, which is an impact that is less than the second threshold value, the process determines that the sudden behavior has occurred and does not notify the external server device 7. This is because the accident determination process determines that the sudden behavior is a low-level impact.

[0018] However, as mentioned above, typical accident determination processing only allows two choices: accident or no accident, so even if the vehicle is impacted and the vehicle occupants recognize that an accident has occurred, they may not be able to make an appropriate determination.

[0019] Therefore, as shown in FIG. 1 , the determination device 10 according to the first embodiment analyzes not only the impact that occurred on the vehicle 20 but also the audio data before and after the impact was detected, and thereby appropriately determines that an accident that was erroneously determined to be caused by a sudden movement (such as sudden acceleration, sudden braking, or sudden steering) because the detected impact level was low is an accident based on the volume peak at the time of the sudden movement.

[0020] (Processing Contents of Determination Device 10) Next, processing contents of the determination device 10 according to the first embodiment will be described. The determination device 10 according to the first embodiment detects an impact occurring on the vehicle 20 and a sound inside the vehicle 20, and determines an accident of the vehicle 20 based on the detection results. Then, when the determination device 10 detects an impact less than a second threshold and detects a sudden change in the volume of the sound within a predetermined period including the timing at which the impact is detected, it determines that an accident has occurred.

[0021] Here, a specific example of the processing content of the determination device 10 will be described. Fig. 3 is a diagram illustrating the processing content of the determination device 10 according to the first embodiment. Fig. 3 shows an example of the conditions under which the determination device 10 determines that an accident has occurred.

[0022] For example, when the vehicle 20 receives an impact, the determination device 10 determines whether an accident has occurred by combining data related to the impact and data related to audio inside the vehicle 20. At this time, the determination device 10 determines whether the impact is below a second threshold for determining a sudden movement. Furthermore, the determination device 10 constantly detects audio inside the vehicle, and determines whether there has been a sudden change in volume in particular within a few seconds before and after the timing of the detection of the impact. Then, when the determination device 10 detects both an impact below the second threshold for determining a sudden movement and a sudden change in volume, the determination device 10 determines that the sudden movement is an accident.

[0023] As a result, the determination device 10 can determine that sudden behavior that was determined not to be an accident in the above accident determination process is an accident by performing sound detection in addition to impact detection, so the determination device 10 can make appropriate determinations about accidents.

[0024] (Functional Configuration of Determination Device 10) Next, a functional configuration of the determination device 10 will be described. Fig. 4 is a block diagram showing an example of the functional configuration of the determination device 10 according to embodiment 1. As shown in Fig. 4, the determination device 10 includes a storage unit 11, a determination processing unit 12, a camera 20a, a microphone 20b, an acceleration sensor 20c, a video encoder processing unit 2, an audio encoder processing unit 3, a muxer unit 4, and a sudden behavior detection unit 5.

[0025] The video encoder processing unit 2, the audio encoder processing unit 3, the muxer unit 4, and the sudden behavior detection unit 5 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 processor 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).

[0026] The video encoder processing unit 2 is a processing unit that converts analog image data captured by the camera 20a into a digital signal. The audio encoder processing unit 3 is software that converts the format of an audio file of audio data acquired by the microphone 20b.

[0027] The acceleration sensor 20c measures the acceleration of the vehicle 20. For example, the acceleration sensor 20c measures acceleration along three axes, namely the X-axis, Y-axis, and Z-axis. The acceleration sensor 20c then outputs information about the measured acceleration of the vehicle 20 to the determination processing unit 12. Note that the acceleration information measured here may include the angular velocity of the vehicle 20, and this information is used by the determination processing unit 12 as impact data indicating the impact received by the vehicle 20.

[0028] The muxer 4 combines the imaging data and audio data to output a moving image file 11a. For example, the muxer 4 combines the imaging data output from the video encoder processing unit 2 with the audio data output from the audio encoder processing unit 3, and outputs the moving image file 11a.

[0029] The memory unit 11 stores various programs executed by the judgment processing unit 12, data required when the judgment processing unit 12 performs processing, video files 11a output by the muxer unit 4, and analyzed audio data output by the audio detection unit 12b described later.

[0030] The judgment processing unit 12 has an impact detection unit 12a, a sound detection unit 12b, a calculation unit 12c, a judgment unit 12d, and a short-time Fourier transform unit 13, and judges whether or not an accident has occurred using the impact and sound obtained from the vehicle 20.

[0031] The impact detection unit 12a is an example of a first detection unit that detects an impact occurring to the vehicle 20. For example, the impact detection unit 12a detects an impact occurring to the vehicle 20 using impact data, which is acceleration information output from the acceleration sensor 20c. For example, the impact detection unit 12a 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 20c.

[0032] The classification of accidents based on the value of the resultant vector will be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of the classification of impacts detected by the impact detection unit 12a according to the first embodiment. The impact detection unit 12a detects an impact as a major accident if the value of the resultant vector is higher than a first threshold, and detects an impact as a medium or minor accident if the value of the resultant vector is lower than the first threshold and equal to or higher than a second threshold. Furthermore, the impact detection unit 12a detects an impact as a sudden movement if the impact is equal to or lower than the second threshold.

[0033] The voice detection unit 12b is an example of a second detection unit that detects voice inside the vehicle 20. For example, the voice detection unit 12b constantly detects voice inside the vehicle 20 by using voice data inside the vehicle 20 collected by the microphone 20b and the audio encoder processing unit 3.

[0034] The short-time Fourier transform unit 13 uses the audio data obtained from the audio detector 12 b, the microphone 20 b, and the audio encoder processor 3 to perform a short-time Fourier transform (STFT).

[0035] The short-time Fourier transform unit 13 has a windowing unit 13a and an FFT unit 13b. The windowing unit 13a is a processing unit that multiplies input signal data, which is audio data acquired from the voice detection unit 12b, the microphone 20b, and the audio encoder processing unit 3, by a window function of a specific analysis frame length on the time axis. For example, the windowing unit 13a extracts frames of a specific time length from the input signal input by the vehicle 20 for each frame period and multiplies the extracted frames by a window function, for example, a Hanning window.

[0036] To reduce information loss due to the window function, the windowing unit 13a can overlap the preceding and following analysis frames at any desired rate. For example, by analyzing a fixed length of 512 samples at a fixed frame period of 256 samples, the overlap rate can be set to 50%. The analysis frames obtained in this manner are output to the FFT unit 13b, the calculation unit 12c, and the determination unit 12d.

[0037] The FFT unit 13b is a processing unit that performs FFT (Fast Fourier Transform). For example, the FFT unit 13b applies FFT to the analysis frame that has been windowed by the windowing unit 13a. This converts the input signal of the analysis frame into an amplitude spectrum and a phase spectrum.

[0038] Thereafter, the FFT unit 13b outputs the amplitude spectrum obtained by the FFT to the calculation unit 12c and the determination unit 12d. Note that although an example in which the FFT is applied has been given here, other algorithms such as Fourier transform and discrete Fourier transform may be applied to convert from the time domain to the frequency domain.

[0039] The calculation unit 12c calculates the sum of the amplitudes of all frequency bands of the amplitude spectrum obtained by the short-time Fourier transform unit 13. For example, the calculation unit 12c calculates the sum of the amplitudes of all frequency bands using FFT, and calculates the peak value of the audio data.

[0040] Here, the difference between the sound data after FFT analysis in the normal state and the sound data when a contact sound is generated will be described. Fig. 6 is a diagram showing an example of sound data subjected to FFT analysis according to the first embodiment. In the example of Fig. 6, FFT is performed on the sound data including the contact sound acquired by the microphone 20b, and the amplitude value is shown for each frequency.

[0041] 6, the graph showing the FFT results for normal times when no contact sound is present shows large amplitude values ​​in low frequency bands, indicating that the overall amplitude values ​​are small. On the other hand, the graph showing the FFT results for when contact sound is present also shows large amplitude values ​​in high frequency bands, indicating that the overall amplitude values ​​are large.

[0042] Next, a description will be given of analysis data obtained by calculating the sum of the amplitudes of all frequency bands after performing an FFT on the audio data including the contact sound shown in Fig. 6. Fig. 7 is a diagram showing an example of audio data after FFT analysis used for accident detection according to embodiment 1. The example of Fig. 7 shows a graph in which the sum of the amplitudes of all frequency bands after performing an FFT on the audio data including the contact sound shown in Fig. 7 is calculated for each playback time (seconds).

[0043] In the graph shown in Figure 7, the vertical axis represents the sum of amplitudes (Σ) of all frequency bands, and the horizontal axis represents the playback time (seconds) of the acquired audio data. As shown in Figure 6, the sum of amplitudes Σ exceeds 600 around 9.7 seconds when the contact sound occurred, while the maximum sum of amplitudes at other times remains around 300. In other words, over the playback time of approximately 16 seconds, the audio data around 9.7 seconds when the contact sound occurred due to the accident is detected as a volume peak.

[0044] As a result, the voice detection unit 12b can create analysis data capable of detecting volume peaks from the voice data acquired by the microphone 20b, which is used by the determination unit 12d described later.

[0045] The determination unit 12d determines whether an accident has occurred in the vehicle 20 based on the detection results of the impact detection unit 12a and the sound detection unit 12b. Furthermore, the determination unit 12d determines that the vehicle 20 has exhibited abrupt behavior when it detects sudden deceleration, sudden acceleration, or sudden steering of the vehicle 20. The conditions under which the determination unit 12d determines that an accident has occurred will be described below. When abrupt behavior is detected by the impact detection unit 12a, the determination unit 12d determines that an accident has occurred when conditions 1 to 3 are additionally satisfied for sound.

[0046] Here, when the determination unit 12d detects a sudden movement in which the detected impact is less than a small to medium accident, the determination unit 12d 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.

[0047] (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 approximately 20 seconds, including the time point at which an impact is detected. Fig. 8 is a diagram showing an example of processing details of the determination unit 12d according to the first embodiment. As shown in Fig. 8, the determination unit 12d determines that the volume peak at around 9.7 seconds, which indicates a sound at the time of contact sound, is audio that may be deviating from normal volume and may indicate contact.

[0048] Here, a specific example of the determination made by the determination unit 12d for condition 1 will be described. Fig. 9 is a diagram showing an example of the processing performed by the accident detection unit according to embodiment 1. Fig. 9 shows an example of the case where the sum of the amplitudes of all frequency bands of audio data is calculated at 100 ms intervals by FFT, and a sudden change in volume is detected when the calculated sum of the amplitudes satisfies the following (1) to (4):

[0049] First, the determination unit 12d 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 12d determines whether the following condition is satisfied: "total amplitude value Σ of the target amplitude for 100 ms > average amplitude Σ for the immediately preceding 5 seconds + 3σ." Here, σ represents standard deviation.

[0050] Next, the determination unit 12d performs a gradient determination to determine whether the amplitude of the target is abruptly changing in volume (Condition 1-(2)). Specifically, the determination unit 12d determines whether the following condition is satisfied: "target amplitude 100 msΣ - immediately preceding amplitude 100 msΣ > gradient threshold."

[0051] Next, the determination unit 12d performs a contact volume determination to determine whether the target amplitude is equivalent to the contact volume (Condition 1-(3)). Specifically, the determination unit 12d determines whether the condition "target amplitude 100 msΣ>contact volume threshold" is satisfied.

[0052] Then, the determination unit 12d performs a detection validity determination to determine whether or not the immediately preceding sound field is in a detectable state (Condition 1-(4)). Specifically, the determination unit 12d determines whether or not "amplitude σ for the immediately preceding 5 seconds < detection validity σ threshold" is satisfied.

[0053] 9, the accident detection unit 125 performs the determination of 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 that satisfy all of conditions 1-(1) to 1-(4). That is, the determination unit 12d determines that condition 1 is satisfied. Note that the order in which the determination unit 12d performs the determination of the above-described conditions 1-(1) to 1-(4) is not particularly limited.

[0054] (Explanation of Condition 2) Condition 2 determines whether or not a volume peak that satisfies the above-described Condition 1 exists between 2 seconds before and 1 second after the point in time when a sudden movement is detected. Fig. 10 is a diagram showing an example of the processing content of the determination unit 12d according to the first embodiment. Fig. 10 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.

[0055] As shown in Figure 10, the judgment unit 12d determines that condition 2 is met because a volume peak that satisfies the above-mentioned condition 1 is detected around 9.7 seconds, which is within 2 seconds before the playback time of 10 seconds when the sudden behavior was detected.

[0056] (Explanation of Condition 3) Condition 3 is a condition for determining whether the vehicle 20 has slowed down or stopped within a certain distance from the point where a sudden movement was 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.

[0057] The certain distance can be obtained 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 distance can be used. For example, the distance may be measured based on parameters obtained from a vehicle speed sensor, or based on an odometer value obtained via a CAN (Controller Area Network).

[0058] For example, when the speed of the vehicle 20 becomes equal to or less than a slow speed within a travel distance of 100 meters, which is an example of a certain distance, from the point where the sudden behavior was detected, the determination unit 12d determines that Condition 3 is satisfied. Explaining using the example of Fig. 10 , the determination unit 12d uses the vehicle position at the point of 10 seconds into the playback time when the sudden behavior was detected as a reference, and determines that Condition 3 is satisfied when the speed of the vehicle 20 becomes equal to or less than a threshold value (e.g., 5 km / h) within a certain distance (e.g., 100 m) from the reference, or when the speed of the vehicle 20 becomes 0 m / h.

[0059] 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 12d determines that Condition 3 is satisfied if the vehicle 20 stops within a certain time (e.g., 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 determination device 10 or another on-board device to measure the time from the detection of the sudden movement until the vehicle speed becomes equal to or less than a threshold.

[0060] As described above, when the impact detected by the detection result of the impact detection unit 12a is determined to be a sudden movement that is less than the second threshold, the judgment unit 12d additionally determines whether all of conditions 1 to 3 are met using the analysis data created by the sound detection unit 12b, thereby making it possible to properly judge an accident that was mistakenly determined to be a sudden movement as an accident.

[0061] 11 is a diagram showing an example of the flow of the determination process of the determination device 10 according to embodiment 1. As shown in Fig. 11 , when a sudden movement is determined based on the detection result of the impact detection unit 12a, the determination device 10 can also determine that the sudden movement is an accident by additionally determining whether or not the sound inside the vehicle 20 satisfies all of the above-described conditions 1 to 3.

[0062] <Processing Executed by Determination Device 10> Next, the processing of the determination device 10 according to the first embodiment will be described with reference to Fig. 12 and Fig. 13. Fig. 12 is a flowchart showing the overall flow of the determination processing procedure according to the first embodiment. First, the determination device 10 detects an impact to the vehicle 20 (step S101) and a sound inside the vehicle 20 (step S102).

[0063] Next, the determination device 10 performs an FFT using the detected audio from inside the vehicle 20 (step S103). Next, the determination device 10 calculates the sum of the amplitudes of all frequency bands from the results of the FFT (step S104). Then, the determination device 10 combines the impact result obtained in step S101 with the audio data result obtained in step S104 to determine whether an accident has occurred (step S105).

[0064] 13 is a flowchart showing a detailed flow of the determination process procedure according to the first embodiment. First, the determination device 10 performs FFT to calculate the sum of the amplitudes of all frequency bands of the audio data (step S201). Next, if the amplitude is equal to or greater than a threshold compared to the sound immediately before the vehicle 20 receives an impact (step S202, Yes), the determination device 10 determines whether a sudden volume change has occurred (step S203). On the other hand, if the amplitude is not equal to or greater than the threshold compared to the sound immediately before the vehicle 20 receives an impact (step S202, No), the determination device 10 ends the process.

[0065] Next, if a sudden volume change has occurred (step S203, Yes), the determination device 10 determines whether the amplitude is about the volume that caused the vehicle 20 to come into contact with something (step S204).On the other hand, if a sudden volume change has not occurred (step S203, No), the determination device 10 ends the process.

[0066] Next, if the amplitude is about the same as the volume of sound when the vehicle 20 comes into contact with something (step S204, Yes), the determination device 10 determines whether or not the sound field immediately before the vehicle 20 receives an impact can be detected (step S205). On the other hand, if the amplitude is not about the same as the volume of sound when the vehicle 20 comes into contact with something (step S204, No), the determination device 10 ends the process.

[0067] If the determination device 10 can detect the sound field immediately before the vehicle 20 receives an impact (Yes in step S205), it determines that an accident has occurred (step S206) and ends the process. On the other hand, if the determination device 10 cannot detect the sound field immediately before the vehicle 20 receives an impact (No in step S205), it ends the process.

[0068] <Effects of Embodiment 1> As described above, when the vehicle 20 receives an impact, the determination device 10 makes a determination by combining the impact detected as a sudden movement with the audio of the vehicle 20 before and after the impact, and is therefore able to determine that a sudden movement that would not be determined to be an accident by a general accident determination process is an accident.

[0069] Furthermore, the determination device 10 can determine that an abrupt behavior that satisfies any one of conditions 1 to 3 is an accident. As a result, the determination device 10 can detect all accidents even when an abrupt behavior occurs that is indistinguishable from a simple abrupt behavior such as abrupt steering and an accident due to abrupt behavior.

[0070] Furthermore, the determination device 10 can detect an accident when two or more of the determination conditions from Condition 1 to Condition 3 are satisfied, or detect an accident when all of the conditions are satisfied, allowing the occupant (passenger) to set the desired conditions. As a result, the determination device 10 can provide an appropriate accident detection service according to the occupant's wishes.

[0071] Furthermore, the determination device 10 can detect an accident when all of the conditions 1 to 3 are satisfied, thereby enabling accurate accident detection with reduced false detections. As a result, the determination device 10 can provide a safe and secure car life for the occupants.

[0072] In addition, by determining that sudden movements are also accidents, the determination device 10 can prevent a situation in which the occupants recognize an accident but do not make a call to the call center, resulting in them being unable to receive appropriate service.

[0073] Furthermore, the determination device 10 can provide a device that realizes a determination algorithm through the above-described processing and determines that even sudden movements are accidents, thereby realizing accurate and high-speed determination processing by the determination device 10.

[0074] (Determination by moving average of acceleration) In the above-mentioned first embodiment, an example of detecting sudden behavior using a composite vector of Gx, Gy, and Gz, which are accelerations on the X-axis, Y-axis, and Z-axis, respectively, was described. However, the determination device 10 of the first embodiment can detect in detail what kind of sudden behavior has occurred using a moving average of acceleration.

[0075] For example, the impact detection unit 12a of the determination device 10 detects details of the sudden behavior using a moving average of acceleration in each direction measured by the acceleration sensor 20c mounted on the vehicle 20. FIG. 14 is a diagram illustrating an example of a determination condition according to the first embodiment. As illustrated in FIG. 14 , the impact detection unit 12a determines that the sudden behavior is a sudden deceleration when the moving average of acceleration in the x-axis direction measured by the acceleration sensor 20c mounted on the vehicle 20 is greater than a third threshold. The impact detection unit 12a also detects a sudden acceleration in which the moving average of acceleration in the x-axis direction is less than the third threshold, a sudden right turn in which the moving average of acceleration in the y-axis direction is greater than the third threshold, or a sudden left turn in which the moving average of acceleration in the y-axis direction is greater than the third threshold.

[0076] <Embodiment 2> (Outline of Embodiment 2) Incidentally, in the first embodiment, an example has been described in which the determination device 10 realizes accurate accident determination of sudden movement by determining whether the sound inside the vehicle 20 when a sudden movement is detected satisfies the conditions for an accident. However, the disclosed determination device can also notify the occupants by displaying, on a screen mounted on the vehicle 20, the detection method used to detect the accident when an accident is detected.

[0077] Therefore, in the second embodiment, a determination device 10 will be described as an example of a notification device that, when an accident is detected, presents the detection result and the detection method to an occupant, and allows the occupant to change the setting of the detection method. Note that the system configuration of the second embodiment is the same as that of FIG. 1, and therefore detailed description thereof will be omitted.

[0078] For example, the determination device 10 suppresses the detection of accidents caused by small impacts by a first detection method using "impact only" determined by the resultant vector of acceleration, and performs the detection of accidents caused by large impacts. Furthermore, the determination device 10 can also detect accidents caused by small impacts, such as sudden movements, by a second detection method using both "impact" determined by the resultant vector of acceleration and "audio" determined by the total amplitude of the frequency band (hereinafter, sometimes referred to as "impact + audio"). In this way, the determination device 10 can select a detection method depending on the setting situation, such as using the first detection method when performing broad accident detection and the second detection method when performing strict accident detection.

[0079] Although the determination device 10 can detect accidents involving small impacts by setting a low threshold for the first detection method using "impact only," erroneous detection of an accident may occur depending on the threshold setting. Even in such cases, an accident notification is sent to the external server device 7, which may be annoying to the vehicle occupants.

[0080] This will be explained in detail with reference to Fig. 15. Fig. 15 is a diagram illustrating problems with accident notification. For example, when the accident detection method is set to "impact and sound," the determination device 10 detects a situation in which the sound becomes abnormally loud due to "sudden behavior such as sudden steering, sudden braking, or sudden acceleration" as an accident using the method of embodiment 1, and notifies the external server device 7.

[0081] On the other hand, when the accident detection method is set to "impact only" and a small threshold is set, the determination device 10 not only detects accidents with large impacts but also detects simple sudden movements as small impact accidents and notifies the external server device 7. In other words, an erroneous determination occurs due to an incorrect setting of the threshold. Note that even when the "impact and sound" detection method is used, it is possible that an erroneous setting of the threshold may result in an erroneous detection of sudden movements with small sounds as an accident.

[0082] Therefore, in order to reduce the inconvenience to passengers who receive accident alerts every time an accident is falsely detected due to a small impact or a strict accident detection due to sudden movement, the determination device 10 displays a setting screen for information related to accident detection, allowing passengers to change the detection method and threshold value.

[0083] (Processing Contents of Determination Device 10) Next, processing contents of the determination device 10 according to the second embodiment will be described. Specifically, the determination device 10 according to the second embodiment detects an accident of the vehicle 20 using a first detection method using an impact occurring on the vehicle 20 or a second detection method using an impact and sound inside the vehicle 20. The determination device 10 displays a notification screen including the accident detection result by the detection unit and information indicating whether the detected accident was detected by the first detection method or the second detection method. Then, the determination device 10 accepts a change in the setting of the accident detection method on the displayed notification screen.

[0084] In other words, when an accident occurs, the judgment device 10 displays an alert screen on a screen installed in the vehicle 20 or on a screen such as a smartphone held by the occupant, which screen accepts changes to the accident detection method and threshold for accident detection, accepts the detection level desired by the occupant from the occupant, and detects the accident at the detection level desired by the occupant.

[0085] 16 is a diagram illustrating a notification screen and a setting change. Here, "changing the detection method" is explained as an example, and "changing the threshold" will be described later.

[0086] 16 , for example, when the determination device 10 detects an accident in a situation where the detection method is set to “impact only,” the determination device 10 displays a notification screen such as “Detection method: Impact only. Do you want to change the setting?” Then, when the “Yes” button requesting a setting change is selected, the determination device 10 changes the accident detection method to “impact + sound.”

[0087] Similarly, when the determination device 10 detects an accident in a situation where the detection method is set to "impact + sound," it displays a notification screen such as "Detection method: impact + sound. Do you want to change the setting?" Then, when the "Yes" button requesting a setting change is selected, the determination device 10 changes the accident detection method to "impact only."

[0088] This allows the determination device 10 to accept the occupant's selection of a detection method or change of settings, and allows appropriate accident detection for each occupant, thereby reducing the inconvenience to the occupant.

[0089] (Functional Configuration of Determination Device 10) Next, the configuration functions of the determination device 10 according to the second embodiment will be described. FIG. 17 is a block diagram showing an example of the functional configuration of the determination device 10 according to the second embodiment. As shown in FIG. 17, the determination device 10 according to the second embodiment has the same configuration as the storage unit 11, determination processing unit 12, short-time Fourier transform unit 13, camera 20a, microphone 20b, acceleration sensor 20c, video encoder processing unit 2, audio encoder processing unit 3, and muxer unit 4 described in FIG. 4, and therefore detailed description thereof will be omitted. Here, the determination unit 12d, notification unit 12e, and setting change unit 12f of the determination processing unit 12, which have configurations different from those of the first embodiment, will be described.

[0090] The determination unit 12d performs accident detection using a first detection method that uses only impact or a second detection method that uses impact and sound. For example, when the determination unit 12d uses the first detection method, it detects an accident when it detects an impact equal to or greater than a threshold. When the determination unit 12d uses the second detection method, it detects an accident by the determination process described in the first embodiment.

[0091] The notification unit 12e outputs a notification screen including the accident detection results by the impact detection unit 12a and the sound detection unit 12b and information indicating the detection results of the detected accident to the screen of a terminal device or the like mounted on the vehicle 20. For example, the notification unit 12e outputs a notification screen including, in addition to the detection results, the detection method used to detect the accident "a detection method that combines impact and sound sensitivity (threshold), or a detection method that uses only impact sensitivity (threshold)."

[0092] The setting change unit 12f accepts changes to the setting of the accident detection method and the threshold value used for accident detection on the notification screen output by the notification unit 12e. Then, the setting change unit 12f instructs the determination unit 12d to change the method and the threshold value used for accident detection. As a result, the determination unit 12d executes the accident detection process after changing the detection method and the threshold value.

[0093] <Specific Example> Here, details of the notification screen output by the determination device 10 will be described. FIG. 18 is an example of a notification screen for the accident detection method. As shown in FIG. 18 , when an accident is detected in a situation where the detection method is set to "impact only," the notification unit 12e displays a notification screen including the questions "Detection method: Impact only. Would you like to change the setting?" and "Do you want to change the impact threshold?" Here, when the "Yes" button requesting a setting change is selected, the setting change unit 12f changes the accident detection method to "impact + sound." When the "No" button for setting change is selected, the setting change unit 12f does not change the detection method. Furthermore, when the "Yes" button requesting a setting change for the "impact threshold" is selected, the setting change unit 12f displays a screen for changing the impact threshold set at the time of the accident. When the "No" button for setting change is selected, the threshold is not changed.

[0094] Similarly, when an accident is detected in a situation where "impact and sound" is set as the detection method, the notification unit 12e displays a notification screen including the following questions: "Detection method: Impact + sound only. Do you want to change the setting?" and "Do you want to change the impact and sound thresholds?" Here, when the "Yes" button requesting a setting change is selected, the setting change unit 12f changes the accident detection method to "impact only." When the "No" button for setting change is selected, the setting change unit 12f does not change the detection method. Furthermore, when the "Yes" button requesting a setting change for the "impact and sound thresholds" is selected, the setting change unit 12f displays a screen for changing the thresholds set when an accident occurs. When the "No" button for setting change is selected, the setting change unit 12f does not change the thresholds.

[0095] Next, the details of the threshold change described in Fig. 18 will be explained. Fig. 19 shows an example of a screen for accepting a change in threshold setting. Here, the change in the threshold for impact (e.g., a resultant vector of acceleration data) used for accident detection will be explained as an example, but the change in the threshold for sound (e.g., the total amplitude of a frequency band) used for accident detection can also be processed in a similar manner.

[0096] 19, for example, if the occupant finds it annoying that sudden starts and stops are sometimes determined to be minor accidents by the first detection method of "impact only," the occupant sets the threshold to be higher. In this case, the setting change unit 12f displays a screen in which the vertical axis represents the threshold "impact sensitivity" and the horizontal axis represents the threshold before the change (before setting), and accepts an operation to move the horizontal axis up, thereby setting a higher threshold.

[0097] On the other hand, if the occupant is concerned about the accuracy of accident detection because the sudden impact is not determined to be an accident by the first detection method of "impact only," the threshold value is set to a lower value. In this case, the setting change unit 12f can set a lower threshold value by displaying the above screen and accepting an operation to move the horizontal axis downward.

[0098] Here, assumed situations in which the threshold value is changed will be described. Fig. 20 is a diagram illustrating an example of threshold value changes on expressways and general roads.

[0099] As shown in Figure 20, expressways tend to have more vehicles 20 traveling at high speeds than ordinary roads, and are therefore congested, resulting in louder sounds outside the vehicles 20 and a higher frequency of accident detection. In such cases, setting a higher threshold value can prevent unnecessary accident detection. On the other hand, ordinary roads tend to have fewer vehicles 20 traveling at high speeds and are not congested, resulting in quieter sounds outside the vehicles 20 and a lower frequency of accident detection. In such cases, setting a lower threshold value can detect accidents caused by small impacts or sounds.

[0100] In this way, by accepting changes to the threshold on a visually easy-to-understand screen, the determination device 10 can reduce occupant anxiety regarding changes to the threshold settings and questions such as how to set a new threshold.

[0101] Furthermore, the setting change unit 12f can assist the occupant in changing the setting by displaying a notification screen that further associates the magnitude of the impact or the volume of the sound when an accident involving the vehicle 20 is detected with the currently set impact threshold or sound threshold used to detect the accident involving the vehicle 20. Using the example of FIG. 19 , the setting change unit 12f displays the numerical value when an accident is detected on the vertical axis (impact sensitivity). Then, when the horizontal axis (impact threshold) is moved up or down, the setting change unit 12f displays the numerical value representing the impact sensitivity in accordance with the movement. This allows the occupant to visually set the threshold.

[0102] As another example, the setting change unit 12f can simultaneously display the currently set impact and sound thresholds and other thresholds to be compared with each other. Fig. 21 is a diagram illustrating threshold change with the comparison target displayed.

[0103] As shown in FIG. 21 , when a request to "change threshold settings" is made on the accident notification screen, the setting change unit 12f displays the currently set threshold and a threshold to be compared on the same screen. This helps the occupant change the setting of the sensitivity (threshold) of the detection method. The comparison target may be, for example, an average threshold of users who use the same vehicle as the vehicle 20, or an average threshold by region or road. These are merely examples and are not limiting.

[0104] <Processing flow of the determination device 10> Next, an example of a processing procedure by the determination device 10 according to the second embodiment will be described. Fig. 22 is a flowchart showing an example of the processing flow in the determination device 10 according to the second embodiment. However, since the contents up to step S105 in Fig. 22 are the same as those described in the first embodiment, detailed description thereof will be omitted.

[0105] 22 , when the determination device 10 detects that an accident has occurred, it displays on the notification screen what detection method was used to detect the accident (step S106). Then, when the notification ends, the determination device 10 accepts a setting change to the threshold value (sensitivity) of the occupant (step S107), and ends the process.

[0106] Effect of Second Embodiment When an accident occurs, the determination device 10 displays to the occupant what detection method was used to detect the accident and accepts an operation to change the setting of the detection method. As a result, the determination device 10 can reduce notifications due to erroneous determinations by changing the setting, and can reduce the inconvenience to the occupant of having to notify the call center every time an erroneous determination is made.

[0107] In addition, the determination device 10 displays the currently set impact and sound thresholds on the screen and accepts an operation to change the threshold settings, thereby enabling the detection method to be set to suit the occupant.

[0108] In addition, the determination device 10 simultaneously displays the comparison target on the setting change screen, allowing the threshold value change to be accepted on a visually easy-to-understand screen, thereby reducing occupant anxiety regarding threshold value setting changes and questions such as how to set a new threshold value.

[0109] In addition, the determination device 10 accepts setting changes made by the occupant, allowing the occupant to change settings that may cause false detections, thereby reducing false detections and alerts based on false detections and reducing inconvenience to the occupant.

[0110] <Embodiment 3> (Outline of Embodiment 3) Incidentally, in Embodiments 1 and 2, an example has been described in which an accident notification is always sent to the external server device 7 when an accident is detected, but the present invention is not limited to this. For example, the determination device 10 can determine the accident level by dividing it into stages and change the method of notifying the external server device 7 depending on the determined accident level. Therefore, in Embodiment 3, a description will be given of the determination device 10, which is an example of an accident notification device that classifies the accident level and selects the notification method. Note that detailed description of the system configuration of Embodiment 3 that is similar to that of Embodiments 1 and 2 will be omitted.

[0111] Here, improvements to the continuous accident notification will be described. Fig. 23 is a diagram for explaining improvements to the continuous accident notification. Fig. 23 explains an example of the determination device 10 that is set to detect both "impact and sound" and is set to issue an accident notification (alert) every time an accident occurs.

[0112] 23 , for example, when the determination device 10 detects an accident such as the above-mentioned large impact, medium impact, or small impact, it notifies the external server device 7 of the accident. In such a determination device 10, if an attempt is made to reduce notifications due to erroneous detection, the threshold value or the like would have to be changed, which would make it difficult to detect accidents with small impacts such as slipping.

[0113] On the other hand, if the determination device 10 attempts to notify of accidents involving small impacts, the number of false positives may increase. In other words, the occupant must cancel the notification each time, which can be inconvenient.

[0114] Therefore, in the determination device 10 according to the third embodiment, when an accident is detected in the vehicle 20, the determination device 10 determines whether or not the criteria are met, and automatically issues an alert if the impact is large, and allows the occupant to operate whether or not to issue an alert if the impact is small, and issues an alert if the occupant operates the device, or ends the detection without issuing an alert if the occupant does not operate the device. In this way, the determination device 10 provides an appropriate alert while reducing the operational burden on the user in response to false detections that occur when even relatively small impacts are detected in order to prevent accidents from being overlooked.

[0115] (Processing Contents of Determination Device 10) Next, a description will be given of processing contents of the determination device 10 according to embodiment 3. The determination device 10 according to embodiment 3 determines the accuracy of accident detection based on the output of a sensor mounted on the vehicle 20, selects a reporting mode according to the accuracy, and executes reporting processing in the selected mode.

[0116] Here, a specific example of the processing content of the determination device 10 will be described. Fig. 24 is a diagram illustrating a method for determining whether or not an accident notification is necessary according to embodiment 3. Fig. 24 shows an example of classification of accidents according to the impact level executed by the determination device 10 and a notification method.

[0117] For example, when the determination device 10 determines that the vehicle 20 has caused an accident, it classifies the accident according to the level of the impact. As shown in Fig. 24, for example, when the determination device 10 detects an impact equal to or greater than a first standard but less than a second standard, it determines the accident as a sudden movement, when the determination device 10 detects an impact equal to or greater than a second standard but less than a third standard, it determines the accident as a medium impact or a small impact, and when the determination device 10 detects an impact equal to or greater than the third standard, it determines the accident as a large impact. Furthermore, when the determination device 10 detects an impact less than the first standard, it determines the accident as a small impact.

[0118] Next, the determination device 10 selects a notification method using the classification of the accident according to the above-mentioned first to third criteria. For example, when the determination device 10 determines that the vehicle 20 has made a sudden movement based on the detection of an impact and sound, it selects the first notification mode and manually issues a notification to the external server device 7. Manual notification is a method in which the occupant can select whether or not to report the occurrence of an accident to a call center.

[0119] Furthermore, when the determination device 10 detects a medium or small impact, it selects the second notification mode, automatically notifies the external server device 7, and accepts cancellation of the notification by the occupant. Furthermore, when the determination device 10 detects a large impact, it selects the third notification mode, and automatically notifies the external server device 7.

[0120] As a result, when the determination device 10 determines that the vehicle 20 has had an accident, it classifies the accident according to the level of impact and selects an alarm method appropriate for the classified accident, thereby preventing alarms from being issued due to erroneous determination and reducing the burden on the occupants of having to cancel the alarm.

[0121] (Functional Configuration of Determination Device 10) Next, a description will be given of the functional configuration of the determination device 10. The determination device 10 according to the third embodiment determines the accuracy of accident detection based on the output of a sensor mounted on the vehicle 20, selects a reporting mode according to the accuracy, and executes reporting processing in the selected mode.

[0122] 25 is a diagram showing an example of a block diagram of the determination device 10 according to embodiment 3. The determination device 10 according to embodiment 3 has the same configurations as the storage unit 11, determination processing unit 12, short-time Fourier transform unit 13, camera 20a, microphone 20b, acceleration sensor 20c, video encoder processing unit 2, audio encoder processing unit 3, Muxer unit 4, and sudden behavior detection unit 5 described in FIGS. 4 and 17 , and therefore detailed description thereof will be omitted. Here, the determination unit 12d, selection unit 12g, and communication processing unit 12h of the determination processing unit 12, which have configurations different from those of embodiment 1 and embodiment 2, will be described.

[0123] The determination unit 12d determines the accuracy of accident detection based on the output of the acceleration sensor 20c mounted on the vehicle 20. For example, the determination unit 12d determines the accuracy of accident using a resultant vector of accelerations measured by the acceleration sensor 20c.

[0124] The selection unit 12g selects a reporting mode depending on the accuracy determined by the determination unit 12d. The reporting mode selected by the selection unit 12g will now be described with reference to FIG. 26 . FIG. 26 is a diagram illustrating an example of the accuracy determined by the determination unit 12d according to the third embodiment. As shown in FIG. 26 , when the accuracy is equal to or greater than a first standard and less than a second standard, the selection unit 12g determines that the vehicle is moving suddenly, and selects the (1) first reporting mode. For example, the (1) first reporting mode involves manually issuing a report to the external server device 7.

[0125] Furthermore, when the accuracy is equal to or greater than the second standard and less than the third standard, the determining unit 12d determines that the impact is a medium or small impact, and the selecting unit 12g selects the (2) second notification mode. For example, the (2) second notification mode automatically issues a notification to the external server device 7, and if the notification is incorrect, a cancellation notification is accepted.

[0126] Furthermore, when the accuracy is equal to or greater than a third standard, the determination unit 12d determines that the impact is a large impact, and the selection unit 12g selects the third notification mode (3). For example, the third notification mode (3) automatically issues a notification to the external server device 7. Furthermore, when the accuracy is less than the first standard, the determination unit 12d determines that the impact is a small impact, and the selection unit 12g selects the fourth notification mode (4). For example, the fourth notification mode (4) does not issue a notification to the external server device 7.

[0127] When a third criterion, which is more accurate than the second criterion, is satisfied, the selection unit 12g selects a third notification mode in which a notification is made without accepting a cancellation operation by the occupant. In other words, when the (3) third notification mode is selected, an operation by the occupant to cancel the issuance of a notification to the external server device 7 is not accepted. This is because the (3) third notification mode is classified as a major accident, and the necessity of issuing a notification to the external server device 7 is higher than in the (1) first notification mode or the (2) second notification mode.

[0128] The communication processing unit 12h executes the notification process in the mode selected by the selection unit 12g. Here, a selection screen for notification will be described with reference to Fig. 27 . Fig. 27 is an example of the selection screen for notification according to the third embodiment. For example, when (1) the first notification mode or (2) the second notification mode is selected by the selection unit 12g, the communication processing unit 12h displays a screen that prompts the occupant to select whether or not to issue a notification to make a call to a call center.

[0129] Next, detailed processing when the first notification mode is selected will be described. Fig. 28 is a diagram showing detailed processing when the first notification mode according to embodiment 3 is selected. When the selection unit 12g selects (1) the first notification mode, the communication processing unit 12h presents information prompting the occupant to perform a notification operation, and then, if the occupant does not perform the notification operation within a predetermined time, stops presenting the information prompting the occupant to perform the notification operation.

[0130] That is, when the selection unit 12g selects (1) the first notification mode, if the occupant has not issued an alert to the external server device 7 within a certain time period, the communication processing unit 12h stops displaying the screen prompting the occupant to issue a manual alert. As a result, even if the determination device 10 recognizes that the occupant has not had an accident and the first notification mode is selected and a screen prompting the occupant to issue a manual alert is displayed, an alert will not be issued to the external server device 7 unless the occupant operates to issue an alert, which eliminates the need for the occupant to cancel the alert and reduces the burden on the occupant.

[0131] Furthermore, the communication processing unit 12h accepts an operation to cancel the issuance of the alert when the selection unit 12g selects (2) the second notification mode but the occupant recognizes that there is no accident, or when an impact has occurred but the occupant is not in a state to call the call center. This allows the determination device 10 to reduce erroneous determinations and eliminates the burden on the occupant by eliminating the need to cancel the issuance of the alert every time an erroneous determination occurs.

[0132] (Determination Based on Acceleration) The determination unit 12d can also determine the accuracy using impact data obtained from the acceleration sensor 20c. Fig. 29 is a diagram showing an example of the accuracy determined by the determination unit 12d according to the third embodiment using data obtained from the acceleration sensor 20c. For example, the determination unit 12d determines that the accuracy satisfies the first criterion when the output of the acceleration sensor 20c exceeds the first impact threshold and, at the same time, the output of the microphone 20b exceeds the first sound threshold. In other words, the determination unit 12d determines that the accuracy satisfies the first criterion when the conditions (1) of the impact being equal to or greater than the first impact threshold and less than the second impact threshold and (2) of the sound being equal to or greater than the first sound threshold are simultaneously satisfied.

[0133] Furthermore, the determination unit 12d determines that the accuracy satisfies the second criterion when the output of the acceleration sensor 20c exceeds a second impact threshold that is greater than the first impact threshold. That is, the determination unit 12d determines that the accuracy satisfies the second criterion when the condition (3) is satisfied, which is the threshold of the impact that is equal to or greater than the second criterion.

[0134] <Processing flow of determination device 10> Next, an example of the processing procedure of the determination device 10 according to embodiment 3 will be described with reference to Fig. 30 and Fig. 31. Fig. 30 is a flowchart showing an example of the accident notification processing procedure according to embodiment 3. However, since the contents up to step S104 in Fig. 30 are the same as those described in embodiments 1 and 2, detailed description thereof will be omitted.

[0135] 30 , the determination device 10 determines the accuracy of accident detection by combining the impact and the sound inside the vehicle 20 (step S105). Then, the determination device 10 selects a notification mode according to the determined accuracy (step S106), and executes notification processing to the external server device 7 in the selected notification mode (step S107). Note that the selection of the notification mode will be described in detail later.

[0136] 31 is a flowchart showing an example of an accident reporting process procedure according to embodiment 3. As shown in FIG. 31 , when the accuracy is higher than the first criterion (step S201, Yes), the determination device 10 determines whether the accuracy is higher than the second criterion (step S203). On the other hand, when the accuracy is lower than the first criterion (step S201, No), the determination device 10 determines that the impact is a minor impact and does not issue an alert (step S202).

[0137] Next, if the accuracy is higher than the second criterion (step S203, Yes), the determination device 10 determines whether the accuracy is higher than the third criterion (step S205). On the other hand, if the accuracy is lower than the second criterion (step S203, No), the determination device 10 determines that the vehicle is moving suddenly and issues a manual alert (step S204).

[0138] Next, if the accuracy is higher than the third standard (step S205, Yes), the determination device 10 determines that the impact is a large impact and automatically issues a report (step S206).On the other hand, if the accuracy is lower than the third standard (step S205, No), the determination device 10 determines that the impact is a medium or small impact and accepts automatic reporting or cancellation of reporting (step S207).

[0139] <Effects of Embodiment 3> In Embodiment 3, when it is detected that the vehicle 20 has been involved in an accident, the accuracy of the accident detection is determined, and the method of issuing an alert is changed according to the determined accuracy: automatic alert for a large impact, automatic alert and cancellation of alert for a medium or small impact, and manual alert for a sudden movement. As a result, even if a false detection occurs due to the setting of the detection method, the determination device 10 can issue an appropriate alert while reducing the operational burden on the occupant.

[0140] In addition, when a sudden movement is detected, the judgment device 10 manually issues an alert to the external server device 7, so that the alert is only issued when an operation to issue the alert is performed, and by automatically ceasing to issue the alert after a certain period of time has elapsed, false detections can be prevented and the burden on occupants can be reduced.

[0141] In addition, the determination device 10 automatically issues an alert to the external server device 7 when a major impact is detected, and does not accept cancellation of the alert from the occupant, thereby enabling a rapid response to major accidents.

[0142] In addition, the determination device 10 automatically issues an alert to the external server device 7 when a medium or small impact is detected, and by accepting cancellation of the alert from the occupant, it is possible to cancel the alert if the occupant does not recognize it as an accident but the device determines that it is an accident.

[0143] Fourth Embodiment Although the embodiments of the present invention have been described above, the present invention may be embodied in various different forms other than the above-described embodiments.

[0144] (Numeric Values, etc.) The numerical values, graphs, threshold values ​​(for example, arbitrary numerical values), etc. used in the above embodiments are merely examples and can be changed as desired. Furthermore, 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 in decibels (db). Note that each embodiment can be applied to various vehicles, such as private cars, taxis, buses, electric vehicles, hybrid vehicles, motorcycles, and three-wheeled vehicles.

[0145] <Hardware> The determination device 100 according to the first, second, and third embodiments described above is realized, for example, by a computer 1000 configured as shown in Fig. 32. The following description will be given taking the determination device 100 as an example. Fig. 32 is a hardware configuration diagram showing an example of a computer that realizes the functions of the determination device according to the first, second, third, and fourth embodiments. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0146] 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.

[0147] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0148] 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.

[0149] 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.

[0150] For example, when the computer 1000 functions as the determination device 100 according to the first, second, third, and fourth embodiments, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to implement the functions of the determination processing unit 12, the video encoder processing unit 2, the audio encoder processing unit 3, and the muxer unit 4. 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 acquire these programs from another device via a predetermined communication network.

[0151] <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 a known method. 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.

[0152] 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.

[0153] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0154] 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 embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0155] 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.

[0156] 2 Video encoder processing unit 3 Audio encoder processing unit 4 Muxer unit 7 External server device 10 Determination device 11 Storage unit 11a Video file 12 Determination processing unit 12a Impact detection unit 12b Sound detection unit 12c Calculation unit 12d Determination unit 12e Notification unit 12f Setting change unit 12g Selection unit 12h Communication processing unit 13 Short-time Fourier transform unit 13a Windowing unit 13b FFT unit 20a Camera 20b Microphone 20c Acceleration sensor

Claims

1. A determination device mounted on a vehicle, comprising: a first detection unit that detects an impact occurring to the vehicle; a second detection unit that detects sound inside the vehicle; and a determination unit that determines an accident involving the vehicle based on the detection results of the first detection unit and the second detection unit, wherein the determination unit determines that an accident has occurred when the first detection unit detects an impact of a predetermined value or greater and the second detection unit detects a sudden change in the volume of the sound within a predetermined period of time that includes the time when the impact was detected.

2. The determination device described in claim 1, characterized in that the determination unit determines that an accident has occurred when the first detection unit detects an impact equal to or greater than the predetermined value, which is less than a second threshold at which it is determined that the vehicle has had an accident and is greater than or equal to a first threshold at which it is determined that the vehicle has made a sudden movement, and when the second detection unit detects a sudden change in the volume of the audio within a predetermined period including the time at which the impact was detected.

3. The determination device according to claim 2, characterized in that the determination unit determines that the vehicle has made an abrupt move when it detects sudden deceleration, sudden acceleration or sudden steering of the vehicle.

4. The determination device described in claim 3, characterized in that the first detection unit detects, as an impact of greater than the predetermined value, a sudden deceleration in which the moving average of acceleration in the x-axis direction measured by an acceleration sensor attached to the vehicle is greater than a third threshold value, a sudden acceleration in which the moving average of acceleration in the x-axis direction is less than the third threshold value, a sudden right turn in which the moving average of acceleration in the y-axis direction is greater than the third threshold value, or a sudden left turn in which the moving average of acceleration in the y-axis direction is greater than the third threshold value.

5. The determination device described in claim 1, characterized in that the second detection unit performs a short-term Fourier transform on the audio inside the vehicle to calculate the amplitude for each predetermined time period, and the determination unit determines that an accident has occurred when an impact equal to or greater than the predetermined value is detected and the latest amplitude is equal to or greater than a threshold value obtained by using the average value of each amplitude from the predetermined time period before the latest amplitude.

6. The determination device described in claim 1, characterized in that the second detection unit performs a short-term Fourier transform on the audio inside the vehicle to calculate the amplitude at each predetermined time, and the determination unit determines that an accident has occurred when an impact equal to or greater than the predetermined value is detected and the difference between the latest amplitude and the amplitude immediately before the latest amplitude is equal to or greater than a threshold value.

7. The determination device described in claim 1, characterized in that the second detection unit performs a short-term Fourier transform on the audio inside the vehicle to calculate the amplitude at each predetermined time, and the determination unit determines that an accident has occurred if an impact equal to or greater than the predetermined value is detected and the latest amplitude is equal to or greater than a threshold value.

8. The determination device described in claim 1, characterized in that the second detection unit performs a short-term Fourier transform on the audio inside the vehicle to calculate the amplitude for each predetermined time period, and the determination unit, when an impact equal to or greater than the predetermined value is detected, suppresses the determination of an accident if the standard deviation of each amplitude within the predetermined time period, including the most recent amplitude, is equal to or greater than a threshold value.

9. A determination method to be installed in a vehicle, comprising: a first detection process for detecting an impact occurring to the vehicle; a second detection process for detecting sound inside the vehicle; and a determination process for determining an accident involving the vehicle based on the detection results of the first and second detection processes, wherein the determination process determines that an accident has occurred when the first detection process detects an impact of a predetermined value or greater and the second detection process detects a sudden change in the volume of the sound within a predetermined period including the time when the impact was detected.

10. A judgment program to be installed in a vehicle, comprising: a first detection step of detecting an impact occurring to the vehicle; a second detection step of detecting sound inside the vehicle; and a judgment step of judging an accident involving the vehicle based on the detection results of the first and second detection steps, wherein the judgment step judges that an accident has occurred when the first detection step detects an impact of a predetermined value or greater and the second detection step detects a sudden change in the volume of the sound within a predetermined period including the time when the impact was detected.

Images