Detection function control device, detection function control method, and computer-readable recording medium

Abstract

The detection function control device includes a vehicle condition determination section that determines a condition of the vehicle based on a result of detection of any one or more of an ignition state, whether or not a seat is occupied, an acceleration of the vehicle, a position of the vehicle, a speed of the vehicle, and a sound collected, and a detection function control section that determines whether or not to operate any one of one or more detection functions for detecting dangerous driving based on the condition determined by the vehicle condition determination section.

Description

Technical Field

[0001] This invention relates to a detection function control device, a detection function control method, and a computer-readable recording medium. Background Technology

[0002] Technologies that integrate AI (Artificial Intelligence) functions on small terminals to perform functions such as facial recognition and sleep detection are known. For example, there are known devices that detect sleep without a camera (Patent Document 1).

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2010-250577 Summary of the Invention

[0006] AI functions need to execute different inference models depending on their purpose. Executing these inference models requires significant computing resources (CPU resources or dedicated circuit resources). Therefore, there is a limit to the number of inference models that can be executed simultaneously on a small terminal.

[0007] In recent years, some high-performance dashcams have incorporated a Driver Monitoring System (DMS). This DMS includes features such as detecting driver facial recognition, distraction, drowsiness, and phone activity, and issuing warnings for dangerous driving. However, small devices typically lack the computational power to perform all these functions. Therefore, it is difficult to install DMS-like functionality on a small device.

[0008] The required computing power is sufficient to run more detection functions.

[0009] This embodiment was made in view of the above aspects, and provides a detection function control device, a detection function control method, and a computer-readable recording medium capable of running more detection functions with the available computing power.

[0010] This embodiment was made to solve the above-mentioned problems. One aspect of this embodiment is a detection function control device, including: a vehicle condition determination unit that determines the condition of the vehicle based on one or more detection results of ignition state, whether the driver is seated, vehicle acceleration, vehicle position, vehicle speed, and collected sound; and a detection function control unit that determines whether to operate one or more detection functions for detecting dangerous driving based on the condition determined by the vehicle condition determination unit.

[0011] In another embodiment, in the detection function control device described above, when the vehicle condition determination unit determines that the changes in the acceleration, the position, and the speed are all less than a specified amount, and the vehicle condition determination unit determines that the ignition has been turned on within a specified time, or when the vehicle condition determination unit determines that the seating state has changed, the detection function control unit operates the facial authentication function.

[0012] In another embodiment, in the detection function control device described above, when the vehicle condition determination unit determines that the change in any one or more of the acceleration, position, and speed is greater than a predetermined value, the detection function control unit operates a function for determining distracted driving.

[0013] In another embodiment, in the detection function control device described above, when the vehicle condition determination unit determines that the driver is speaking, the detection function control unit operates an image recognition function for determining the call action.

[0014] In another embodiment, in the detection function control device described above, when the vehicle condition determination unit determines that the driver is silent, the detection function control unit operates an image recognition function for determining drowsy driving.

[0015] Another embodiment of this invention is a detection function control method, comprising: a vehicle condition determination step, which determines the condition of the vehicle based on one or more detection results of ignition state, whether the driver is seated, vehicle acceleration, vehicle position, vehicle speed, and collected sound; and a detection function control step, which determines whether to operate one or more detection functions for detecting dangerous driving based on the condition determined by the vehicle condition determination step.

[0016] Alternatively, one embodiment of this invention is a computer-readable recording medium containing a program that causes a computer to execute: a vehicle condition determination step, which determines the condition of the vehicle based on one or more detection results of ignition status, whether the driver is seated, vehicle acceleration, vehicle position, vehicle speed, and collected sound; and a detection function control step, which determines whether to operate one or more detection functions for detecting dangerous driving based on the condition determined by the vehicle condition determination step.

[0017] According to this implementation, more detection functions can be run with the available computing power. Attached Figure Description

[0018] Figure 1This is a diagram illustrating an example of the hardware structure of the dashcam according to this embodiment.

[0019] Figure 2 This is a diagram illustrating an example of the functional structure of the dashcam according to this embodiment.

[0020] Figure 3 This is a diagram illustrating an example of the relationship between vehicle conditions and whether multiple detection functions are running, as described in this embodiment.

[0021] Figure 4 This is a diagram illustrating an example of the detection function control process involved in this embodiment.

[0022] Figure 5 This is a diagram illustrating an example of the detection function control process involved in this embodiment. Detailed Implementation

[0023] (Implementation Method)

[0024] Hereinafter, this embodiment will be described in detail with reference to the accompanying drawings. In this embodiment, as an example, we will describe a case where the dashcam 1 is equipped with AI that detects multiple items such as facial recognition, distraction, drowsiness, and phone calls of the driver. The dashcam 1 is mounted on a vehicle 3 (not shown) driven by a driver 2 (not shown). The dashcam 1 is mainly installed, for example, on the dashboard or windshield of the vehicle 3 (not shown).

[0025] [Structure of a dashcam]

[0026] Figure 1 This diagram illustrates an example of the hardware structure of the dashcam 1 according to this embodiment. The dashcam 1 includes an accelerometer 10, a gyroscope 11, a GPS receiver 12, a vehicle signal cable 13, a camera 14, a speaker 15, a display 16, operation buttons 17, a microphone 18, a timer 19, a CPU 110, a ROM 111, a RAM 112, and a communication module 113. The accelerometer 10, gyroscope 11, GPS receiver 12, vehicle signal cable 13, camera 14, speaker 15, display 16, operation buttons 17, microphone 18, timer 19, CPU 110, ROM 111, RAM 112, and communication module 113 are connected to each other via signal lines.

[0027] Accelerometer 10 measures the acceleration of vehicle 3.

[0028] The gyroscope sensor 11 measures the angular velocity of the vehicle 3.

[0029] GPS receiver 12 uses GPS (Global Positioning System) to obtain information indicating the current location of vehicle 3.

[0030] Vehicle signal cable 13 receives vehicle signals from vehicle 3. Vehicle signals are signals indicating the status of vehicle 3. Vehicle signal cable 13 receives various vehicle signals from the ECU (Electronic Control Unit) of vehicle 3. These various vehicle signals include, for example, ignition switch signals, vehicle speed signals, signals indicating the steering angle of vehicle 3, and signals indicating the pressure value applied to the seat of vehicle 3.

[0031] Camera 14 includes a first camera and a second camera. The first camera captures part or all of the driver 2's body. The second camera captures and records images of the vehicle 3 in motion.

[0032] Speaker 15 outputs a sound-based warning tone.

[0033] The display 16 displays various images. The display 16 is, for example, a liquid crystal display or an organic electroluminescence (EL) display.

[0034] Operation button 17 is a button used by the user to operate the dashcam 1.

[0035] Alternatively, the display 16 can also be a touch panel, in which case the operation buttons 17 can be integrated with the display 16. Or, they can be integrated with the display 16 as part of the operation buttons 17.

[0036] Microphone 18 captures sound. This sound includes the voice of driver 2 speaking.

[0037] Timer 19 starts timing.

[0038] CPU 110 reads the program from ROM 111 and executes various controls according to the read program. CPU 110 has multiple internal storage media such as registers. CPU 110 temporarily stores data from ROM 111 to the internal storage media and performs calculations on it. CPU 110 outputs the calculation results to the registers, and then from the registers to RAM 112 and external storage media.

[0039] ROM111 is a main storage device that stores various programs, data, and parameters used by CPU110 for various operations and controls. ROM111 can retain its stored contents even when the power supplied to it is zero.

[0040] RAM 112 is a main storage device used as working memory in CPU 110. Programs, data, etc., are written to and deleted from RAM 112 by CPU 110. RAM 112 is configured using storage devices such as semiconductor storage devices.

[0041] The communication module 113 sends and receives various types of information via the wireless network NW. The communication module 113 has a communication interface (I / F).

[0042] Figure 2 This diagram illustrates an example of the functional structure of the dashcam 1 according to this embodiment. The dashcam 1 includes a control unit 20, an acceleration acquisition unit 21, an angular velocity acquisition unit 22, a position acquisition unit 23, a vehicle signal acquisition unit 24, a data acquisition unit 25, a recording unit 26, a timing unit 27, an operation unit 28, a sound output unit 29, a display unit 210, a communication unit 211, and a storage unit 212.

[0043] The control unit 20 performs various controls on the dashcam 1. The control unit 20, for example, includes a CPU, which performs various calculations and transmits and receives information. The various functional units of the control unit 20 are implemented by the CPU reading programs from the ROM and executing them. The various functional units of the control unit 20 will be described later. The control unit 20 includes... Figure 1 The CPU110, ROM111, and RAM112 are shown.

[0044] Acceleration acquisition unit 21 acquires the acceleration of vehicle 3. Acceleration acquisition unit 21 generates acceleration data A1 based on the acquired acceleration. Acceleration data A1 represents the acceleration of vehicle 3. Acceleration acquisition unit 21 includes... Figure 1 The acceleration sensor 10 is shown.

[0045] The angular velocity acquisition unit 22 acquires the angular velocity of the vehicle 3. The angular velocity acquisition unit 22 generates angular velocity data B1 based on the acquired angular velocity. Angular velocity data B1 represents the angular velocity of the vehicle 3. The angular velocity acquisition unit 22 includes... Figure 1 The gyroscope sensor 11 shown.

[0046] The location acquisition unit 23 acquires the location of the vehicle 3. Based on the acquired location, the location acquisition unit 23 generates location data C1. Location data C1 represents the location of the vehicle 3. The location acquisition unit 23 includes... Figure 1 The GPS receiver 12 shown.

[0047] The vehicle signal acquisition unit 24 acquires vehicle signals from the vehicle 3. Based on the acquired vehicle signals, the vehicle signal acquisition unit 24 generates vehicle signal data D1. Vehicle signal data D1 includes data indicating ignition on / off, data indicating the vehicle speed of the vehicle 3, steering angle data, and seating data. The steering angle data represents the steering angle of the vehicle 3. The seating data represents the pressure value applied to the seat of the vehicle 3. The vehicle signal acquisition unit 24 includes... Figure 1 The vehicle signal cable 13 is shown.

[0048] The acquisition unit 25 acquires the sound produced by the driver 2's speech. The acquisition result of the acquisition unit 25 is the generation of sound data E1. Sound data E1 represents the sound produced by the driver 2's speech. The acquisition unit 25 includes... Figure 1 The microphone 18 shown.

[0049] The camera unit 26 captures one or more of the driver 2's face and the driver 2's movements. The camera unit 26 generates image data F1 from the captured images. Image data F1 represents one or more of the driver 2's face and the driver 2's movements. The camera unit 26 includes... Figure 1 Camera 14 is shown.

[0050] The timing unit 27 performs various timing operations. The timing unit 27 starts and stops the timing based on signals from the control unit 20. The timing unit 27 generates timing data G1 based on the timing results. The timing data G1 includes, for example, the time elapsed from receiving the start signal from the control unit 20 to receiving the stop signal. The timing unit 27 sometimes performs multiple timing operations in parallel. In the case of multiple timing operations in parallel, the timing data G1 includes the results of these multiple timings. Alternatively, the timing data G1 may also include the current time.

[0051] Timing unit 27 includes Figure 1 The timer 19 shown.

[0052] The operation unit 28 receives various operations performed by the user on the dashcam 1. The operation unit 28 includes... Figure 1 The operation button 17 is shown. Alternatively, if the operation button 17 is integrated with the display 16 and is provided as a touch panel, the operation unit 28 includes the touch panel.

[0053] The sound output unit 29 outputs various sounds. The sounds output by the sound output unit 29 include, for example, a warning sound output as a result of detecting an abnormality in the driver 2.

[0054] Display unit 210 displays various screens. Among the screens displayed on display unit 210 are, for example, warning screens displayed as a warning when an anomaly is detected, indicating that the driver 2 has been detected. Display unit 210 includes... Figure 1 The display 16 and RAM 112 are shown. RAM 112 contains the image data for the warning screen.

[0055] The communication unit 211 communicates with external devices. The external devices with which the communication unit 211 communicates include a server (not shown). The communication unit 211 includes... Figure 1 The communication module 113 shown.

[0056] Storage unit 212 stores various information. Storage unit 212 includes... Figure 1 The RAM112 shown.

[0057] Here, the functional units of the control unit 20 will be described. The control unit 20 includes an acquisition unit 200, an operation receiving unit 2010, a display control unit 2011, an alarm unit 2012, a detection execution unit 30, and a detection function management unit 31.

[0058] The acquisition unit 200 acquires various types of information. The acquisition unit 200 includes an acceleration data acquisition unit 201, an angular velocity data acquisition unit 202, a steering angle data acquisition unit 203, a position information acquisition unit 204, a vehicle signal data acquisition unit 205, a seating data acquisition unit 206, an audio data acquisition unit 207, an image acquisition unit 208, and a timing data acquisition unit 209.

[0059] The acceleration data acquisition unit 201 acquires acceleration data A1 from the acceleration acquisition unit 21.

[0060] The angular velocity data acquisition unit 202 acquires angular velocity data B1 from the angular velocity acquisition unit 22.

[0061] The steering angle data acquisition unit 203 acquires the steering angle data contained in the vehicle signal data D1 from the vehicle signal acquisition unit 24.

[0062] The location information acquisition unit 204 acquires location data C1 from the location acquisition unit 23.

[0063] The vehicle signal data acquisition unit 205 acquires vehicle signal data D1 from the vehicle signal acquisition unit 24.

[0064] The seating data acquisition unit 206 acquires the pressure data contained in the vehicle signal data D1 from the vehicle signal acquisition unit 24.

[0065] The sound data acquisition unit 207 acquires sound data E1 from the acquisition unit 25.

[0066] The image acquisition unit 208 acquires image data F1 from the imaging unit 26.

[0067] The timing data acquisition unit 209 acquires timing data G1 from the timing unit 27.

[0068] The operation receiving unit 2010 receives various operations performed on the operation unit 28.

[0069] The display control unit 2011 controls the display unit 210, causing the display unit 210 to display various screens.

[0070] The warning unit 2012 executes a warning. For example, the warning unit 2012 controls the sound output unit 29 to output a warning sound.

[0071] The detection execution unit 30 has AI capabilities and detects multiple items such as call actions. In other words, the detection execution unit 30 performs multiple detection functions based on multiple detection items. Furthermore, the learned models used by the detection execution unit 30 to make various decisions are stored in the storage unit 212. The detection execution unit 30 is equivalent to a driver monitoring system (DMS).

[0072] The detection execution unit 30 includes a facial authentication unit 300, a distracted driving determination unit 301, a drowsy driving determination unit 302, and a call action determination unit 303.

[0073] The facial authentication unit 300 authenticates the driver 2's face. The facial authentication unit 300 performs authentication based on AI functions by comparing the driver 2's face as represented by image data F1 acquired by the image acquisition unit 208 with the facial image (not shown) of the vehicle 3's owner stored in the storage unit 212. The facial authentication unit 300 collects the facial authentication result as driver information. Facial authentication is used, for example, to prevent unauthorized or unrelated persons from driving the vehicle 3, such as when the vehicle 3 is a business vehicle. For example, if the facial authentication result determines that the driver 2 is an unauthorized person, the facial authentication unit 300 causes the warning unit 2012 to issue a warning. Alternatively, facial authentication can also be used for theft prevention purposes to verify whether the driver 2 is the owner of the vehicle 3.

[0074] Distracted driving determination unit 301 determines distracted driving. The distracted driving determination unit 301 determines whether the driver 2 is distracted based on the actions of the driver 2 (e.g., the direction of their face, the direction of their gaze, etc.) represented by image data F1 acquired by the image acquisition unit 208. If the distracted driving determination unit 301 determines that the driver 2 is distracted, the warning unit 2012 issues a warning.

[0075] The drowsy driving determination unit 302 determines whether the driver is drowsy. The drowsy driving determination unit 302 determines whether the driver is drowsy based on the actions of the driver 2 (e.g., head movement, whether eyelids are open, etc.) represented by image data F1 acquired by the image acquisition unit 208. If the drowsy driving determination unit 302 determines that the driver 2 is drowsy, the warning unit 2012 issues a warning.

[0076] The call action determination unit 303 determines a call action. The call action determination unit 303 determines the call action based on the driver's voice as represented by the voice data E1 acquired by the voice data acquisition unit 207. The call action determination unit 303 may also determine the call action based on the driver's action (e.g., holding the mobile phone to his ear) as represented by the image data F1 acquired by the image acquisition unit 208. If the call action determination unit 303 determines that the driver 2 is making a call, it causes the warning unit 2012 to issue a warning.

[0077] The detection function management unit 31 determines whether to run any one of the multiple detection functions executed by the detection execution unit 30. In other words, the detection function management unit 31 selects the detection function to run from among the multiple detection functions. As a result of the determination (or selection), the detection function management unit 31 may run one detection function or multiple detection functions.

[0078] In the following explanation, the processing performed by the detection function management unit 31 will also be referred to as the detection function control processing.

[0079] The detection function management unit 31 includes a vehicle condition determination unit 310 and a detection function control unit 311.

[0080] The vehicle condition determination unit 310 determines the vehicle condition based on the test results of prescribed test items. These prescribed test items include, for example, ignition status, whether the driver is seated, vehicle acceleration, vehicle position, vehicle speed, and any one or more of the collected sounds. Vehicle condition refers to the condition of vehicle 3. Vehicle condition includes, for example, the movement of vehicle 3, the start of driving or a change of driver, and the driver 2 speaking. The movement of vehicle 3 includes, for example, vehicle 3 being moving, vehicle 3 traveling straight forward, etc.

[0081] In addition, the specified test items can also be any one or more of the following: ignition status, whether the person is seated, vehicle acceleration, vehicle position, vehicle speed, and the collected sound.

[0082] The detection function control unit 311 determines whether to run any one of the more than one detection functions for detecting dangerous driving based on the vehicle condition determined by the vehicle condition determination unit 310. The detection function control unit 311 outputs the determination result to the detection execution unit 30, causing the detection execution unit 30 to run the detection function represented by the determination result among the multiple detection functions.

[0083] Here, refer to Figure 3 The relationship between vehicle condition and whether multiple detection functions are running is explained. Figure 3 This is a diagram illustrating an example of the relationship between vehicle conditions and whether multiple detection functions are running, as described in this embodiment.

[0084] exist Figure 3 In the diagram, the vehicle status is shown as follows: vehicle 3 is stopped, vehicle 3 is moving, vehicle 3 is rotating, driver 2 is silent, and driver 2 is speaking. Figure 3 In each of these vehicle conditions, the system indicates whether a testing agency is operating for each of the detection items, namely facial recognition, distraction, drowsiness, and call activity.

[0085] The collection of driver information based on facial recognition is required at the start of driving and when the driver changes. Facial recognition is only performed when the vehicle is detected not to be moving (stopped) based on acceleration sensor, GPS data, vehicle speed pulse data, etc.; facial recognition stops for the remaining time when none of these are detected.

[0086] Dangerous driving warnings based on distracted driving detection are required when vehicle 3 is traveling straight ahead. The distracted driving detection function is only activated when vehicle 3 is detected to be moving based on acceleration sensor data, GPS data, vehicle speed pulse data, etc., or when vehicle 3 is not turning (is traveling straight) based on gyroscope sensor data, steering angle data, etc. If none of these conditions are detected, the distracted driving detection function will cease for the remaining time. Furthermore, the determination of whether to activate the distracted driving detection function does not require detection of driver silence or driver speech.

[0087] A drowsy driving warning based on drowsiness detection is required when vehicle 3 is moving and driver 2 is silent. The drowsiness detection function is only executed when vehicle 3 is detected to be moving based on acceleration sensor, GPS data, vehicle speed pulse data, etc.; when vehicle 3 is detected to be turning based on gyroscope sensor, steering angle data, etc.; or when driver silence is detected based on sound data collected from the microphone. The drowsiness detection function is stopped for the remaining time if any of these conditions are not detected.

[0088] The dangerous driving warning based on call detection is required when vehicle 3 is moving and driver 2 is speaking. The call detection function is only executed when vehicle 3 is detected to be moving based on acceleration sensor, GPS data, vehicle speed pulse data, etc.; when vehicle 3 is detected to be turning based on gyroscope sensor, steering angle data, etc.; or when the driver is detected to be speaking based on sound data collected from the microphone. The call detection function is stopped for the remaining time if any of these conditions are not detected.

[0089] [Detection Function Control Processing]

[0090] Next, refer to Figure 4 and Figure 5 A specific example of the detection function control processing will be explained. For example, during the period when the power of the dashcam 1 is turned on, the control unit 20 repeatedly executes the detection function in parallel. Figure 4 and Figure 5 The detection function control processing is shown. Alternatively, it can be executed only. Figure 4 and Figure 5 Any one of the detection function control processes shown.

[0091] exist Figure 4 and Figure 5 Before the detection function control process shown begins, multiple detection functions are determined to be inactive. That is, the control unit 20 prevents any of the multiple detection functions from operating. Figure 4 and Figure 5 The detection function control process shown did not determine that the detection function was running. However, due to repeated execution... Figure 4 and Figure 5 The detection function control process shown means that even if a detection function is determined to be not running at a certain point in time, it may sometimes be determined to be running in the next detection function control process. Similarly, even if a detection function is determined to be running at a certain point in time, it may sometimes be determined to be not running in the next detection function control process.

[0092] Figure 4 This is a diagram illustrating an example of the detection function control process involved in this embodiment.

[0093] Step S10: The vehicle condition determination unit 310 acquires various detection results. Here, the vehicle condition determination unit 310 acquires acceleration data A1 from the acceleration data acquisition unit 201. The vehicle condition determination unit 310 acquires position data C1 from the position information acquisition unit 204. The vehicle condition determination unit 310 acquires vehicle signal data D1 from the vehicle signal data acquisition unit 205. The vehicle condition determination unit 310 acquires timing data G1 from the timing data acquisition unit 209. The vehicle condition determination unit 310 acquires pressure data from the seating data acquisition unit 206.

[0094] Step S20: The vehicle condition determination unit 310 determines whether the total changes in the acceleration, position, and speed of the vehicle 3 are less than a predetermined value. For example, for changes in acceleration, the vehicle condition determination unit 310 calculates the change by dividing the acceleration represented by acceleration data A1 by a predetermined time represented by timing data G1. For changes in position, the vehicle condition determination unit 310 calculates the change by dividing the distance between multiple positions represented by position data C1 by a predetermined time represented by timing data G1. For changes in speed, the vehicle condition determination unit 310 calculates the change based on the vehicle speed signal represented by vehicle signal data D1 and the predetermined time represented by timing data G1.

[0095] The specified change in the acceleration of vehicle 3 is, for example, a change exceeding the change in continuous vibration of the engine, etc. This specified change in acceleration can be determined in advance or calculated on-the-spot based on representative values ​​such as the average or median value of the changes in acceleration over a specified period of time.

[0096] The specified change in the position of vehicle 3 refers, for example, to a change in GPS position after 1 second, representing a specified distance of 1 meter. The unit of time is not limited to 1 second; it can also be set to an appropriate time between 10 milliseconds and 10 seconds. Furthermore, the specified distance is not limited to 1 meter; it can also be set to an appropriate distance between 0 meters and 10 meters.

[0097] The speed of vehicle 3 is specified to vary by, for example, 3 kilometers per hour. It is not limited to 3 kilometers per hour; it can also be set to an appropriate speed between 0 and 5 kilometers per hour.

[0098] If the vehicle condition determination unit 310 determines that the total changes in the acceleration, position, and speed of the vehicle 3 are less than a specified value (step S20; yes), it executes the processing in step S30. On the other hand, if the vehicle condition determination unit 310 determines that the changes in any one or more of the acceleration, position, and speed of the vehicle 3 are greater than or equal to a specified value (step S20; no), the detection function management unit 31 executes the processing in step S50.

[0099] Step S30: The vehicle condition determination unit 310 determines whether the ignition has been turned on within a specified time or whether there has been a change in the seat occupancy sensor. A change in the seat occupancy sensor indicates a change in the position or number of occupants seated in the seat.

[0100] To determine whether the ignition has been switched on within a specified time, the vehicle status determination unit 310 starts timing unit 27 when the vehicle signal data D1 indicates that the ignition is switched on. The vehicle status determination unit 310 makes a determination based on a comparison of the elapsed time from the switch on to the specified time using timing data G1.

[0101] In addition, to determine whether the ignition is turned on within the specified time, a determination can also be made based on vehicle signals other than vehicle signal data D1.

[0102] In order to determine whether there is a change in the seat seating sensor, the vehicle condition determination unit 310 makes a determination based on the pressure value applied to the seat of the vehicle 3 as expressed by the pressure data.

[0103] If the vehicle condition determination unit 310 determines that the ignition has been turned on within a specified time or that there has been a change in the seat occupancy sensor (step S30; Yes), the detection function management unit 31 executes the processing in step S40. On the other hand, if the vehicle condition determination unit 310 determines that the ignition has been turned on outside the specified time and there has been no change in the seat occupancy sensor (step S30; No), the detection function management unit 31 terminates the detection function control processing.

[0104] Step S40: The detection function control unit 311 determines that the facial authentication function is to be run. The detection function control unit 311 causes the facial authentication unit 300 to perform the facial authentication function.

[0105] Step S50: The detection function control unit 311 determines that the distracted driving judgment function is to be executed. The detection function control unit 311 causes the distracted driving judgment unit 301 to execute the distracted driving judgment function. That is, the detection function control unit 311 executes the distracted driving judgment function when the vehicle condition judgment unit 310 determines that any one or more of the changes in the acceleration of the vehicle 3, the position of the vehicle 3, and the speed of the vehicle 3 are above a certain limit.

[0106] The above completes the detection function control process in the Detection Function Management Department 31.

[0107] Additionally, facial recognition is required when driver 2 is replaced. Figure 4 The detection function control process shown is based on the assumption that driver 2 is replaced by driver 3 who has not moved. Figure 4 In the detection function control process shown, as an example of the condition that vehicle 3 has not moved, the condition of being within a specified time after ignition is turned on is used.

[0108] Additionally, the determination of distracted driving needs to be made when vehicle 3 is in motion. Figure 4In the detection function control process shown, as an example of the condition that vehicle 3 is moving, the changes in the acceleration, position, and speed of vehicle 3 are used as the conditions specified above.

[0109] Furthermore, as mentioned above, in Figure 4 The detection function control process shown is an example illustrating two scenarios: whether to run the facial recognition function and whether to run the distracted driving detection function. However, it is not limited to this. Figure 4 In the detection function control process shown, the determination of whether to run the facial authentication function or the function to determine distracted driving can also be omitted.

[0110] Without determining whether facial recognition is enabled, Figure 4 The detection function control process shown omits steps S30 and S40. In this case, in step S20, if the vehicle condition determination unit 310 determines that the changes in all of the vehicle 3's acceleration, vehicle 3's position, and vehicle 3's speed are less than a predetermined value (step S20; Yes), the detection function management unit 31 terminates the detection function control process. On the other hand, if the vehicle condition determination unit 310 determines that the changes in any one or more of the vehicle 3's acceleration, vehicle 3's position, and vehicle 3's speed are greater than or equal to a predetermined value (step S20; No), the detection function management unit 31 executes step S50.

[0111] Without determining whether the function for detecting distracted driving is running, Figure 4 The steps S20 and S50 are omitted in the detection function control process shown. In this case, the process of step S30 is executed after the process of step S10. In step S30, if the vehicle condition determination unit 310 determines that the ignition has been turned on within a specified time or that there is a change in the seat occupancy sensor (step S30; Yes), the detection function management unit 31 executes the process of step S40. On the other hand, if the vehicle condition determination unit 310 determines that the ignition has been turned on within a specified time and there is no change in the seat occupancy sensor (step S30; No), the detection function management unit 31 ends the detection function control process.

[0112] Furthermore, a change in the seat seating sensor is one example of a change in the seating status. Another example of a change in the seating status is when a door of vehicle 3 is opened or closed. To determine whether a change in the seating status has occurred, the vehicle condition determination unit 310 can also determine whether a door of vehicle 3 has been opened or closed. In this case, the vehicle signal data D1 includes a signal indicating whether the door has been opened or closed. The vehicle condition determination unit 310 determines whether a door of vehicle 3 has been opened or closed based on this signal.

[0113] In addition, the vehicle condition determination unit 310 can also determine whether the seating status has changed, and whether the seat seating sensor has changed or whether the vehicle door of the vehicle 3 has been opened or closed, in order to determine whether the seating status has changed.

[0114] As described above, in step S30, the vehicle condition determination unit 310 determines whether the ignition has been turned on within a specified time or whether the seating position has changed. Therefore, the detection function control unit 311 operates the facial authentication function when the vehicle condition determination unit 310 determines that the changes in the acceleration, position, and speed of the vehicle 3 are all less than a specified amount, and the vehicle condition determination unit 310 determines that the ignition has been turned on within a specified time or that the seating position has changed.

[0115] Figure 5 This is a diagram illustrating an example of the detection function control process involved in this embodiment.

[0116] Step S110: The vehicle condition determination unit 310 acquires various test results. Here, the vehicle condition determination unit 310 acquires sound data E1 from the sound data acquisition unit 207.

[0117] Step S120: The vehicle condition determination unit 310 determines whether the driver 2 is speaking. The vehicle condition determination unit 310 determines whether the driver 2 is speaking or silent based on the voice of the driver 2 represented by the voice data E1.

[0118] If the vehicle condition determination unit 310 determines that the driver 2 is speaking (step S120; yes), the detection function management unit 31 performs the processing of step S130. On the other hand, if the vehicle condition determination unit 310 determines that the driver 2 is not speaking (silent) (step S120; no), the detection function management unit 31 performs the processing of step S140.

[0119] Step S130: The detection function control unit 311 determines that the image recognition function for determining a call action is to be executed. The detection function control unit 311 causes the call action determination unit 303 to execute the image recognition function for determining a call action. Therefore, the detection function control unit 311 executes the image recognition function for determining a call action when the vehicle condition determination unit 310 determines that the driver 2 is speaking.

[0120] Step S140: The detection function control unit 311 determines that the image recognition function for determining drowsy driving is to be executed. The detection function control unit 311 causes the drowsy driving determination unit 302 to execute the image recognition function for determining drowsy driving. Therefore, when the vehicle condition determination unit 310 determines that the driver 2 is silent, the detection function control unit 311 executes the image recognition function for determining drowsy driving.

[0121] The above completes the detection function control process in the Detection Function Management Department 31.

[0122] In addition, Figure 5 The detection function control process shown illustrates an example of determining whether to run the image recognition function for detecting drowsy driving based on whether the driver 2 is speaking, but it is not limited to this. For example, it is also possible to determine whether to run the image recognition function for detecting drowsy driving based on the driver 2's speech and steering angle. In this case, if the driver 2 is silent and the steering angle is above a certain limit, it is considered that there is a possibility of drowsiness, and the detection function control unit 311 runs the function.

[0123] As explained above, the detection function control device (in this embodiment, the vehicle recorder 1) includes a vehicle condition determination unit 310 and a detection function control unit 311.

[0124] The vehicle condition determination unit 310 determines the condition of the vehicle 3 (in this embodiment, vehicle condition) based on one or more of the following detection results: ignition status, whether the person is seated, acceleration of the vehicle 3, position of the vehicle 3, speed of the vehicle 3, and collected sound.

[0125] The detection function control unit 311 determines whether to run one or more detection functions (in this embodiment, facial recognition unit 300, distracted driving determination unit 301, drowsy driving determination unit 302, and call action determination unit 303) based on the condition determined by the vehicle condition determination unit 310 (vehicle condition in this embodiment).

[0126] According to this structure, in the detection function control device (driving recorder 1 in this embodiment), regarding more than one detection function for detecting dangerous driving, only the necessary function can be run according to the condition of the vehicle 3, thus enabling the execution of more detection functions within the available computing power. As mentioned above, the detection function is based on AI. In the detection function control device of this embodiment, even in a small terminal with limited computing power equipped with a DMS, more dangerous driving warning functions can be installed and executed.

[0127] Furthermore, in the detection function control device (in this embodiment, a driving recorder 1) involved in this embodiment, the detection function control unit 311 operates the facial authentication function (in this embodiment, the facial authentication unit 300) when the vehicle condition determination unit 310 determines that the changes in all of the acceleration, position, and speed of the vehicle 3 are less than a specified amount, and the vehicle condition determination unit 310 determines that the ignition has been turned on within a specified time or the vehicle condition determination unit 310 determines that the seating state has changed. When the vehicle condition determination unit 310 determines that any one or more of the changes in the acceleration, position, and speed of the vehicle 3 are greater than a specified amount, the distracted driving determination function (in this embodiment, the distracted driving determination unit 301) is operated.

[0128] According to this structure, in the detection function control device (driving recorder 1 in this embodiment), it is possible to determine whether a change of driver 2 has occurred based on the fact that the vehicle 3 has not moved. Therefore, if a change of driver 2 has occurred, the facial recognition function can be operated. In addition, since the detection function control device in this embodiment can determine whether the vehicle 3 is in motion, it is possible to operate the function of detecting distracted driving when the vehicle 3 is in motion.

[0129] Furthermore, the conditions under which the detection function control device operates the facial recognition function or the distracted driving determination function are not limited to the conditions described above. For example, the detection function control unit 311 may also operate the facial recognition unit 300 if the vehicle condition determination unit 310 determines that any one or more changes in the acceleration, position, or speed of the vehicle 3 are less than a predetermined value and the vehicle condition determination unit 310 determines that the ignition has been turned on within a predetermined time. Additionally, the detection function control unit 311 may also operate the distracted driving determination unit 301 if the vehicle condition determination unit 310 determines that all changes in the acceleration, position, and speed of the vehicle 3 are greater than or equal to a predetermined value.

[0130] Furthermore, the detection function control unit 311 can also operate the facial recognition unit 300 if the vehicle condition determination unit 310 determines that any one of the changes in the acceleration, position, or speed of the vehicle 3 is less than a specified value. The detection function control unit 311 can also operate the facial recognition unit 300 if the vehicle condition determination unit 310 determines that the ignition has been turned on within a specified time.

[0131] In addition, in the detection function control device (driving recorder 1 in this embodiment), when the vehicle condition determination unit 310 determines that the driver 2 is speaking, the detection function control unit 311 runs the image recognition function for determining the call action (call action determination unit 303 in this embodiment), and when the vehicle condition determination unit 310 determines that the driver 2 is silent, it runs the image recognition function for determining drowsy driving (drowsy driving determination unit 302 in this embodiment).

[0132] According to this structure, in the detection function control device (driving recorder 1 in this embodiment), it is possible to determine whether the driver 2 is talking. Therefore, when the driver 2 is silent, the image recognition function for determining drowsy driving can be run.

[0133] Alternatively, one or more of the facial authentication unit 300, distracted driving determination unit 301, drowsy driving determination unit 302, or call action determination unit 303 may be omitted from the structure of the detection execution unit 30. Furthermore, in addition to the facial authentication unit 300, distracted driving determination unit 301, drowsy driving determination unit 302, and call action determination unit 303, or replacing any one of them, the detection execution unit 30 may include functional units with other detection functions.

[0134] Additionally, the vehicle condition determination unit 310 can also handle day / night recognition based on vehicle condition. During the day, it is considered unnecessary to detect drowsy driving. In this case, the dashcam 1 can also be equipped with an illuminance sensor. If the vehicle condition determination unit 310 determines that the brightness measured by the illuminance sensor is above a certain level, the detection function control unit 311 prevents the drowsy driving determination unit 302 from operating the image recognition function for detecting drowsy driving.

[0135] In addition, dashcam 1 Figure 2 In addition to the functions described above, it also has a recording function that stores images continuously recorded by camera 14 in storage unit 212.

[0136] Additionally, the dashcam 1 can also perform impact detection processing. During impact detection processing, if an impact of a predetermined magnitude or greater is detected, this includes processing such as outputting a warning sound from the sound output unit 29 and displaying a warning image on the display unit 210. Furthermore, the impact detection processing includes generating event information and storing the event information in the storage unit 212.

[0137] Furthermore, the control unit 20 can also be configured as a device installed in the vehicle 3, other than a dashcam. When the device is a small terminal, the structure of the control unit 20 is preferred. Here, a small terminal refers to a terminal with relatively low computing power, making it difficult to perform multiple AI functions simultaneously.

[0138] Alternatively, a part of the dashcam 1 described in the above embodiment, such as the control unit 20, can be implemented using a computer. In this case, it can also be achieved by recording the program for implementing the control function on a computer-readable recording medium, and having the computer system read and execute the program recorded on the recording medium. Furthermore, the "computer system" referred to here is a computer system built into the dashcam 1, including hardware such as the operating system and peripheral devices. Additionally, the "computer-readable recording medium" refers to removable media such as floppy disks, optical disks, ROMs, and CD-ROMs, and storage devices such as hard disks built into the computer system. Moreover, the "computer-readable recording medium" can also include a medium that dynamically maintains the program for a short period of time, such as a communication line in the case of transmitting the program via a network such as the Internet or a communication line such as a telephone line, or a medium that maintains the program for a certain period of time, such as volatile memory inside a computer system that serves as a server or client in such cases. Furthermore, the program described above can be a program used to implement the aforementioned functions, or it can be a program that can implement the aforementioned functions by combining with programs already recorded in the computer system.

[0139] Alternatively, part or all of the dashcam 1 in the above embodiments can be implemented as an integrated circuit such as an LSI (Large Scale Integration). Each functional block of the dashcam 1 can be processorized individually, or part or all can be integrated into a processor. Furthermore, the method of integrated circuit implementation is not limited to LSI; it can also be implemented using dedicated circuits or general-purpose processors. Additionally, if advancements in semiconductor technology lead to integrated circuit technologies that replace LSI, integrated circuits based on such technologies can also be used.

[0140] The above description of one embodiment of the present invention has been provided with reference to the accompanying drawings. However, the specific structure is not limited to the structure described above, and various design changes can be made without departing from the spirit of the present invention.

[0141] Industrial availability

[0142] The detection function control device involved in this embodiment can be used as a dashcam mounted in a vehicle.

[0143] Symbol Explanation

[0144] 1: Dashcam;

[0145] 2: Driver;

[0146] 3: Vehicles;

[0147] 310: Vehicle Condition Assessment Department;

[0148] 311: Detection Function Control Unit;

[0149] 300: Facial Recognition Department;

[0150] 301: Distracted Driving Detection Unit;

[0151] 302: Drowsy Driving Detection Department;

[0152] 303: Call Action Judgment Department.

Claims

1. A detection function control device, comprising: The vehicle condition determination unit determines the condition of the vehicle based on one or more of the following detection results: ignition status, whether the person is seated, vehicle acceleration, vehicle position, vehicle speed, and collected sound. as well as The detection function control unit determines, based on the condition determined by the vehicle condition determination unit, whether to activate any one of the more than one detection functions for detecting dangerous driving. When the vehicle condition determination unit determines that the total changes in acceleration, position, and speed are less than a specified value and the vehicle condition determination unit determines that the ignition has been turned on within a specified time, or when the vehicle condition determination unit determines that the total changes in acceleration, position, and speed are less than a specified value and the vehicle condition determination unit determines that the seating status has changed, the detection function control unit operates the facial authentication function.

2. The detection function control device according to claim 1, wherein, When the vehicle condition determination unit determines that the change in any one or more of the acceleration, position, and speed is above a certain limit, the detection function control unit operates the function for determining distracted driving.

3. The detection function control device according to claim 1, wherein, When the vehicle condition determination unit determines that the driver is speaking, the detection function control unit operates the image recognition function for determining the call action.

4. The detection function control device according to claim 1, wherein, When the vehicle condition determination unit determines that the driver is silent, the detection function control unit operates the image recognition function for determining drowsy driving.

5. A detection function control method, comprising: The vehicle condition determination step determines the vehicle condition based on one or more of the following detection results: ignition status, whether the person is seated, vehicle acceleration, vehicle position, vehicle speed, and collected sound. The detection function control step determines, based on the condition determined by the vehicle condition determination step, whether to operate any one of the more than one detection functions for detecting dangerous driving; as well as When the vehicle condition determination step determines that the total changes in acceleration, position, and speed are less than a specified value and the vehicle condition determination step determines that the ignition has been turned on within a specified time, or when the vehicle condition determination step determines that the total changes in acceleration, position, and speed are less than a specified value and the vehicle condition determination step determines that the seating status has changed, the facial authentication function is activated.

6. A computer-readable recording medium containing a program for causing a computer to execute: The vehicle condition determination step determines the vehicle condition based on one or more of the following detection results: ignition status, whether the person is seated, vehicle acceleration, vehicle position, vehicle speed, and collected sound. The detection function control step determines, based on the condition determined by the vehicle condition determination step, whether to operate any one of the more than one detection functions for detecting dangerous driving; as well as When the vehicle condition determination step determines that the total changes in acceleration, position, and speed are less than a specified value and the vehicle condition determination step determines that the ignition has been turned on within a specified time, or when the vehicle condition determination step determines that the total changes in acceleration, position, and speed are less than a specified value and the vehicle condition determination step determines that the seating status has changed, the facial authentication function is activated.

Images