Automatic location method and device for determining inattentive area, road vehicle, electronic device
The method and device improve inattentive area detection accuracy by capturing and analyzing multiple facial images to determine a normal driving angle, filtering abnormal conditions, and adapting to individual drivers and conditions, thereby reducing false detections and enhancing road safety.
Patent Information
- Application Number
- JP2024533151
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2021-12-07
- Filing Date
- 2022-11-10
- Publication Date
- 2024-11-21
- Estimated Expiration
- 2042-11-10
AI Technical Summary
Current methods for detecting driver inattentiveness in vehicles suffer from poor accuracy due to individual differences and environmental factors, leading to false detections and inadequate handling of varying driving postures and conditions.
A method and device that captures multiple facial images of a driver within a predetermined time, combines these images to determine a normal driving angle, and locates inattentive areas based on this angle and a critical deflection angle, filtering out abnormal driving conditions to improve accuracy.
Enhances the accuracy of inattentive area detection by adapting to individual drivers and driving conditions, reducing false detections and improving road safety through real-time tracking and adaptive threshold adjustments.
Smart Images

Figure 2024543600000001_ABST
Abstract
Description
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims priority to a Chinese patent application filed with the China Patent Office on December 7, 2021, bearing application number 202111489217.X and titled "Method and apparatus for automatic location of inattentive area, road vehicle, electronic device," the entire contents of which are incorporated herein by reference. [Technical field]
[0002] The present disclosure relates to the technical field of information processing, and in particular to a method and device for automatically locating inattentive areas, road vehicles, and electronic devices. [Background technology]
[0003] In the related art, drivers often become distracted during driving due to fatigue, external factors, etc., and such distracted driving may lead to traffic accidents, so it is necessary to monitor whether the driver is in a distracted state, and before monitoring whether the driver is in a distracted state, it is necessary to quickly locate the distracted driving area of each vehicle, and currently, when locating the distracted driving area, the location error is large because it is influenced by the difference between the drivers themselves (difference due to driving posture or personnel change), driving habits, and the types of vehicles. Also, current inattentive driving area location methods generally locate the inattentive driving area using a fixed area threshold, so errors are likely to occur in the located inattentive driving area due to driving posture or personnel change. Summary of the Invention [Problem to be solved by the invention]
[0004] In the currently adopted location method, the driver's inattentive state can be detected in real time by acquiring the driver's eye movement behavior information, and an early warning can be given to the driver's inattentive behavior during driving, thereby effectively improving road traffic safety. However, this method uses traditional machine learning methods, and the accuracy is poor due to the influence of light and individual differences of drivers. In addition, this method does not handle the special scenarios of real vehicles, and there are many false detection situations.
[0005] No effective solution has yet been put forward to the above problems.
[0006] In order to solve the technical problem in at least the related art that the inattentive area changes due to changes in driving posture or person status, and the inattentive detection still uses a fixed inattentive area, resulting in erroneous detection, the present disclosure provides a method and device for automatically locating the inattentive area, a road vehicle, and an electronic device. [Means for solving the problem]
[0007] According to one aspect of the present disclosure, a method for automatically locating an inattentive area is provided, comprising the steps of: capturing a plurality of facial images of a driver currently within a vehicle within a predetermined time period; combining the plurality of facial images to determine a normal driving angle of the driver within the current vehicle; and locating a non-inattentive area and an inattentive area of the driver within the current vehicle based on the normal driving angle and a predetermined critical inattentive deviation angle of the current vehicle.
[0008] Preferably, the step of combining the plurality of facial images to determine the normal driving angle of the driver in the current vehicle includes the steps of combining non-normal driving information to determine the non-normal driving state of the driver, removing images corresponding to the non-normal driving state from all facial images, and obtaining a normal driving image set; and calculating and updating the normal driving angle based on the normal driving image set.
[0009] Preferably, before combining the multiple facial images to determine a normal driving angle of the driver in the current vehicle, the method further includes a step of initializing the normal driving angle, including a step of initializing the normal driving angle using a default value, or a step of initializing the normal driving angle using a first gaze angle when the driver gazes at a first mark point.
[0010] Preferably, the non-normal driving information includes at least one of low vehicle speed, triggering of steering signals, inattentive driving, and grip strength.
[0011] Preferably, the step of combining a low vehicle speed to determine the driver's abnormal driving state includes the steps of: acquiring a vehicle speed of the current vehicle; and determining that the driver is in an abnormal driving state if the vehicle speed is lower than a predetermined speed threshold.
[0012] Preferably, the step of combining the triggering of a steering signal to determine the abnormal driving state of the driver includes the steps of: capturing a signal trigger state of a steering signal of the current vehicle; determining that the driver is in a normal driving state if the signal trigger state indicates that the steering signal has not been triggered; and determining that the current vehicle is in a cornering state and that the driver is in an abnormal driving state if the signal trigger state indicates that the steering signal has been triggered.
[0013] Preferably, the step of combining the inattentive bias to determine the non-normal driving state of the driver includes the steps of capturing the face and gaze angle of the driver, collecting statistics on the period during which the face and gaze angle of the driver are in a predetermined non-normal driving area, and determining that the driver is in an non-normal driving state if the period during which the face and gaze angle are in the non-normal driving area reaches a first period threshold.
[0014] Preferably, the step of combining grip force to determine the non-normal driving state of the driver includes the steps of capturing the driver's grip force of a steering wheel, and determining that the driver is in a non-normal driving state when the grip force of the steering wheel is lower than a predetermined grip force threshold.
[0015] Preferably, the step of calculating and updating the normal driving angle based on the normal driving image set includes the steps of: outputting, for each image in the normal driving image set, normal face and gaze angle values corresponding to each image by a face angle and gaze angle model; and calculating statistics of all the normal face and gaze angle values to update the normal driving angle.
[0016] Preferably, the step of predetermining the current vehicle's critical inattentive deviation angle includes the steps of locating a non-inattentive marking area and an inattentive marking area inside the current vehicle based on a predetermined region of interest, wherein the non-inattentive marking area includes a normal gaze sign point and the inattentive area includes at least a boundary sign point; capturing images of multiple drivers heading toward the normal gaze sign point and the boundary sign point, respectively, to obtain normal gaze images and inattentive gaze images; and analyzing the normal gaze images and the inattentive gaze images to determine a critical inattentive deviation angle of the current vehicle's inattentive area.
[0017] Preferably, the step of locating the non-inattentive marking area and the inattentive marking area inside the current vehicle based on a predetermined area of interest includes the steps of representing the predetermined area of interest as the non-inattentive marking area inside the current vehicle, determining a center point of the non-inattentive marking area to obtain the normal gaze marking point, and determining a plurality of boundaries of the non-inattentive marking area and determining an inattentive marking area outside the non-inattentive marking area with each of the boundaries as a side, wherein any point on the boundary is represented as the boundary marking point.
[0018] Preferably, the step of analyzing the normal gaze image and the inattentive gaze image to obtain the critical inattentive deviation angle of the current vehicle inattentive region includes the steps of: analyzing the normal gaze image to determine a gaze angle for gazing at the normal gaze sign point, and obtaining a first normal driving angle based on a distribution of gaze angles for gazing at the normal gaze sign point; analyzing all the inattentive gaze images to obtain a distribution of the critical inattentive driving angle of the inattentive region, and calculating an average value of the critical inattentive driving angle of the inattentive region based on the distribution of the critical inattentive driving angle of the inattentive region; and calculating a difference value between the first normal driving angle and the average value of the critical inattentive driving angle to obtain all the current vehicle critical inattentive deviation angles.
[0019] Preferably, the step of locating the non-inattentive area and the inattentive area within the current vehicle of the driver based on the normal driving angle and the predetermined critical inattentive deviation angle of the current vehicle includes the steps of adding the critical inattentive deviation angle of the current vehicle based on the normal driving angle to obtain a critical position of the inattentive area boundary, and locating the area included in the critical position of the inattentive area boundary as the non-inattentive area, and locating the area excluding the area included in the critical position of the inattentive area boundary as the inattentive area.
[0020] According to another aspect of the present disclosure, there is further provided an automatic location device for inattentive areas, comprising: a capture unit, configured to capture a plurality of facial images of a driver currently within a vehicle within a predetermined time period; a determination unit, configured to combine the plurality of facial images to determine a normal driving angle of the driver within the current vehicle; and a location unit, configured to locate a non-inattentive area and an inattentive area of the driver within the current vehicle based on the normal driving angle and a predetermined critical inattentive deviation angle of the current vehicle.
[0021] Preferably, the determination unit includes: a first determination module, which is arranged to combine non-normal driving information to determine a non-normal driving state of the driver, and remove images corresponding to the non-normal driving state from all facial images to obtain a normal driving image set; and an update module, which is arranged to statistically update the normal driving angle based on the normal driving image set.
[0022] Preferably, the automatic location device further includes an initialization unit configured to initialize the normal driving angle before combining the multiple facial images to determine the normal driving angle of the driver in the current vehicle, and the initialization unit includes a first initialization module configured to initialize the normal driving angle using a default value, or a second initialization module configured to initialize the normal driving angle using a first gaze angle when the driver gazes at a first mark point.
[0023] Preferably, the non-normal driving information includes at least one of low vehicle speed, triggering of steering signals, inattentive driving, and grip strength.
[0024] Preferably, the first determination module includes a first capture sub-module configured to capture a vehicle driving speed of the current vehicle, and a first determination sub-module configured to determine that the driver is in an abnormal driving state if the vehicle driving speed is lower than a predetermined speed threshold.
[0025] Preferably, the first determination module includes: a second capture sub-module arranged to capture a signal trigger state of the steering signal of the current vehicle; a second determination sub-module for determining that the driver is in a normal driving state if the signal trigger state indicates that the steering signal has not been triggered; and a third determination sub-module for determining that the current vehicle is in a cornering state and that the driver is in an abnormal driving state if the signal trigger state indicates that the steering signal has been triggered.
[0026] Preferably, the first determination module includes a third capture sub-module configured to capture the driver's face and gaze angle, a first statistics sub-module configured to collect statistics on the period during which the driver's face and gaze angle are in a predetermined abnormal driving area, and a fourth determination sub-module configured to determine that the driver is in an abnormal driving state if the period during which the driver's face and gaze angle are in a predetermined abnormal driving area reaches a first period threshold.
[0027] Preferably, the first determination module includes a fourth capture sub-module configured to capture the driver's steering wheel grip force, and a fifth determination sub-module configured to determine that the driver is in an abnormal driving state if the steering wheel grip force is lower than a predetermined grip force threshold.
[0028] Preferably, the update module includes: an output sub-module, configured to output, for each image in the normal driving image set, normal face and gaze angle values corresponding to each image according to a face angle and gaze angle model; and a second statistics sub-module, configured to collect statistics of all the normal face and gaze angle values and update the normal driving angle.
[0029] Preferably, the automatic location device for inattentive areas further includes: an area location module arranged to locate a non-inattentive marking area and an inattentive marking area inside the current vehicle based on a predetermined area of interest, where the non-inattentive marking area includes a normal gaze sign point and the inattentive area includes at least a boundary sign point; an image capture module arranged to capture images of multiple drivers heading toward the normal gaze sign points and the boundary sign points, respectively, to obtain normal gaze images and inattentive gaze images; and an image analysis module that analyzes the normal gaze images and the inattentive gaze images to obtain a critical inattentive deviation angle for the current vehicle inattentive area.
[0030] Preferably, the area location module includes a sixth determination sub-module arranged to represent a predetermined area of interest as a non-inattentive marking area inside the current vehicle, a seventh determination sub-module arranged to determine a center point of the non-inattentive marking area to obtain the normal gaze marking point, and an eighth determination sub-module arranged to determine a plurality of boundaries of the non-inattentive marking area and determine an inattentive marking area outside the non-inattentive marking area with each of the boundaries as a side, wherein any point on the boundary is represented as the boundary marking point.
[0031] Preferably, the image analysis module includes: an analysis sub-module configured to analyze the normal gaze image to determine a gaze angle for gazing at the normal gaze sign point, and obtain a first normal driving angle based on a distribution of gaze angles for gazing at the normal gaze sign point; a first calculation sub-module configured to analyze all the inattentive gaze images to obtain a distribution of a critical inattentive driving angle of an inattentive region, and calculate an average value of the critical inattentive driving angle of the inattentive region based on the distribution of the critical inattentive driving angle of the inattentive region; and a second calculation sub-module configured to calculate a difference value between the first normal driving angle and the average value of the critical inattentive driving angle, and obtain all the current vehicle critical inattentive deviation angles.
[0032] Preferably, the location unit includes a first location module arranged to add the current vehicle critical inattentive deviation angle based on the normal driving angle to obtain a critical position of an inattentive area boundary, and a second location module arranged to locate an area included in the critical position of the inattentive area boundary to the non-inattentive area, and to locate an area excluding the area included in the critical position of the inattentive area boundary to the inattentive area.
[0033] According to another aspect of the present disclosure, a road vehicle is further provided, comprising an on-board camera mounted on a windshield at the front of the vehicle and positioned to capture a road image of the road ahead, and an on-board control unit connected to the on-board camera and configured to execute the method for automatically locating an inattentive area described in any one of the above claims.
[0034] According to another aspect of the present disclosure, there is further provided an on-board electronic device, comprising: a processor; and a memory configured to store executable instructions for the processor, the processor being configured to execute the method for automatically locating an inattentive area as described in any one of the above claims by executing the executable instructions.
[0035] According to another aspect of the present disclosure, there is further provided a computer-readable storage medium, the computer-readable storage medium including a computer program stored therein, the computer program controlling an apparatus in which the computer-readable storage medium is located to execute the method for automatically locating an inattentive area described in any one of the above claims when the apparatus is driven. Effect of the Invention
[0036] In the present disclosure, automatic location is used to perform tracking processing for different driver individuals and driving conditions, which improves the accuracy of location of inattentive areas and effectively reduces false detection compared with the fixed threshold method.
[0037] In the present disclosure, a multi-information fusion solution is used to filter out non-normal driving conditions during driving to avoid false detection.
[0038] In the present disclosure, a plurality of face images of the driver currently in the vehicle within a predetermined time period are used to determine the normal driving angle of the driver in the current vehicle by combining the plurality of face images, and locating the non-inattentive area and inattentive area of the driver in the current vehicle according to the normal driving angle and the predetermined critical inattentive deviation angle of the current vehicle. In the present disclosure, a plurality of face images of the driver in the current vehicle are analyzed to locate the non-inattentive area and inattentive area of the automatic driver in the current vehicle, and a tracking process is performed for different driver individuals and driving states to improve the accuracy of locating the inattentive area, and further improve the accuracy of detecting the inattentive state, solving the technical problem in the related art that the inattentive area changes due to driving posture or person change, and the inattentive detection still uses a fixed inattentive area, resulting in erroneous detection. [Brief description of the drawings]
[0039] Here, the drawings provide a further understanding of the present disclosure and constitute a part of this application, and the schematic embodiments of the present disclosure and the description thereof are for interpreting the present disclosure without undue limitation to the present disclosure. [Figure 1] 1 is a flowchart of a preferred method for automatically locating an inattentive region according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a schematic diagram of a preferred predetermined abnormal operating region according to an embodiment of the present disclosure. [Diagram 3] FIG. 2 is a schematic diagram of a preferred inattentive region localization according to an embodiment of the present disclosure. [Figure 4] FIG. 1 is a schematic diagram of a preferred automatic inattentive area location device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0040] In order to allow those skilled in the art to better understand the solution of the present disclosure, the following clearly and completely describes the technical solutions of the embodiments of the present disclosure in combination with the drawings of the embodiments of the present disclosure, obviously, the described embodiments are not all the embodiments, but only some embodiments of the present disclosure, based on the embodiments of the present disclosure, on the premise that those skilled in the art do not make any inventive efforts, all other embodiments obtained fall within the protection scope of the present disclosure.
[0041] Here, the terms "first", "second", etc. in the specification, claims and the above drawings of the present disclosure do not describe a particular order or sequence, but are intended to distinguish between similar objects. Here, where appropriate, the data so used are interchangeable, and the embodiments of the present disclosure described herein may be performed in an order other than that shown or described herein. Also, the terms "comprise", "comprise" and any variations thereof are intended to include a non-exclusive inclusion, e.g., a process, method, system, product or apparatus comprising a series of steps or units is not limited to those steps or units expressly recited, and further includes elements not expressly recited or inherent in such process, method, product or equipment.
[0042] The present disclosure is applicable to various types of transportation means (such as automobiles, buses, motorcycles, airplanes, trains, etc.), and in the schematic description of the present embodiment taking a vehicle as an example, the detection of vehicle inattentive regions and driver inattentive states is realized. The types of vehicles include, but are not limited to, cars, trucks, sports cars, SUVs, and MINIs. The present disclosure automatically locates inattentive regions in various parking spaces and regions, and analyzes whether the driver is in an inattentive state based on the located inattentive regions, and performs tracking processing for different drivers and driving states, which improves the accuracy of inattentive detection and effectively reduces false detection compared with the fixed threshold method. The present disclosure self-adaptively adjusts the inattentive region to avoid false detection of inattentiveness due to changes in driving posture or person. The present disclosure will be described in detail below in combination with each embodiment.
[0043] Example 1 According to an embodiment of the present disclosure, there is provided an embodiment of a method for automatically locating an inattentive area, in which the steps illustrated in the flowcharts of the drawings are performed, for example, on a computer system as a set of computer-executable instructions, and although the flowcharts show a logical order, in some cases the steps shown or described may be performed in an order different from that shown here.
[0044] FIG. 1 is a flow chart of a preferred method for automatically locating an inattentive region according to an embodiment of the present disclosure. As shown in FIG. 1, the method includes the following steps: Step S102: Capture a plurality of face images of a driver currently in a vehicle within a predetermined time period; Step S104: Combine multiple facial images to determine the driver's normal driving angle in the current vehicle; Step S106: Locating the driver's non-inattentive region and inattentive region in the current vehicle according to the normal driving angle and the predetermined critical inattentive deviation angle of the current vehicle.
[0045] According to the above steps, a plurality of face images of the driver in the current vehicle within a predetermined time period are captured, the plurality of face images are combined to determine the normal driving angle of the driver in the current vehicle, and the non-inattentive area and inattentive area of the driver in the current vehicle are located according to the normal driving angle and the predetermined critical inattentive deviation angle of the current vehicle. In this embodiment, the plurality of face images of the driver in the current vehicle are analyzed to locate the non-inattentive area and inattentive area of the automatic driver in the current vehicle, and the tracking process is performed for different driver individuals and driving states, thereby improving the accuracy of locating the inattentive area and further improving the accuracy of detecting the inattentive state, solving the technical problem in the related art that the inattentive area changes due to the change of driving posture or person, and the inattentive detection still uses a fixed inattentive area, which leads to erroneous detection.
[0046] The following describes in detail the embodiments of the present disclosure by combining the above implementation steps.
[0047] Step S102: A plurality of facial images of the driver currently inside the vehicle within a predetermined time period are captured.
[0048] In order to accurately locate the inattentive area, a specific deflection area (area shape and area size) of the current vehicle is combined, and the driving attributes of the driver (the driver's physique and driving angle) are taken into consideration in real time, for example, if the driver's physique or height is different, the located inattentive area is changed. A photographing module installed in the vehicle captures multiple facial images of the driver within a specific time period, and real-time information on the accurately located inattentive area is restored from the multiple facial images.
[0049] The predetermined time period in this embodiment is preset, and the duration of the predetermined time period is related to the actual detection accuracy requirements, for example, within 1 minute, within 30 seconds. In addition, the photographing module captures the video stream, and in this application, performs slide processing on the cover frame of the predetermined time period, and after processing the current frame, inputs the next frame, removes the first frame, updates the image set, and then processes the image set again, thereby real-time and automatic orientation.
[0050] In this embodiment, at least one photographing module is provided in the vehicle so as to be adjacent to the vehicle driving area, and the specific mounting position of the photographing module is not limited, and it is preferable to capture an image including the face of the driver. The type of the photographing module includes, but is not limited to, a camera, a depth camera, an infrared camera, etc., and the image type of the captured face image includes, but is not limited to, a normal RGB image, a depth image, a thermal imaging, etc., and this embodiment will be described briefly by taking a normal RGB image as an example.
[0051] Step S104: Combine the multiple facial images to determine the normal driving angle of the driver in the current vehicle.
[0052] Preferably, the step of combining multiple facial images to determine the normal driving angle of the driver in the current vehicle includes the steps of combining non-normal driving information to determine the driver's non-normal driving state, removing images corresponding to the non-normal driving state from all facial images, and obtaining a normal driving image set; and calculating and updating the normal driving angle based on the normal driving image set.
[0053] Specifically, the normal driving angle refers to the line of sight angle when the driver is currently concentrating on driving in the vehicle, concentrating on driving means that the driver's line of sight is kept in front, and there is no situation of making a phone call, turning around, or looking at the rearview mirror. Furthermore, the normal driving angle changes with the change of scenario, and when driving on a sunny day, the normal driving angle is kept in front, and the field of vision is large, and when entering a tunnel or driving in the fog, the driver unconsciously lowers his head to focus on the environment in front of him, and the field of vision becomes smaller, and the normal driving angle moves downward from the front position in a sunny day. In this application, the video stream is captured in real time, and the slide processing is performed on the captured video stream in real time to ensure the real-time update of the normal driving angle information. In addition, in actual cases, the image set captured within a certain time period is not in a state corresponding to the state of the driver concentrating on driving, and in this application, the image corresponding to the non-normal driving state in all face images is deleted to obtain the normal driving image set, and the normal driving angle for a long time is statistically updated based on the normal driving image set.
[0054] In addition, the abnormal driving information includes at least one of low vehicle speed, triggering of steering signal, inattentiveness, and grip strength. Hereinafter, a method for determining the abnormal driving state of the driver by combining each abnormal driving information will be described.
[0055] Preferably, the step of combining the low vehicle speed to determine the driver's abnormal driving state includes the steps of acquiring a vehicle speed of the current vehicle, and determining that the driver is in an abnormal driving state if the vehicle speed is lower than a predetermined speed threshold.
[0056] In this embodiment, generally, in the scenarios such as starting stairs and roadside parking, the vehicle drives at a low speed, looks around the environment, and accurately judges that the stairs do not belong to normal driving stairs. In this application, the vehicle speed is compared with a predetermined speed threshold to judge whether it is in a low-speed driving state, and the predetermined speed threshold is preset, and the specific setting of the predetermined speed threshold can be determined according to the actual user needs. For example, the predetermined speed threshold is set to 30km / h, and if the current vehicle speed is >30km / h, it is considered to be in a normal vehicle speed driving state, and if the vehicle speed is <30km / h, it is considered that the vehicle speed is in a low-speed driving state and the driver is in an abnormal driving state, and further, the frame corresponding to the abnormal driving stairs is removed from the image set.
[0057] Preferably, the step of combining the trigger of the steering signal to determine the non-normal driving state of the driver includes the steps of: capturing a signal trigger state of the steering signal of the current vehicle; determining that the driver is in a normal driving state if the signal trigger state indicates that the steering signal has not been triggered; and determining that the vehicle is currently in a cornering state and the driver is in an non-normal driving state if the signal trigger state indicates that the steering signal has been triggered.
[0058] When steering or turning, a steering signal is initiated, and the driver looks around the surrounding environment to make an accurate judgment. In this application, the judgment of the driving state is realized by detecting the trigger state of the steering signal, when the steering signal is not triggered, the driver is in a normal driving state, when the steering signal is triggered, the vehicle is in a cornering state, and the frame corresponding to the abnormal driving step is removed from the image set.
[0059] Preferably, the step of combining the inattentive bias to determine the driver's abnormal driving state includes the steps of capturing the driver's face and gaze angle, collecting statistics on the period during which the driver's face and gaze angle are in a predetermined abnormal driving area, and determining that the driver is in an abnormal driving state if the period during which the driver's face and gaze angle are in a predetermined abnormal driving area reaches a first period threshold.
[0060] In this embodiment, the range of the inattentive driving area is equal to or larger than the predetermined abnormal driving area, and the predetermined abnormal driving area is set by the user to indicate that the driver is clearly in the inattentive driving area.
[0061] 2 is a schematic diagram of a preferred predetermined abnormal driving area according to an embodiment of the present disclosure, as shown in FIG. 2, the area excluding the inattentive area is the non-inattentive area, and the area excluding the predetermined normal driving area is the predetermined abnormal driving area, and the predetermined abnormal driving area is a roughly positioned area compared with the inattentive area that requires accurate automatic location. If the gaze angle falls into the area, it indicates that the driver is obviously in the inattentive driving area, for example, when the driver is driving, the gaze is attracted to a roadside signboard for a long time, and is in the predetermined abnormal driving area for a long time, it is determined that the driver is in an abnormal driving state, and further, the frame corresponding to the abnormal driving state is removed from the image set.
[0062] In addition, the step of combining the grip force to determine the driver's abnormal driving state includes the steps of capturing the driver's steering wheel grip force, and determining that the driver is in an abnormal driving state if the steering wheel grip force is lower than a predetermined grip force threshold.
[0063] In actual cases, when the driver is in other distracted states such as fatigue driving, the grip force of the steering wheel will be small. Based on the above cases, the embodiment of the present disclosure obtains the grip force value by a sensor, and combines the grip force to determine the abnormal driving state of the driver, the grip force threshold of the embodiment is pre-set self-adaptively according to the vehicle type of each vehicle, and when the grip force of the steering wheel is lower than the predetermined grip force threshold, it is determined that the driver is in an abnormal driving state, and further, the frame corresponding to the abnormal driving state is removed from the image set.
[0064] In the embodiments of the present application, there is no limitation on any combination of types included in the above non-normal driving information, and there is no limitation on the priority order of types included in the non-normal driving information when selecting an image set.
[0065] Preferably, the step of calculating and updating the normal driving angle based on the normal driving image set includes the steps of: outputting normal face and gaze angle values corresponding to each image in the normal driving image set by a face angle and gaze angle model; and calculating all normal face and gaze angle values to update the normal driving angle.
[0066] After capturing a set of normal driving images in the vehicle, each image is analyzed to determine the normal face and gaze angle value corresponding to each image, and the normal driving angle is updated according to all the face and gaze angle values during normal driving. In this embodiment, the image is input into the face angle and gaze angle model to obtain the output face and gaze angle output value. The present disclosure does not limit the form and type of the face angle and gaze angle model, and may adopt a traditional geometric model or a neural network model. In this embodiment, the normal driving angle is updated by stating for a long time, for example, the face and gaze angle of the driver during normal driving in the first 60s are statistically calculated and the average value is taken and updated.
[0067] As a preferred embodiment of this embodiment, before combining the multiple facial images to determine the normal driving angle of the driver in the current vehicle, the method further includes a step of initializing the normal driving angle, including a step of initializing the normal driving angle using a default value, or a step of initializing the normal driving angle using a first gaze angle when the driver gazes at a first mark point.
[0068] The first mark point in this embodiment may be a single point or an average value of multiple points. For example, the first mark point may be a point directly in front of the windshield of the current vehicle, or the average value of multiple arbitrary points included in a specific area of the windshield may be the first mark point. By initializing the normal driving angle, the automatic inattentive region quickly and smoothly enters the driving mode in which the normal driving angle is updated, and does not consume a large amount of time and resources because the initial data has extreme deviations, and the error of the initial calculation value of the normal driving angle is too large, and it does not return to normal calculation again.
[0069] Step S106: Locating the driver's non-inattentive region and inattentive region in the current vehicle according to the normal driving angle and the predetermined critical inattentive deviation angle of the current vehicle.
[0070] In addition, the step of pre-determining the critical inattentive deviation angle of the current vehicle includes the steps of locating a non-inattentive marking area and an inattentive marking area inside the current vehicle based on a predetermined region of interest, where the non-inattentive marking area includes a normal gaze sign point and the inattentive area includes at least a boundary sign point; capturing images of multiple drivers heading toward the normal gaze sign points and the boundary sign points, respectively, to obtain normal gaze images and inattentive gaze images; and analyzing the normal gaze images and the inattentive gaze images to obtain a critical inattentive deviation angle of the current vehicle inattentive area.
[0071] In this embodiment, the step of locating the non-inattentive marking area and the inattentive marking area inside the current vehicle based on the predetermined area of interest includes the steps of representing the predetermined area of interest as the non-inattentive marking area inside the current vehicle, determining a center point of the non-inattentive marking area to obtain a normal gaze marking point, and determining a plurality of boundaries of the non-inattentive marking area and determining an inattentive marking area outside the non-inattentive marking area with each boundary as a side, wherein any point on the boundary is represented as a boundary marking point.
[0072] FIG. 3 is a schematic diagram of a suitable inattentive region location according to an embodiment of the present disclosure. As shown in FIG. 3, an area of interest (for example, a marking frame located above the steering wheel in FIG. 3) is divided from an image of the driving region in the vehicle, and the area is a non-inattentive marking region. The present application does not limit the shape of the area of interest, which may be a circle, a triangle, a rectangle, etc., and is generally set according to the attributes of the vehicle at the time of factory shipment, and a rectangle is taken as an example in FIG. 3. A marker position 1 is placed in the non-inattentive marking region, and the marker position 1 is the center point in the region, that is, the normal gaze marker point. A number of boundaries of the non-inattentive marking region are determined, and any point on the boundary is represented as a boundary marker point. In FIG. 3, marker positions 2, 3, 4, and 5 are placed at the four boundaries of the non-inattentive marking region, namely, the top, bottom, left, and right, respectively, and the area excluding the boundary positions is the inattentive marking region. Specifically, position 1 is the middle of the windshield, position 2 is the top edge of the windshield, position 3 is the right edge of the rearview mirror, position 4 is the middle of the steering wheel, and position 5 is the left rearview mirror.
[0073] Preferably, the step of analyzing the normal gaze image and each inattentive gaze image to obtain the critical inattentive deviation angle of the current vehicle inattentive region includes the steps of: analyzing the normal gaze image, determining the gaze angle at the normal gaze sign point, and obtaining a first normal driving angle based on the distribution of the gaze angle at the normal gaze sign point; analyzing all inattentive gaze images to obtain the distribution of the critical inattentive driving angle of each inattentive region, and calculating the average value of the critical inattentive driving angle of each inattentive region based on the distribution of the critical inattentive driving angle of each inattentive region; and calculating the difference value between the first normal driving angle and the average critical inattentive driving angle to obtain all the current vehicle critical inattentive deviation angles.
[0074] Taking FIG. 3 as an example, in this embodiment, multiple images of the driver facing sign positions 1-5 are captured, and the images are input into the face angle and gaze angle model obtained by pre-training, and face and gaze angle output values are output. Specifically, based on the image set captured by gaze sign position 1, the distribution of gaze angles when gazing at the normal gaze sign point is determined, and the average value is calculated to obtain Mean_A1, i.e., the first normal angle; similarly, the average values Mean_A2, Mean_A3...Mean_A5 of the critical inattentive driving angles are determined for the image set captured by gaze sign positions 2-5, and the difference values between the first normal driving angle and the average value of the critical inattentive driving angle are calculated according to the yaw and pitch directions, respectively, to obtain all the current vehicle critical inattentive deviation angles. For example, the critical inattentive deviation angle at sign position 2 is calculated according to the following formula: Yaw_A2_1=Yaw(Mean_A2)― Yaw(Mean_A1); Pitch_A2_1=Pitch(Mean_A2)―Pitch(Mean_A1).
[0075] According to different vehicles or inattentive regions, the inattentive deflection angle for capturing face and gaze is set, which avoids re-acquiring data training model and achieves good applicability.
[0076] In this embodiment, the average angle of each driver toward the normal gaze sign point and the boundary sign point is calculated, and the difference between the first normal driving angle and the average critical inattentive driving angle is calculated to obtain the critical inattentive deviation angles of all the current vehicles. According to the inattentive deviation angle and the normal driving angle of the driver, the non-inattentive area and inattentive area of the driver in the current vehicle are located.
[0077] Preferably, the step of locating the non-inattentive area and the inattentive area in the current vehicle based on the normal driving angle and the predetermined critical inattentive deviation angle of the current vehicle includes the steps of adding the critical inattentive deviation angle of the current vehicle based on the normal driving angle and obtaining a critical position of the inattentive area boundary, and locating the area included in the critical position of the inattentive area boundary as the non-inattentive area, and locating the area excluding the area included in the critical position of the inattentive area boundary as the inattentive area.
[0078] After locating the non-inattentive area and inattentive area of the driver currently in the vehicle, the driver's long-term inattentive state is output, and for example, if the driver is in the inattentive area for 5 seconds continuously, the driver is in an inattentive driving state, otherwise, the driver is in a normal driving state, and when the vehicle speed reaches a threshold value or when a steering signal starts, the driver is considered to be in a non-inattentive state. When it is confirmed that the driver is inattentive by detecting whether the driver is inattentive, presentation information (e.g., audio presentation, warning sound) is transmitted in a timely manner to reduce the probability of the driver having an accident and improve the safety of vehicle driving.
[0079] In the embodiment of the present disclosure, a multi-information integration solution is used to filter out abnormal driving states during driving and avoid false detection; the embodiment of the present disclosure further adopts automatic location to perform tracking processing for different drivers and driving states. Compared with the fixed threshold location method, the present application improves the accuracy of inattentive location and effectively reduces false detection.
[0080] Hereinafter, the present disclosure will be described in combination with other preferred embodiments.
[0081] Example 2 This embodiment provides an automatic location device for determining an inattentive area, and each unit included in the automatic location device corresponds to each implementation step in the first embodiment.
[0082] FIG. 4 is a schematic diagram of a preferred automatic location device for determining an inattentive region according to an embodiment of the present disclosure. As shown in FIG. 4, the automatic location device: A capture unit 41 arranged to capture a number of facial images of the driver currently included in the vehicle within a given time period. a determining unit 43 arranged to combine a plurality of face images to determine a normal driving angle of the driver in the current vehicle; and a locating unit 45 arranged to locate the driver's non-inattentive and inattentive regions within the current vehicle based on the normal driving angle and a predetermined current vehicle critical inattentive deviation angle.
[0083] In the above-mentioned automatic inattentive region location device, the capture unit 41 captures multiple face images of the driver currently in the vehicle within a predetermined time period, the determination unit 43 combines the multiple face images to determine the normal driving angle of the driver in the current vehicle, and the location unit 45 locates the non-inattentive region and inattentive region of the driver in the current vehicle according to the normal driving angle and the predetermined critical inattentive deviation angle of the current vehicle. In this embodiment, the multiple face images of the driver in the current vehicle are analyzed to locate the non-inattentive region and inattentive region of the automatic driver in the current vehicle, and the tracking process is performed for different driver individuals and driving states, thereby improving the accuracy of locating the inattentive region and further improving the accuracy of detecting the inattentive state, solving the technical problem in the related art that the inattentive region changes due to driving posture or person change, and the inattentive detection still uses a fixed inattentive region, resulting in erroneous detection.
[0084] Preferably, the determination unit includes: a first determination module, which is arranged to combine the non-normal driving information to determine a non-normal driving state of the driver, remove images corresponding to the non-normal driving state from all face images, and obtain a normal driving image set; and an update module, which is arranged to statistically update a normal driving angle based on the normal driving image set.
[0085] Preferably, the method further includes an initialization unit configured to initialize the normal driving angle before combining the multiple facial images to determine the normal driving angle of the driver in the current vehicle, and the initialization unit further includes a first initialization module configured to initialize the normal driving angle using a default value, or a second initialization module configured to initialize the normal driving angle using a first gaze angle when the driver gazes at the first mark point.
[0086] Preferably, the abnormal driving information includes at least one of low vehicle speed, triggering of steering signals, inattentive driving, and grip strength.
[0087] Preferably, the first determination module includes a first capture sub-module configured to capture a vehicle driving speed of the current vehicle, and a first determination sub-module configured to determine that the driver is in an abnormal driving state if the vehicle driving speed is lower than a predetermined speed threshold.
[0088] Preferably, the first determination module includes a second capture sub-module, arranged to capture a signal trigger state of a steering signal of the current vehicle, a second determination sub-module, arranged to determine that the driver is in a normal driving state if the signal trigger state indicates that the steering signal has not been triggered, and a third determination sub-module, arranged to determine that the vehicle is currently in a cornering state and that the driver is in a non-normal driving state if the signal trigger state indicates that the steering signal has been triggered.
[0089] Preferably, the first determination module includes a third capture sub-module configured to capture the driver's face and gaze angle, a first statistics sub-module configured to collect statistics on the period during which the driver's face and gaze angle are in a predetermined abnormal driving area, and a fourth determination sub-module configured to determine that the driver is in an abnormal driving state if the period during which the driver's face and gaze angle are in a predetermined abnormal driving area reaches a first period threshold.
[0090] Preferably, the first determination module includes a fourth capture sub-module arranged to capture the driver's steering wheel grip force, and a fifth determination sub-module arranged to determine that the driver is in an abnormal driving state if the steering wheel grip force is lower than a predetermined grip force threshold.
[0091] Preferably, the update module includes an output sub-module configured to output, for each image in the normal driving image set, normal face and gaze angle values corresponding to each image according to the face angle and gaze angle model, and a second statistics sub-module configured to collect statistics of all normal face and gaze angle values and update the normal driving angle.
[0092] Preferably, the automatic location device for the inattentive area includes: an area location module arranged to locate a non-inattentive marking area and an inattentive marking area inside the current vehicle based on a predetermined area of interest, where the non-inattentive marking area includes a normal gaze sign point and the inattentive area includes at least a boundary sign point; an image capture module arranged to capture images of multiple drivers heading toward the normal gaze sign points and the boundary sign points, respectively, to obtain normal gaze images and inattentive gaze images; and an image analysis module arranged to analyze the normal gaze images and the inattentive gaze images to obtain a critical inattentive deviation angle for the current vehicle inattentive area.
[0093] Preferably, the area location module includes a sixth determination sub-module arranged to represent a predetermined area of interest as a non-inattentive marking area inside the current vehicle, a seventh determination sub-module arranged to determine a center point of the non-inattentive marking area to obtain a normal gaze marking point, and an eighth determination sub-module arranged to determine a plurality of boundaries of the non-inattentive marking area and determine an inattentive marking area outside the non-inattentive marking area with each boundary as a side, wherein any point on the boundary is represented as a boundary marking point.
[0094] Preferably, the image analysis module includes: an analysis sub-module arranged to analyze the normal gaze image, determine a gaze angle for gazing at the normal gaze sign point, and obtain a first normal driving angle based on a distribution of the gaze angles for gazing at the normal gaze sign point; a first calculation sub-module arranged to analyze all the inattentive gaze images to obtain a distribution of the critical inattentive driving angle of the inattentive region, and calculate an average value of the critical inattentive driving angle of the inattentive region based on the distribution of the critical inattentive driving angle of the inattentive region; and a second calculation sub-module arranged to calculate a difference value between the first normal driving angle and the average critical inattentive driving angle to obtain all current vehicle critical inattentive deviation angles.
[0095] Preferably, the location unit includes a first location module arranged to add a current vehicle critical inattentive deviation angle based on the normal driving angle and obtain a critical position of the inattentive area boundary, and a second location module arranged to location an area included in the critical position of the inattentive area boundary to a non-inattentive area, and to location an area excluding the area included in the critical position of the inattentive area boundary to an inattentive area.
[0096] The above-mentioned automatic location device for side-gaze areas further includes a processor and a memory, and the above-mentioned capture unit 41, determination unit 43, location unit 45, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.
[0097] The processor includes a kernel, which calls corresponding program units from memory, and one or more kernels are configured to adjust the parameters of the kernel to locate the non-inattentive area and the inattentive area of the driver in the current vehicle according to the normal driving angle and the predetermined critical inattentive deviation angle of the current vehicle.
[0098] The memory may include non-permanent memory in a computer-readable medium, such as random access memory (RAM) and / or non-volatile memory, for example, read only memory (ROM) or flash memory (flash RAM), and the memory may include at least one storage chip.
[0099] According to another aspect of the present disclosure, a road vehicle is further provided, comprising an on-board camera mounted on a windshield at the front of the vehicle and positioned to capture a road image of the road ahead, and an on-board control unit connected to the on-board camera and configured to execute any one of the methods for automatically locating an inattentive area described above.
[0100] According to another aspect of the present disclosure, there is further provided an on-board electronic device, comprising: a processor; and a memory configured to store executable instructions for the processor, the processor being configured to execute the executable instructions to perform any one of the above-mentioned methods for automatically locating an inattentive area.
[0101] According to another aspect of the present disclosure, there is further provided a computer-readable storage medium including a computer program stored therein, the computer program controlling an apparatus in which the computer-readable storage medium is located to execute any one of the above-described automatic location methods for inattentive areas when the apparatus is operated.
[0102] The present application further provides a computer program product, which, when executed on a data processing device, is suitable for performing initialization, the program including the following method steps: capturing a plurality of facial images of a driver currently contained in a vehicle within a predetermined time period; combining the plurality of facial images to determine a normal driving angle of the driver in the current vehicle; and locating a non-inattentive area and an inattentive area of the driver in the current vehicle based on the normal driving angle and a predetermined critical inattentive deviation angle of the current vehicle.
[0103] The numbers of the embodiments of the present disclosure above do not indicate the superiority or inferiority of the embodiments, but are merely for the purpose of description.
[0104] In the above embodiments of the present disclosure, the description of each embodiment has a certain emphasis, and for the parts not described in detail in an embodiment, reference may be made to the relevant descriptions of other embodiments.
[0105] In some embodiments provided by the present application, the disclosed technical contents may be realized in other ways. The above-described device embodiments are merely schematic, and the division of the units is a division of logical functions, and may have other division methods when actually realized, for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not implemented. In addition, the couplings or direct couplings or communication connections between the shown or discussed may be indirect couplings or communication connections through some interfaces, units or modules, and may be electrical or other forms.
[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed among multiple units. According to actual needs, some or all of the units may be selected to realize the purpose of the solution of the embodiment.
[0107] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, each unit may exist physically alone, or two or more units may be integrated into one unit. The integrated units may be realized in the form of hardware or in the form of a software functional unit.
[0108] The integrated unit may be realized in the form of a software functional unit and stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the essence of the technical solution of the present disclosure, or a part having a contribution to the prior art, or all or a part of the technical solution, may be embodied in the form of a software product, and the computer software product is stored in a storage medium and includes some instructions that cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or a part of the steps of the method in each embodiment of the present disclosure. The storage medium includes various media that can store program code, such as a U disk, a read-only memory (ROM), a random access memory (RAM), a portable hard disk, a magnetic disk, or an optical disk, etc.
[0109] The above are only preferred embodiments of the present disclosure, and those skilled in the art may make some improvements and modifications without departing from the principles of the present disclosure, and these improvements and modifications should also be considered as the protection scope of the present disclosure.
Claims
1. A method for automatically locating an aside-looking area, comprising: capturing a plurality of facial images of a driver currently within a vehicle within a predetermined time period; combining the plurality of facial images to determine a normal driving angle for the driver within the current vehicle; and locating non-distracted and inattentive regions of the driver within the current vehicle based on the normal driving angle and the predetermined current vehicle critical inattentive deviation angle.
2. The step of combining the plurality of facial images to determine a normal driving angle for the driver in the current vehicle includes: Combining the abnormal driving information to determine an abnormal driving state of the driver, and removing images corresponding to the abnormal driving state from all face images to obtain a normal driving image set; and updating the normal driving angle based on the set of normal driving images.
3. Before combining the plurality of facial images to determine a normal driving angle for the driver in the current vehicle, the method further includes initializing the normal driving angle; initializing the normal driving angle using a default value; or The method of claim 1 , comprising initializing the normal driving angle using a first gaze angle when the driver gazes at a first mark point.
4. The method of claim 2 , wherein the non-normal driving information includes at least one of a low vehicle speed, a triggered steering signal, distraction, and grip strength.
5. The step of determining an abnormal driving state of the driver by combining a low vehicle speed includes: acquiring a vehicle speed of the current vehicle; and determining that the driver is in an abnormal driving condition if the vehicle speed is below a predetermined speed threshold.
6. The step of combining the steering signal trigger to determine the abnormal driving state of the driver includes: capturing a signal trigger state of the current vehicle steering signal; determining that the driver is in a normal driving condition if the signal triggering condition indicates that the steering signal is not being triggered; and determining that the vehicle is currently in a cornering condition and that the driver is in an abnormal driving condition if the signal trigger condition indicates that the steering signal has been triggered.
7. The step of determining the abnormal driving state of the driver by combining the inattentive bias includes: capturing the driver's face and gaze angle; Counting the period during which the driver's face and line of sight angle are in a predetermined abnormal driving region; and determining that the driver is in an abnormal driving condition if the time period in the abnormal driving region reaches a first time period threshold.
8. The step of determining an abnormal driving state of the driver by combining the grip force includes: capturing the driver's grip force on a steering wheel; and determining that the driver is in an abnormal driving condition when the grip force of the steering wheel is below a predetermined grip force threshold.
9. The step of statistically updating the normal driving angle based on the normal driving image set includes: for each image in the set of normal driving images, outputting normal face and gaze angle values corresponding to each image according to a face angle and gaze angle model; and updating said normal driving angle by stating all said normal face and gaze angle values.
10. The step of predetermining a current vehicle critical sideways deviation angle includes: Locating a non-inattentive marking area and an inattentive marking area inside the current vehicle based on a predetermined region of interest, the non-inattentive marking area including a normal gaze marking point, and the inattentive area including at least a boundary marking point; capturing images of a plurality of drivers heading toward the normal gaze sign point and the boundary sign point, respectively, to obtain normal gaze images and inattentive gaze images; and analyzing the normal gaze image and the inattentive gaze image to obtain a current vehicle inattentive region critical inattentive deviation angle.
11. The step of locating the non-inattentive marking area and the inattentive marking area inside the current vehicle based on a predetermined region of interest includes: representing the predetermined region of interest as a non-inattentive marking region inside the current vehicle; determining a center point of the non-inattentive marking area to obtain the normal gaze marking point; 11. The method of claim 10, comprising the steps of: determining a plurality of boundaries of the non-inattentive marking area, and determining an inattentive marking area outside the non-inattentive marking area with each of the boundaries as a side, wherein any point on the boundary is represented as the boundary landmark point.
12. The step of analyzing the normal gaze image and the inattentive gaze image to obtain the critical inattentive deviation angle of the current vehicle inattentive region includes: Analyzing the normal gaze image to determine a gaze angle at the normal gaze mark point, and obtaining a first normal driving angle according to a distribution of the gaze angles at the normal gaze mark point; Analyzing all the inattentive gaze images to obtain a distribution of a critical inattentive driving angle of an inattentive region, and calculating an average value of the critical inattentive driving angle of the inattentive region according to the distribution of the critical inattentive driving angle of the inattentive region; and calculating a difference value between the first normal driving angle and an average value of the critical inattentive driving angles to obtain all the current vehicle critical inattentive deviation angles.
13. Locating a non-inattentive region and an inattentive region of the driver in the current vehicle based on the normal driving angle and the predetermined critical inattentive deviation angle of the current vehicle, adding the current vehicle critical inattentive deviation angle based on the normal driving angle to obtain a critical position of an inattentive region boundary; 2. The method according to claim 1, further comprising a step of: designating an area included in a critical position of the inattentive area boundary as the non-inattentive area; and designating an area excluding the area included in the critical position of the inattentive area boundary as the inattentive area.
14. An automatic location device for determining an inattentive area, a capture unit arranged to capture a plurality of facial images of a driver currently within the vehicle within a predetermined time period; a determining unit configured to combine the plurality of facial images to determine a normal driving angle of the driver in the current vehicle; a location unit configured to locate non-inattentive and inattentive regions of the driver within the current vehicle based on the normal driving angle and the predetermined current vehicle critical inattentive deviation angle.
15. The decision unit is A first determination module is configured to combine the abnormal driving information to determine an abnormal driving state of the driver, and remove images corresponding to the abnormal driving state from all face images to obtain a normal driving image set; and an update module configured to statistically update the normal driving angle based on the set of normal driving images.
16. The method further includes an initialization unit configured to initialize a normal driving angle before combining the plurality of face images to determine a normal driving angle of the driver in the current vehicle, the initialization unit comprising: a first initialization module configured to initialize the normal driving angle using a default value; or 15. The apparatus of claim 14, further comprising a second initialization module configured to initialize the normal driving angle using a first gaze angle when the driver gazes at a first mark point.
17. The apparatus of claim 15 , wherein the non-normal driving information includes at least one of low vehicle speed, steering signal trigger, distraction, and grip strength.
18. A road vehicle, An on-board camera mounted on the windshield at the front of the vehicle and positioned to capture a road image of the road ahead; A road vehicle including an on-board control unit connected to the on-board camera and executing the method for automatically locating an inattentive area according to any one of claims 1 to 13.
19. An in-vehicle electronic device, A processor; a memory configured to store executable instructions for said processor; The processor is arranged to execute the executable instructions to perform the method for automatically locating an inattentive area according to any one of claims 1 to 13.
20. A computer-readable storage medium including a computer program stored therein, the computer-readable storage medium controlling a device in which the computer-readable storage medium is located so as to execute the method for automatically locating an inattentive area according to any one of claims 1 to 13 when the computer program is operated.
Citation Information
Patent Citations
Dozing-driving operation alarm device
JP1995329598A
Information processing apparatus, driver monitoring system, information processing method, and information processing program
JP2019091255A
