Driver behavior detection method and device based on vehicle body signal

Abstract

The invention relates to the technical field of vehicle-mounted safety, and discloses a driver behavior detection method and device based on a vehicle body signal, and the method comprises the steps: collecting a current vehicle body signal of a driving test vehicle driven by a driver in a driving test; according to the current vehicle body signal, judging whether the current vehicle body signal meets a triggering condition of driving behavior detection based on the current vehicle body signal or not; when it is judged that the triggering condition is met, according to the current vehicle body signal and the corresponding triggering condition, a driving behavior detection operation needing to be triggered currently is determined; and according to the driving behavior detection operation, analyzing the driving behavior of the driver under the current vehicle body signal. Therefore, by adopting an automatic driver behavior detection scheme, the detection efficiency and accuracy of the driving behavior can be improved, the behavior of the driver can be automatically detected in real time, the subjectivity and error of manual intervention are reduced, and the driving safety of the driver can be improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle safety technology, and in particular to a driver behavior detection method and device based on vehicle body signals. Background Art

[0002] In the existing driving behavior monitoring and evaluation system, the scoring and deduction of driving behavior mainly rely on the manual visual observation of the safety officer in the car. The safety officer visually monitors the driver's behavior, such as whether he looks forward, whether he lowers his head to check the gear position when changing gears, and whether he checks the rearview mirror when turning or changing lanes, to determine whether the driver has irregular or unsafe driving behavior.

[0003] However, this manual observation method has many problems in practical applications, such as low efficiency, subjectivity and errors in manual intervention that easily lead to behavioral detection errors, etc., which will seriously affect the driver's driving safety. Therefore, it is particularly important to propose a technical solution for efficiently, automatically and accurately detecting the driver's various driving behaviors. Summary of the invention

[0004] The present invention provides a driver behavior detection method and device based on vehicle body signals. By adopting an automated driver behavior detection scheme, the detection efficiency and accuracy of driving behavior can be improved, and automatic and real-time detection of driving behavior can be achieved, which is beneficial to improving the driving safety of the driver.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a driver behavior detection method based on vehicle body signals, the method comprising:

[0006] Collect the current body signal of the driving test vehicle driven by the driver during the driving test;

[0007] According to the current vehicle body signal, determining whether the current condition of the driving test vehicle satisfies a trigger condition for performing driving behavior detection based on the current vehicle body signal;

[0008] When it is determined that the current condition of the driving vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal, determining the driving behavior detection operation that needs to be triggered currently according to the current vehicle body signal and its corresponding triggering condition;

[0009] According to the driving behavior detection operation, the driving behavior of the driver under the current vehicle body signal is analyzed.

[0010] As an optional implementation, in the first aspect of the present invention, judging whether the current condition of the driving test vehicle satisfies the triggering condition for driving behavior detection based on the current vehicle body signal according to the current vehicle body signal includes:

[0011] Acquire a signal type of the current vehicle body signal, where the signal type includes one of a vehicle speed signal, a gear position signal, a turn signal, a steering wheel position signal, a brake pedal signal, an accelerator pedal signal, and an ignition status signal;

[0012] According to the current vehicle body signal and its signal type, analyzing the degree of change of driving information corresponding to the signal type, the driving information including one of speed information, gear information, turn signal information, steering wheel angle information, pedal state information and driving test vehicle start state information;

[0013] Determining whether the degree of change of the driving information corresponding to the signal type reaches a preset degree of change corresponding to the driving information;

[0014] When it is determined that the degree of change of the driving information corresponding to the signal type reaches a preset degree of change corresponding to the driving information, determining that the current condition of the driving test vehicle meets the triggering condition for performing driving behavior detection based on the current vehicle body signal;

[0015] When it is determined that the degree of change of the driving information corresponding to the signal type has not reached the preset degree of change corresponding to the driving information, it is determined that the current condition of the driving test vehicle does not meet the triggering condition for driving behavior detection based on the current vehicle body signal.

[0016] As an optional implementation, in the first aspect of the present invention, analyzing the degree of change of the driving information corresponding to the signal type according to the current vehicle body signal and its signal type includes:

[0017] According to the signal type of the current vehicle body signal, at least one historical vehicle body signal matching the signal type is screened out from preset historical vehicle body signals, each of the historical vehicle body signals corresponding to a historical collection time;

[0018] Calculating the time difference between the historical collection time corresponding to each of the historical vehicle body signals and the current collection time corresponding to the current vehicle body signal as the signal collection time difference corresponding to each of the historical vehicle body signals;

[0019] Filter out the historical vehicle body signals whose corresponding signal acquisition time difference is less than or equal to the preset time difference from all historical vehicle body signals matching the signal type, as the reference vehicle body signals corresponding to the current vehicle body signal;

[0020] Comparing the current body signal with the reference body signal to obtain body signal difference information of the driving test vehicle;

[0021] The degree of change of the driving information corresponding to the signal type is analyzed according to the vehicle body signal difference information.

[0022] As an optional implementation, in the first aspect of the present invention, analyzing the driving behavior of the driver under the current vehicle body signal according to the driving behavior detection operation includes:

[0023] Determining a target part to be monitored among all parts of the driver according to the driving behavior detection operation;

[0024] Based on the monitoring equipment of the driving test vehicle, monitoring the current position information of the target part of the driver;

[0025] The driving behavior of the driver under the current vehicle body signal is analyzed according to the current position information of the target part.

[0026] As an optional implementation, in the first aspect of the present invention, the driving behavior detection operation includes a visual detection operation for the driver or a gesture detection operation for the driver;

[0027] When the driving behavior detection operation includes a vision detection operation for the driver, the target part includes the eyeball of the driver;

[0028] When the driving behavior detection operation includes a gesture detection operation for the driver, the target part includes a hand of the driver.

[0029] As an optional implementation, in the first aspect of the present invention, when the driving behavior detection operation includes a visual detection operation for the driver, the analyzing the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part includes:

[0030] Acquire the initial position information of the target part contained in the information comparison library corresponding to the driver, wherein the information comparison library is determined based on the body posture feature information of the driver collected by the monitoring device after the driver gets on the vehicle;

[0031] For the current eyeball position information of the eyeball part contained in the current position information of the target part, calculate the eyeball distance between the left eye and the right eye in the eyeball part relative to the monitoring device according to the current eyeball position information;

[0032] Determining the eyeball distance as the horizontal change information of the driver's eyeball in the horizontal direction, and analyzing the horizontal change information to obtain the first movement information of the driver's head;

[0033] For the initial eyeball position information of the eyeball part contained in the current position information of the target part, compare the current eyeball position information with the initial eyeball position information to obtain vertical change information of the eyeball part in the vertical direction, and analyze the vertical change information to obtain second motion information of the driver's head;

[0034] The driving behavior of the driver under the current vehicle body signal is determined according to the first action information and the second action information.

[0035] As an optional implementation, in the first aspect of the present invention, when the driving behavior detection operation includes a gesture detection operation for the driver, the analyzing the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part includes:

[0036] Acquire the device position of the monitoring device and the steering wheel position of the steering wheel of the driving test vehicle, and calculate the first distance information between the monitoring device and the steering wheel according to the device position and the steering wheel position, wherein the monitoring device is arranged above the steering wheel;

[0037] For the current hand position information of the hand included in the current position information of the target part, calculate the second distance information between the monitoring device and the hand according to the current hand position information and the device position;

[0038] The first distance information and the second distance information are compared to obtain distance difference information, and the driving behavior of the driver under the current vehicle body signal is analyzed according to the distance difference information.

[0039] A second aspect of the present invention discloses a driver behavior detection device based on vehicle body signals, the device comprising:

[0040] A collection module is used to collect the current body signal of the driving test vehicle driven by the driver in the driving test;

[0041] A judgment module, used to judge whether the current condition of the driving test vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal according to the current vehicle body signal;

[0042] A determination module, configured to determine a driving behavior detection operation to be triggered according to the current vehicle body signal and its corresponding triggering condition when the determination module determines that the current condition of the driving vehicle satisfies the triggering condition for performing driving behavior detection based on the current vehicle body signal;

[0043] The analysis module is used to analyze the driving behavior of the driver under the current vehicle body signal according to the driving behavior detection operation.

[0044] As an optional implementation, in the second aspect of the present invention, the judgment module judges whether the current condition of the driving test vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal according to the current vehicle body signal, specifically including:

[0045] Acquire a signal type of the current vehicle body signal, where the signal type includes one of a vehicle speed signal, a gear position signal, a turn signal, a steering wheel position signal, a brake pedal signal, an accelerator pedal signal, and an ignition status signal;

[0046] According to the current vehicle body signal and its signal type, analyzing the degree of change of driving information corresponding to the signal type, the driving information including one of speed information, gear information, turn signal information, steering wheel angle information, pedal state information and driving test vehicle start state information;

[0047] Determining whether the degree of change of the driving information corresponding to the signal type reaches a preset degree of change corresponding to the driving information;

[0048] When it is determined that the degree of change of the driving information corresponding to the signal type reaches a preset degree of change corresponding to the driving information, determining that the current condition of the driving test vehicle meets the triggering condition for performing driving behavior detection based on the current vehicle body signal;

[0049] When it is determined that the degree of change of the driving information corresponding to the signal type has not reached the preset degree of change corresponding to the driving information, it is determined that the current condition of the driving test vehicle does not meet the triggering condition for driving behavior detection based on the current vehicle body signal.

[0050] As an optional implementation, in the second aspect of the present invention, the judgment module analyzes the degree of change of the driving information corresponding to the signal type according to the current vehicle body signal and its signal type, specifically including:

[0051] According to the signal type of the current vehicle body signal, at least one historical vehicle body signal matching the signal type is screened out from preset historical vehicle body signals, each of the historical vehicle body signals corresponding to a historical collection time;

[0052] Calculating the time difference between the historical collection time corresponding to each of the historical vehicle body signals and the current collection time corresponding to the current vehicle body signal as the signal collection time difference corresponding to each of the historical vehicle body signals;

[0053] Filter out the historical vehicle body signals whose corresponding signal acquisition time difference is less than or equal to the preset time difference from all historical vehicle body signals matching the signal type, as the reference vehicle body signals corresponding to the current vehicle body signal;

[0054] Comparing the current body signal with the reference body signal to obtain body signal difference information of the driving test vehicle;

[0055] The degree of change of the driving information corresponding to the signal type is analyzed according to the vehicle body signal difference information.

[0056] As an optional implementation, in the second aspect of the present invention, the analysis module analyzes the driving behavior of the driver under the current vehicle body signal according to the driving behavior detection operation, specifically including:

[0057] Determining a target part to be monitored among all parts of the driver according to the driving behavior detection operation;

[0058] Based on the monitoring equipment of the driving test vehicle, monitoring the current position information of the target part of the driver;

[0059] The driving behavior of the driver under the current vehicle body signal is analyzed according to the current position information of the target part.

[0060] As an optional implementation, in the second aspect of the present invention, the driving behavior detection operation includes a visual detection operation for the driver or a gesture detection operation for the driver;

[0061] When the driving behavior detection operation includes a vision detection operation for the driver, the target part includes the eyeball of the driver;

[0062] When the driving behavior detection operation includes a gesture detection operation for the driver, the target part includes a hand of the driver.

[0063] As an optional implementation, in the second aspect of the present invention, when the driving behavior detection operation includes a visual detection operation for the driver, the analysis module analyzes the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part, specifically including:

[0064] Acquire the initial position information of the target part contained in the information comparison library corresponding to the driver, wherein the information comparison library is determined based on the body posture feature information of the driver collected by the monitoring device after the driver gets on the vehicle;

[0065] For the current eyeball position information of the eyeball part contained in the current position information of the target part, calculate the eyeball distance between the left eye and the right eye in the eyeball part relative to the monitoring device according to the current eyeball position information;

[0066] Determining the eyeball distance as the horizontal change information of the driver's eyeball in the horizontal direction, and analyzing the horizontal change information to obtain the first movement information of the driver's head;

[0067] For the initial eyeball position information of the eyeball part contained in the current position information of the target part, compare the current eyeball position information with the initial eyeball position information to obtain vertical change information of the eyeball part in the vertical direction, and analyze the vertical change information to obtain second motion information of the driver's head;

[0068] The driving behavior of the driver under the current vehicle body signal is determined according to the first action information and the second action information.

[0069] As an optional implementation, in the second aspect of the present invention, when the driving behavior detection operation includes a gesture detection operation for the driver, the analysis module analyzes the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part, specifically including:

[0070] Acquire the device position of the monitoring device and the steering wheel position of the steering wheel of the driving test vehicle, and calculate the first distance information between the monitoring device and the steering wheel according to the device position and the steering wheel position, wherein the monitoring device is arranged above the steering wheel;

[0071] For the current hand position information of the hand included in the current position information of the target part, calculate the second distance information between the monitoring device and the hand according to the current hand position information and the device position;

[0072] The first distance information and the second distance information are compared to obtain distance difference information, and the driving behavior of the driver under the current vehicle body signal is analyzed according to the distance difference information.

[0073] The third aspect of the present invention discloses another driver behavior detection device based on vehicle body signals, the device comprising:

[0074] A memory storing executable program code;

[0075] a processor coupled to the memory;

[0076] The processor calls the executable program code stored in the memory to execute the driver behavior detection method based on vehicle body signals disclosed in the first aspect of the present invention.

[0077] The fourth aspect of the present invention discloses a computer storage medium, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the driver behavior detection method based on vehicle body signals disclosed in the first aspect of the present invention.

[0078] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0079] In an embodiment of the present invention, the current body signal of the driving test vehicle driven by the driver in the driving test is collected; according to the current body signal, it is determined whether the current body signal meets the triggering condition for driving behavior detection based on the current body signal; when it is determined that the current condition of the driving vehicle meets the triggering condition for driving behavior detection based on the current body signal, the driving behavior detection operation required to be triggered is determined according to the current body signal and its corresponding triggering condition; according to the driving behavior detection operation, the driving behavior of the driver under the current body signal is analyzed. It can be seen that the present invention can improve the accuracy and efficiency of determining the driving behavior detection operation required to be triggered by adopting an automated driver behavior detection scheme, can improve the detection efficiency and accuracy of the driver's driving behavior based on the driving behavior detection operation, and realize automatic and real-time detection of the driver's behavior, reduce the subjectivity and error of manual intervention, so as to be conducive to quickly and accurately reminding the driver when the driver's behavior is abnormal, and to improve the accuracy of correcting the driver's abnormal driving behavior, and then to improve the driver's driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0081] Figure 1 It is a flow chart of a driver behavior detection method based on vehicle body signals disclosed in an embodiment of the present invention;

[0082] Figure 2 is a flow chart of another driver behavior detection method based on vehicle body signals disclosed in an embodiment of the present invention;

[0083] Figure 3 It is a structural schematic diagram of a driver behavior detection device based on vehicle body signals disclosed in an embodiment of the present invention;

[0084] Figure 4 It is a structural schematic diagram of another driver behavior detection device based on vehicle body signals disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0086] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0087] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0088] The present invention discloses a driver behavior detection method and device based on vehicle body signals. By adopting an automated driver behavior detection scheme, the accuracy and efficiency of determining the driving behavior detection operation that is currently required to be triggered can be improved, and the detection efficiency and accuracy of the driver's driving behavior can be improved based on the driving behavior detection operation. The driver's behavior can be detected automatically and in real time, and the subjectivity and error of manual intervention can be reduced, so that the driver can be reminded quickly and accurately when the driver's behavior is abnormal, and the accuracy of correcting the driver's abnormal driving behavior can be improved, thereby improving the driver's driving safety. The following are detailed descriptions.

[0089] Embodiment 1

[0090] See also Figure 1 , Figure 1is a flow chart of a driver behavior detection method based on vehicle body signals disclosed in an embodiment of the present invention. Figure 1 The driver behavior detection method based on vehicle body signals described above can be applied to a driver behavior detection device based on vehicle body signals, wherein the device may include a detection device or a detection server, wherein the detection server may include a cloud server or a local server, which is not limited in the embodiments of the present invention. Figure 1 As shown, the driver behavior detection method based on vehicle body signals may include the following operations:

[0091] 101. Collect current body signals of the driving test vehicle driven by the driver in the driving test.

[0092] In the embodiment of the present invention, the driver is a candidate in a driving test. Optionally, the current vehicle body signal may be a combination of one or more of the current vehicle speed signal, gear position signal, turn signal, steering wheel position signal, brake pedal signal, accelerator pedal signal and ignition status signal of the driving test vehicle, which is not limited in the embodiment of the present invention.

[0093] 102. Based on the current vehicle body signal, determine whether the current condition of the driving test vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal.

[0094] In an embodiment of the present invention, the trigger condition may be a condition of whether the degree of change of the driving information of the driving test vehicle based on the current vehicle body signal reaches a preset degree of change. Optionally, the trigger condition may include one or more conditions of whether the degree of change of the vehicle speed based on the vehicle speed signal reaches a preset vehicle speed degree (such as: whether the speed of the driving test vehicle is accelerated to a first preset speed threshold, whether the speed of the driving test vehicle is decelerated to a second preset speed threshold, and the first preset speed threshold is greater than the second preset speed threshold), the gear shift information of the driving test vehicle based on the gear position signal is preset gear shift information (such as: whether the gear of the driving test vehicle is switched from P gear to D gear, whether the gear of the driving test vehicle is switched from D gear to R gear), whether the turn signal of the driving test vehicle based on the turn signal signal is activated, whether the steering wheel rotation angle of the driving test vehicle based on the steering wheel position signal reaches a preset angle, whether the brake pedal based on the brake pedal signal is pressed / released, whether the accelerator pedal based on the accelerator pedal signal is pressed / released, and whether the start-up state of the driving test vehicle based on the ignition state signal changes, etc., which are not limited in the embodiment of the present invention.

[0095] In the embodiment of the present invention, when the judgment result of step 102 is yes, that is, when it is judged that the current condition of driving the vehicle meets the trigger condition for driving behavior detection based on the current vehicle body signal, step 103 is triggered to be executed; when the judgment result of step 102 is no, step 101 can be re-executed, or, as Figure 1 As shown, this process can be ended.

[0096] 103. Determine the driving behavior detection operation that needs to be triggered currently according to the current vehicle body signal and its corresponding triggering condition.

[0097] In an embodiment of the present invention, optionally, the driving behavior detection operation that needs to be triggered currently may include a detection operation based on a vehicle speed signal to determine whether the driver lowers his head to check the speedometer or the gear shift area when the driving test vehicle is in an acceleration state or a deceleration state, a detection operation based on a gear signal to determine whether the driver lowers his head to check the gear area when shifting gears, a detection operation based on a turn signal signal to determine whether the driver turns his head to check the rearview mirror when the turn signal is activated, a detection operation based on a steering wheel position signal to determine whether the driver's hands are on the steering wheel when the steering wheel rotation angle reaches a preset angle (reaching the preset angle is used to indicate that the driving test vehicle is turning or changing lanes), a detection operation based on a brake pedal signal to determine whether the driver checks the rearview mirror or the instrument panel when the brake pedal is pressed or released, a detection operation based on a throttle pedal signal to determine whether the driver checks the speedometer or the gear position when the throttle pedal is pressed or released, and a detection operation based on an ignition status signal to determine whether the driver's hands are on the steering wheel when the driving test vehicle is started (ignition on), and one or more combinations of the above detection operations are not limited in the embodiments of the present invention.

[0098] 104. Analyze the driver's driving behavior under the current vehicle body signal according to the driving behavior detection operation.

[0099] In an embodiment of the present invention, specifically, analyzing the driver's driving behavior under the current vehicle body signal according to the driving behavior detection operation may include: according to the driving behavior detection operation, selecting a target monitoring area that matches the driving behavior detection operation from multiple monitoring areas of the monitoring equipment of the driving test vehicle, and based on the monitoring equipment, monitoring the driver's posture change information in the target monitoring area, and analyzing the driver's driving behavior under the current vehicle body signal according to the driver's posture change information. Wherein, each monitoring area has a corresponding monitoring object, and the monitoring correspondence may be the action of a certain part of the driver, or the overall action of the driver, which is not limited in the embodiment of the present invention. In this way, by setting the specific monitoring requirement content that matches the driving behavior detection operation, the monitoring accuracy and efficiency of the driver's monitoring information can be improved, thereby improving the accuracy and efficiency of the analysis of the driver's driving behavior.

[0100] It can be seen that implementation Figure 1The described driver behavior detection method based on vehicle body signals can determine whether the current vehicle body signal meets the triggering conditions for detecting the corresponding driving behavior based on the current vehicle body signal of the driving test vehicle collected by the driver. If so, the driving behavior detection operation that needs to be triggered is determined based on the current vehicle body signal and its corresponding triggering conditions, and then the driving behavior of the driver under the current vehicle body signal is analyzed based on the driving behavior detection operation. By adopting an automated driver behavior detection scheme, the accuracy and efficiency of determining the driving behavior detection operation that needs to be triggered can be improved, and the detection efficiency and accuracy of the driver's driving behavior can be improved based on the driving behavior detection operation, and automatic and real-time detection of the driver's behavior is realized, reducing the subjectivity and errors of manual intervention, which is conducive to quickly and accurately reminding the driver when the driver's behavior is abnormal, and is conducive to improving the accuracy of correcting the driver's abnormal driving behavior, and then is conducive to improving the driver's driving safety.

[0101] In an optional embodiment, the above step 104, analyzing the driving behavior of the driver under the current vehicle body signal according to the driving behavior detection operation, may include:

[0102] According to the driving behavior detection operation, a target part to be monitored among all parts of the driver is determined;

[0103] Based on the monitoring equipment of the driving test vehicle, the current position information of the target part of the driver is monitored;

[0104] According to the current position information of the target part, the driver's driving behavior under the current vehicle body signal is analyzed.

[0105] In an embodiment of the present invention, optionally, the driving behavior detection operation may include a visual detection operation for the driver or a gesture detection operation for the driver. Specifically, when the current body signal is a vehicle speed signal and the behavior detection trigger condition is the acceleration or deceleration of the driving test vehicle, or the current body signal is a gear position signal and the behavior detection trigger condition is the condition of shifting gears, or the current body signal is a turn signal signal and the behavior detection trigger condition is the condition of the turn signal being activated, or the current body signal is a brake pedal signal and the behavior detection trigger condition is the condition of the brake pedal being stepped on or released, or the current body signal is an accelerator pedal signal and the behavior detection trigger condition is the condition of the accelerator pedal being stepped on or released, the driving behavior detection operation may be a visual detection operation for the driver; when the current body signal is a steering wheel position signal and the behavior detection trigger condition is the condition that the steering wheel rotation angle reaches a preset angle, or the current body signal is an ignition status signal and the behavior detection trigger condition is the condition of the driving test vehicle starting, the driving behavior detection operation may be a gesture detection operation for the driver.

[0106] Specifically, when the driving behavior detection operation includes a visual detection operation for the driver, the target part includes the driver's eyeballs; when the driving behavior detection operation includes a gesture detection operation for the driver, the target part includes the driver's hands. Specifically, when the target part includes the driver's head and eyeballs, the driver's driving behavior under the current vehicle body signal is analyzed based on the current position information of the head and the current position information of the eyeballs; when the target part includes the driver's hands, the driver's driving behavior under the current vehicle body signal is analyzed based on the current position information of the hands.

[0107] In an embodiment of the present invention, optionally, the monitoring device may be an image monitoring device (camera) and / or a sensor device, wherein the image monitoring device is used to collect image information of the driver, so that the data processing center analyzes the driver's current position information based on the driver's image information; the sensor device is used to monitor various data of the human body, so that the data processing center analyzes the current position information of various parts of the driver based on the human body data, and the embodiment of the present invention does not limit this.

[0108] It can be seen that this optional embodiment can accurately determine the target part to be monitored among all parts of the driver according to the driving behavior detection operation, which is conducive to improving the accuracy and reliability of determining the target part to be monitored, and based on the monitoring equipment of the driving test vehicle, accurately monitor the current position information of the driver's target part, which is conducive to improving the accuracy and reliability of the current position information of the target part obtained by monitoring, and then analyze the driver's driving behavior under the current vehicle body signal according to the current position information of the target part, which can improve the accuracy and efficiency of the driver's behavior analysis, and can improve the diversity and flexibility of the driver's behavior analysis based on the diversified part position information.

[0109] In this optional embodiment, as an optional implementation, when the driving behavior detection operation includes a visual detection operation for the driver, analyzing the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part may include:

[0110] Obtain the information corresponding to the driver and compare it with the initial position information of the target part contained in the database;

[0111] For the current eyeball position information of the eyeball part included in the current position information of the target part, calculate the eyeball distance between the left eye and the right eye in the eyeball part relative to the monitoring device according to the current eyeball position information;

[0112] Determine the eyeball distance as the horizontal change information of the driver's eyeball in the horizontal direction, and analyze the horizontal change information to obtain the first movement information of the driver's head;

[0113] For the initial eyeball position information of the eyeball part contained in the current position information of the target part, compare the current eyeball position information with the initial eyeball position information to obtain vertical change information of the eyeball part in the vertical direction, and analyze the vertical change information to obtain second motion information of the driver's head;

[0114] The driving behavior of the driver under the current vehicle body signal is determined according to the first action information and the second action information.

[0115] In the embodiment of the present invention, the information comparison library is determined based on the body posture feature information of the driver collected by the monitoring device after the driver gets on the car. For example, in a driving test, the candidate gets on the car and sits down, facing the camera, so that the camera collects the current candidate's body sitting posture feature number, thereby forming the candidate's information comparison library.

[0116] Specifically, when the eyeball distance between the left eye and the right eye relative to the monitoring device represented by the horizontal change information is less than or equal to the preset distance, the first action information of the driver's head is determined to be the action information of the driver turning his head to the left or to the right, and when the eyeball distance is greater than the preset distance, the first action information of the driver's head is determined to be the driver's head not turning. When the vertical change information of the eyeball part in the vertical direction is used to indicate that the current eyeball position information is lower than the initial eyeball position information, the second action information of the driver's head is determined to be the action information of the driver lowering his head, and when the vertical change information of the eyeball part in the vertical direction is used to indicate that the current eyeball position information is higher than the initial eyeball position information, the second action information of the driver's head is determined to be the action information of the driver raising his head.

[0117] Specifically, when the driver's action information includes action information of turning his head left / right, it is determined that the driver's driving behavior includes turning his head to check the rearview mirror or the instrument panel; when the driver's action information includes action information of lowering his head / raising his head, it is determined that the driver's driving behavior includes lowering his head to check the speedometer or the gear shift area.

[0118] It can be seen that this optional implementation manner can, with respect to the current eyeball position information of the eyeball part contained in the current position information of the target part, accurately calculate the eyeball distance between the left eye and the right eye in the eyeball part relative to the monitoring device based on the current eyeball position information, and then automatically determine the eyeball distance as the horizontal change information of the driver's eyeball part in the horizontal direction, which can improve the determination accuracy and efficiency of the position change information of the eyeball part in the horizontal direction, and analyze the horizontal change information to obtain the first movement information of the driver's head, which can improve the analysis accuracy and efficiency of the first movement information of the driver's head, as well as the initial eyeball position information of the eyeball part contained in the current position information of the target part, by comparison The current eye position information and the initial eye position information of the target part are obtained to obtain the vertical change information of the eye part in the vertical direction, which can improve the accuracy and efficiency of determining the position change information of the eye part in the vertical direction. The vertical change information is analyzed to obtain the second motion information of the driver's head, which can improve the analysis accuracy and efficiency of the second motion information of the driver's head, and is beneficial to improve the diversity and flexibility of the determination method of the head motion information through the eye position change information in multiple directions. Then, according to the first motion information and the second motion information, the driving behavior of the driver under the current vehicle body signal is determined, which can improve the analysis accuracy and reliability of the driver's visual behavior based on the diversified head motion information.

[0119] In this optional embodiment, as another optional implementation, when the driving behavior detection operation includes a gesture detection operation for the driver, analyzing the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part may include:

[0120] Obtaining a device position of the monitoring device and a steering wheel position of the driving test vehicle, and calculating first distance information between the monitoring device and the steering wheel according to the device position and the steering wheel position;

[0121] For the current hand position information of the hand included in the current position information of the target part, calculate the second distance information between the monitoring device and the hand according to the current hand position information and the device position;

[0122] The first distance information and the second distance information are compared to obtain distance difference information, and the driving behavior of the driver under the current vehicle body signal is analyzed according to the distance difference information.

[0123] In an embodiment of the present invention, the monitoring device is disposed above the steering wheel. Specifically, the monitoring device may be disposed directly above the steering wheel. Specifically, when the distance difference information is used to indicate that the first distance information is equal to the second distance information, it is determined that the driver's driving behavior includes the driver's hands being placed on the steering wheel; when the distance difference information is used to indicate that the second distance information is less than the first distance information, it is determined that the driver's driving behavior includes the driver's hands not being placed on the steering wheel.

[0124] It can be seen that this optional implementation method can accurately calculate the first distance information between the monitoring device and the steering wheel according to the acquired device position of the monitoring device and the steering wheel position of the driving test vehicle, and for the current hand position information of the hand contained in the current position information of the target part, accurately calculate the second distance information between the monitoring device and the hand according to the current hand position information and the device position, and then compare the first distance information and the second distance information to obtain the distance difference information, which can improve the accuracy of the comparison between the first distance information and the second distance information, and then analyze the driver's driving behavior under the current vehicle body signal according to the distance difference information, which can improve the analysis accuracy and reliability of the driver's gesture behavior.

[0125] Embodiment 2

[0126] See also Figure 2 , Figure 2 is a flow chart of a driver behavior detection method based on vehicle body signals disclosed in an embodiment of the present invention. Figure 2 The driver behavior detection method based on vehicle body signals described above can be applied to a driver behavior detection device based on vehicle body signals, wherein the device may include a detection device or a detection server, wherein the detection server may include a cloud server or a local server, which is not limited in the embodiments of the present invention. Figure 2 As shown, the driver behavior detection method based on vehicle body signals may include the following operations:

[0127] 201. Collect current body signals of the driving test vehicle driven by the driver in the driving test.

[0128] 202. Obtain the signal type of the current vehicle body signal.

[0129] In an embodiment of the present invention, optionally, the signal type may include one of a vehicle speed signal, a gear position signal, a turn signal, a steering wheel position signal, a brake pedal signal, an accelerator pedal signal and an ignition status signal, which is not limited in the embodiment of the present invention.

[0130] 203. Analyze the degree of change of driving information corresponding to the signal type according to the current vehicle body signal and its signal type.

[0131] In an embodiment of the present invention, optionally, the driving information may include one of speed information, gear information, turn signal information, steering wheel angle information, pedal status information and driving test vehicle start-up status information, which is not limited in the embodiment of the present invention.

[0132] 204. Determine whether a change degree of the driving information corresponding to the signal type reaches a preset change degree corresponding to the driving information.

[0133] For example, determine whether the degree of change of the vehicle speed corresponding to the vehicle speed signal type reaches the preset vehicle speed change degree, determine whether the degree of change of the vehicle gear information corresponding to the gear signal type is switching from the first gear to the second gear (for example, switching from P gear to D gear, D gear to R gear, etc.), and determine whether the degree of change of the vehicle turn signal information corresponding to the turn signal signal type is changing from the turn signal being never activated to being activated.

[0134] In an embodiment of the present invention, when the judgment result of step 204 is yes, that is, when it is judged that the degree of change of the driving information corresponding to the signal type reaches the preset degree of change corresponding to the driving information, step 205 is triggered to be executed; when the judgment result of step 204 is no, that is, when it is judged that the degree of change of the driving information corresponding to the signal type has not reached the preset degree of change corresponding to the driving information, step 208 is triggered to be executed.

[0135] 205. Determine whether the current condition of the driving test vehicle satisfies the triggering condition for driving behavior detection based on the current vehicle body signal.

[0136] 206. Determine the driving behavior detection operation that needs to be triggered currently according to the current vehicle body signal and its corresponding triggering condition.

[0137] 207. Analyze the driver's driving behavior under the current vehicle body signal according to the driving behavior detection operation.

[0138] 208. Determine that the current condition of the driving test vehicle does not satisfy the triggering condition for driving behavior detection based on the current vehicle body signal.

[0139] In the embodiment of the present invention, after step 208, the process may be terminated, or, as Figure 2 As shown, step 201 may be re-executed.

[0140] In the embodiment of the present invention, for other descriptions of step 201 to step 208, please refer to the detailed description of step 101 to step 104 in the first embodiment, and the embodiment of the present invention will not be repeated.

[0141] It can be seen that implementation Figure 2The described driver behavior detection method based on vehicle body signals can determine whether the current vehicle body signal meets the triggering conditions for detecting the corresponding driving behavior based on the current vehicle body signal of the driving test vehicle collected by the driver. If so, the driving behavior detection operation that needs to be triggered is determined based on the current vehicle body signal and its corresponding triggering conditions, and then the driving behavior of the driver under the current vehicle body signal is analyzed based on the driving behavior detection operation. By adopting an automated driver behavior detection scheme, the accuracy and efficiency of determining the driving behavior detection operation that needs to be triggered can be improved, and the detection efficiency and accuracy of the driver's driving behavior can be improved based on the driving behavior detection operation, and automatic and real-time detection of the driver's behavior is realized, reducing the subjectivity and errors of manual intervention, which is conducive to quickly and accurately reminding the driver when the driver's behavior is abnormal, and is conducive to improving the accuracy of correcting the driver's abnormal driving behavior, and then is conducive to improving the driver's driving safety. In addition, it is also possible to accurately analyze the degree of change of driving information corresponding to the signal type based on the current vehicle body signal and its signal type, and judge whether the degree of change of driving information corresponding to the signal type is significant enough. If so, it is determined that the current condition of the driving test vehicle meets the trigger condition for driving behavior detection based on the current vehicle body signal, thereby improving the accuracy and reliability of determining the current condition of the vehicle that meets the behavior detection trigger condition. If not, it is determined that the current condition of the driving test vehicle does not meet the trigger condition for driving behavior detection based on the current vehicle body signal, thereby improving the accuracy and reliability of determining the current condition of the vehicle that does not meet the behavior detection trigger condition.

[0142] In an optional embodiment, the above step 203 of analyzing the degree of change of driving information corresponding to the signal type according to the current vehicle body signal and its signal type may include:

[0143] According to the signal type of the current vehicle body signal, at least one historical vehicle body signal matching the signal type is screened out from preset historical vehicle body signals;

[0144] Calculate the time difference between the historical collection time corresponding to each historical vehicle body signal and the current collection time corresponding to the current vehicle body signal as the signal collection time difference corresponding to each historical vehicle body signal;

[0145] Filter out the historical vehicle body signals whose corresponding signal acquisition time difference is less than or equal to the preset time difference from all historical vehicle body signals with matching signal types, and use them as the reference vehicle body signals corresponding to the current vehicle body signal;

[0146] Compare the current body signal with the reference body signal to obtain the body signal difference information of the driving test vehicle;

[0147] According to the vehicle body signal difference information, the degree of change of driving information corresponding to the signal type is analyzed.

[0148] In the embodiment of the present invention, each historical vehicle body signal corresponds to a historical collection moment. Specifically, the moment when the driver gets on the vehicle is taken as the starting moment, and the vehicle body signal corresponding to each subsequent collection moment is collected and recorded. All collection moments before the current collection moment are historical collection moments corresponding to the current collection moment. For example, the moment when the driver gets on the vehicle is recorded as zero seconds, the first moment after getting on the vehicle is recorded as the first second, the second moment after getting on the vehicle is recorded as the second second, and so on. Optionally, the preset time difference can be 2 seconds, or 4 seconds, or any other value that can be set, which is not limited in the embodiment of the present invention.

[0149] It can be seen that this optional embodiment can filter out at least one historical vehicle body signal that matches the signal type from the preset historical vehicle body signals according to the signal type of the current vehicle body signal, which can improve the matching accuracy and matching efficiency between the signal type and the historical vehicle body signal, and automatically calculate the time difference between the historical collection time corresponding to each historical vehicle body signal and the current collection time corresponding to the current vehicle body signal as the signal collection time difference corresponding to each historical vehicle body signal, which can improve the calculation accuracy of the collection time difference between the historical vehicle body signal of the same signal type and the current vehicle body information, and filter out the corresponding historical vehicle body signal whose signal collection time difference is less than or equal to the preset time difference from all historical vehicle body signals that match the signal type as the reference vehicle body signal corresponding to the current vehicle body signal, which can improve the determination accuracy and reliability of the reference vehicle body signal used for comparison with the current vehicle body signal, and then compare the current vehicle body signal with the reference vehicle body signal to obtain the vehicle body signal difference information of the driving test vehicle, and then analyze the degree of change of the driving information corresponding to the signal type according to the vehicle body signal difference information, which can improve the analysis accuracy and reliability of the degree of change of different types of driving information, thereby facilitating the subsequent judgment accuracy of whether the current condition of the driving test vehicle meets the corresponding trigger condition based on the degree of change of the driving information corresponding to the current vehicle body signal.

[0150] Embodiment 3

[0151] See also Figure 3 , Figure 3 : is a schematic diagram of a driver behavior detection device based on vehicle body signals disclosed in an embodiment of the present invention. Figure 3 The driver behavior detection device based on vehicle body signals described may include a detection device or a detection server, wherein the detection server may include a cloud server or a local server, which is not limited in the embodiment of the present invention. Figure 3 As shown, the driver behavior detection device based on vehicle body signals may include:

[0152] The acquisition module 301 is used to acquire the current body signal of the driving test vehicle driven by the driver in the driving test;

[0153] The judgment module 302 is used to judge whether the current condition of the driving test vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal according to the current vehicle body signal;

[0154] The determination module 303 is used to determine the driving behavior detection operation that needs to be triggered currently according to the current vehicle body signal and its corresponding triggering condition when the determination module 302 determines that the current driving condition of the vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal;

[0155] The analysis module 304 is used to analyze the driver's driving behavior under the current vehicle body signal according to the driving behavior detection operation.

[0156] It can be seen that implementation Figure 3 The described driver behavior detection device based on vehicle body signals can determine whether the current vehicle body signal meets the triggering conditions for detecting the corresponding driving behavior based on the current vehicle body signal of the driving test vehicle collected by the driver. If so, the driving behavior detection operation that needs to be triggered is determined based on the current vehicle body signal and its corresponding triggering conditions, and then the driving behavior of the driver under the current vehicle body signal is analyzed based on the driving behavior detection operation. By adopting an automated driver behavior detection scheme, the accuracy and efficiency of determining the driving behavior detection operation that needs to be triggered can be improved, and the detection efficiency and accuracy of the driver's driving behavior can be improved based on the driving behavior detection operation, and automatic and real-time detection of the driver's behavior is realized, reducing the subjectivity and errors of manual intervention, which is conducive to quickly and accurately reminding the driver when the driver's behavior is abnormal, and is conducive to improving the accuracy of correcting the driver's abnormal driving behavior, and then is conducive to improving the driver's driving safety.

[0157] In an optional embodiment, the judgment module 302 judges whether the current condition of the driving test vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal according to the current vehicle body signal, which may specifically include:

[0158] Get the signal type of the current vehicle body signal, which includes one of the following types: vehicle speed signal, gear position signal, turn signal, steering wheel position signal, brake pedal signal, accelerator pedal signal, and ignition status signal;

[0159] According to the current vehicle body signal and its signal type, analyzing the degree of change of driving information corresponding to the signal type, the driving information includes one of speed information, gear information, turn signal information, steering wheel angle information, pedal status information and driving test vehicle start status information;

[0160] Determining whether the degree of change of the driving information corresponding to the signal type reaches a preset degree of change corresponding to the driving information;

[0161] When it is determined that the degree of change of the driving information corresponding to the signal type reaches a preset degree of change corresponding to the driving information, determining that the current condition of the driving test vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal;

[0162] When it is determined that the degree of change in the driving information corresponding to the signal type has not reached the preset degree of change corresponding to the driving information, it is determined that the current condition of the driving test vehicle does not meet the triggering condition for driving behavior detection based on the current vehicle body signal.

[0163] It can be seen that this optional embodiment can accurately analyze the degree of change of driving information corresponding to the signal type based on the current vehicle body signal and its signal type, and determine whether the degree of change of driving information corresponding to the signal type is significant enough. If so, it is determined that the current condition of the driving test vehicle meets the trigger condition for driving behavior detection based on the current vehicle body signal, thereby improving the accuracy and reliability of determining the current condition of the vehicle that meets the behavior detection trigger condition. If not, it is determined that the current condition of the driving test vehicle does not meet the trigger condition for driving behavior detection based on the current vehicle body signal, thereby improving the accuracy and reliability of determining the current condition of the vehicle that does not meet the behavior detection trigger condition.

[0164] In this optional embodiment, as an optional implementation, the judgment module 302 analyzes the degree of change of the driving information corresponding to the signal type according to the current vehicle body signal and its signal type, which may specifically include:

[0165] According to the signal type of the current vehicle body signal, at least one historical vehicle body signal matching the signal type is selected from preset historical vehicle body signals, each historical vehicle body signal corresponding to a historical collection time;

[0166] Calculate the time difference between the historical collection time corresponding to each historical vehicle body signal and the current collection time corresponding to the current vehicle body signal as the signal collection time difference corresponding to each historical vehicle body signal;

[0167] Filter out the historical vehicle body signals whose corresponding signal acquisition time difference is less than or equal to the preset time difference from all historical vehicle body signals with matching signal types, and use them as the reference vehicle body signals corresponding to the current vehicle body signal;

[0168] Compare the current body signal with the reference body signal to obtain the body signal difference information of the driving test vehicle;

[0169] According to the vehicle body signal difference information, the degree of change of driving information corresponding to the signal type is analyzed.

[0170] It can be seen that this optional implementation method can filter out at least one historical vehicle body signal that matches the signal type from the preset historical vehicle body signals according to the signal type of the current vehicle body signal, which can improve the matching accuracy and matching efficiency between the signal type and the historical vehicle body signal, and automatically calculate the time difference between the historical collection time corresponding to each historical vehicle body signal and the current collection time corresponding to the current vehicle body signal as the signal collection time difference corresponding to each historical vehicle body signal, which can improve the calculation accuracy of the collection time difference between the historical vehicle body signal of the same signal type and the current vehicle body information, and filter out the corresponding historical vehicle body signal whose signal collection time difference is less than or equal to the preset time difference from all historical vehicle body signals that match the signal type as the reference vehicle body signal corresponding to the current vehicle body signal, which can improve the determination accuracy and reliability of the reference vehicle body signal used for comparison with the current vehicle body signal, and then compare the current vehicle body signal with the reference vehicle body signal to obtain the vehicle body signal difference information of the driving test vehicle, and then analyze the degree of change of the driving information corresponding to the signal type according to the vehicle body signal difference information, which can improve the analysis accuracy and reliability of the degree of change of different types of driving information, thereby facilitating the subsequent judgment accuracy of whether the current condition of the driving test vehicle meets the corresponding trigger condition based on the degree of change of the driving information corresponding to the current vehicle body signal.

[0171] In another optional embodiment, the analysis module 304 analyzes the driving behavior of the driver under the current vehicle body signal according to the driving behavior detection operation, and the method may specifically include:

[0172] According to the driving behavior detection operation, a target part to be monitored among all parts of the driver is determined;

[0173] Based on the monitoring equipment of the driving test vehicle, the current position information of the target part of the driver is monitored;

[0174] According to the current position information of the target part, the driver's driving behavior under the current vehicle body signal is analyzed.

[0175] In the embodiment of the present invention, the driving behavior detection operation includes a visual detection operation for the driver or a gesture detection operation for the driver.

[0176] Specifically, when the driving behavior detection operation includes a visual detection operation for the driver, the target part includes the eyeball of the driver;

[0177] When the driving behavior detection operation includes a gesture detection operation for the driver, the target part includes the driver's hand.

[0178] It can be seen that this optional embodiment can accurately determine the target part to be monitored among all parts of the driver according to the driving behavior detection operation, which is conducive to improving the accuracy and reliability of determining the target part to be monitored, and based on the monitoring equipment of the driving test vehicle, accurately monitor the current position information of the driver's target part, which is conducive to improving the accuracy and reliability of the current position information of the target part obtained by monitoring, and then analyze the driver's driving behavior under the current vehicle body signal according to the current position information of the target part, which can improve the accuracy and efficiency of the driver's behavior analysis, and can improve the diversity and flexibility of the driver's behavior analysis based on the diversified part position information.

[0179] In this optional embodiment, as an optional implementation, when the driving behavior detection operation includes a visual detection operation for the driver, the analysis module 304 analyzes the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part, and the method may specifically include:

[0180] Obtaining the initial position information of the target part contained in the information comparison library corresponding to the driver, where the information comparison library is determined based on the body posture feature information of the driver collected by the monitoring device after the driver gets on the vehicle;

[0181] For the current eyeball position information of the eyeball part included in the current position information of the target part, calculate the eyeball distance between the left eye and the right eye in the eyeball part relative to the monitoring device according to the current eyeball position information;

[0182] Determine the eyeball distance as the horizontal change information of the driver's eyeball in the horizontal direction, and analyze the horizontal change information to obtain the first movement information of the driver's head;

[0183] For the initial eyeball position information of the eyeball part contained in the current position information of the target part, compare the current eyeball position information with the initial eyeball position information to obtain vertical change information of the eyeball part in the vertical direction, and analyze the vertical change information to obtain second motion information of the driver's head;

[0184] The driving behavior of the driver under the current vehicle body signal is determined according to the first action information and the second action information.

[0185] It can be seen that this optional implementation manner can, with respect to the current eyeball position information of the eyeball part contained in the current position information of the target part, accurately calculate the eyeball distance between the left eye and the right eye in the eyeball part relative to the monitoring device based on the current eyeball position information, and then automatically determine the eyeball distance as the horizontal change information of the driver's eyeball part in the horizontal direction, which can improve the determination accuracy and efficiency of the position change information of the eyeball part in the horizontal direction, and analyze the horizontal change information to obtain the first movement information of the driver's head, which can improve the analysis accuracy and efficiency of the first movement information of the driver's head, as well as the initial eyeball position information of the eyeball part contained in the current position information of the target part, by comparison The current eye position information and the initial eye position information of the target part are obtained to obtain the vertical change information of the eye part in the vertical direction, which can improve the accuracy and efficiency of determining the position change information of the eye part in the vertical direction. The vertical change information is analyzed to obtain the second motion information of the driver's head, which can improve the analysis accuracy and efficiency of the second motion information of the driver's head, and is beneficial to improve the diversity and flexibility of the determination method of the head motion information through the eye position change information in multiple directions. Then, according to the first motion information and the second motion information, the driving behavior of the driver under the current vehicle body signal is determined, which can improve the analysis accuracy and reliability of the driver's visual behavior based on the diversified head motion information.

[0186] In this optional embodiment, when the driving behavior detection operation includes a gesture detection operation for the driver, the analysis module 304 analyzes the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part, and the method may specifically include:

[0187] Obtaining a device position of the monitoring device and a steering wheel position of the driving test vehicle, and calculating first distance information between the monitoring device and the steering wheel according to the device position and the steering wheel position, wherein the monitoring device is arranged above the steering wheel;

[0188] For the current hand position information of the hand included in the current position information of the target part, calculate the second distance information between the monitoring device and the hand according to the current hand position information and the device position;

[0189] The first distance information and the second distance information are compared to obtain distance difference information, and the driving behavior of the driver under the current vehicle body signal is analyzed according to the distance difference information.

[0190] It can be seen that this optional implementation method can accurately calculate the first distance information between the monitoring device and the steering wheel according to the acquired device position of the monitoring device and the steering wheel position of the driving test vehicle, and for the current hand position information of the hand contained in the current position information of the target part, accurately calculate the second distance information between the monitoring device and the hand according to the current hand position information and the device position, and then compare the first distance information and the second distance information to obtain the distance difference information, which can improve the accuracy of the comparison between the first distance information and the second distance information, and then analyze the driver's driving behavior under the current vehicle body signal according to the distance difference information, which can improve the analysis accuracy and reliability of the driver's gesture behavior.

[0191] Embodiment 4

[0192] See also Figure 4 , Figure 4 FIG. 1 is a schematic diagram of another driver behavior detection device based on vehicle body signals disclosed in an embodiment of the present invention. Figure 4 As shown, the driver behavior detection device based on vehicle body signals may include:

[0193] A memory 401 storing executable program codes;

[0194] a processor 402 coupled to the memory 401;

[0195] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the driver behavior detection method based on the vehicle body signal described in the first embodiment of the present invention or the second embodiment of the present invention.

[0196] Embodiment 5

[0197] An embodiment of the present invention discloses a computer storage medium storing computer instructions. When the computer instructions are called, they are used to execute the steps of the driver behavior detection method based on vehicle body signals described in Embodiment 1 or Embodiment 2 of the present invention.

[0198] Embodiment 6

[0199] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the driver behavior detection method based on vehicle body signals described in Example 1 or Example 2.

[0200] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0201] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0202] Finally, it should be noted that the driver behavior detection method and device based on vehicle body signals disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A driver behavior detection method based on vehicle body signals, characterized in that: The method comprises: Collect the current body signal of the driving test vehicle driven by the driver during the driving test; According to the current vehicle body signal, determining whether the current condition of the driving test vehicle satisfies a trigger condition for performing driving behavior detection based on the current vehicle body signal; When it is determined that the current condition of the driving vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal, determining the driving behavior detection operation that needs to be triggered currently according to the current vehicle body signal and its corresponding triggering condition; According to the driving behavior detection operation, the driving behavior of the driver under the current vehicle body signal is analyzed.

2. The driver behavior detection method based on vehicle body signals according to claim 1, characterized in that: The determining, based on the current vehicle body signal, whether the current condition of the driving test vehicle satisfies a trigger condition for performing driving behavior detection based on the current vehicle body signal includes: Acquire a signal type of the current vehicle body signal, where the signal type includes one of a vehicle speed signal, a gear position signal, a turn signal, a steering wheel position signal, a brake pedal signal, an accelerator pedal signal, and an ignition status signal; According to the current vehicle body signal and its signal type, analyzing the degree of change of driving information corresponding to the signal type, the driving information including one of speed information, gear information, turn signal information, steering wheel angle information, pedal state information and driving test vehicle start state information; Determining whether the degree of change of the driving information corresponding to the signal type reaches a preset degree of change corresponding to the driving information; When it is determined that the degree of change of the driving information corresponding to the signal type reaches a preset degree of change corresponding to the driving information, determining that the current condition of the driving test vehicle meets the triggering condition for performing driving behavior detection based on the current vehicle body signal; When it is determined that the degree of change of the driving information corresponding to the signal type has not reached the preset degree of change corresponding to the driving information, it is determined that the current condition of the driving test vehicle does not meet the triggering condition for driving behavior detection based on the current vehicle body signal.

3. The driver behavior detection method based on vehicle body signals according to claim 2, characterized in that: The analyzing, based on the current vehicle body signal and its signal type, the degree of change of the driving information corresponding to the signal type includes: According to the signal type of the current vehicle body signal, at least one historical vehicle body signal matching the signal type is screened out from preset historical vehicle body signals, each of the historical vehicle body signals corresponding to a historical collection time; Calculating the time difference between the historical collection time corresponding to each of the historical vehicle body signals and the current collection time corresponding to the current vehicle body signal as the signal collection time difference corresponding to each of the historical vehicle body signals; Filter out the historical vehicle body signals whose corresponding signal acquisition time difference is less than or equal to the preset time difference from all historical vehicle body signals matching the signal type, as the reference vehicle body signals corresponding to the current vehicle body signal; Comparing the current body signal with the reference body signal to obtain body signal difference information of the driving test vehicle; The degree of change of the driving information corresponding to the signal type is analyzed according to the vehicle body signal difference information.

4. The driver behavior detection method based on vehicle body signals according to any one of claims 1 to 3, characterized in that: The step of analyzing the driving behavior of the driver under the current vehicle body signal according to the driving behavior detection operation includes: Determining a target part to be monitored among all parts of the driver according to the driving behavior detection operation; Based on the monitoring equipment of the driving test vehicle, monitoring the current position information of the target part of the driver; The driving behavior of the driver under the current vehicle body signal is analyzed according to the current position information of the target part.

5. The driver behavior detection method based on vehicle body signals according to claim 4 is characterized in that: The driving behavior detection operation includes a visual detection operation for the driver or a gesture detection operation for the driver; When the driving behavior detection operation includes a vision detection operation for the driver, the target part includes the eyeball of the driver; When the driving behavior detection operation includes a gesture detection operation for the driver, the target part includes a hand of the driver.

6. The driver behavior detection method based on vehicle body signals according to claim 5, characterized in that: When the driving behavior detection operation includes a visual detection operation for the driver, the analyzing the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part includes: Acquire the initial position information of the target part contained in the information comparison library corresponding to the driver, wherein the information comparison library is determined based on the body posture feature information of the driver collected by the monitoring device after the driver gets on the vehicle; For the current eyeball position information of the eyeball part contained in the current position information of the target part, calculate the eyeball distance between the left eye and the right eye in the eyeball part relative to the monitoring device according to the current eyeball position information; Determining the eyeball distance as the horizontal change information of the driver's eyeball in the horizontal direction, and analyzing the horizontal change information to obtain the first movement information of the driver's head; For the initial eyeball position information of the eyeball part contained in the current position information of the target part, compare the current eyeball position information with the initial eyeball position information to obtain vertical change information of the eyeball part in the vertical direction, and analyze the vertical change information to obtain second motion information of the driver's head; The driving behavior of the driver under the current vehicle body signal is determined according to the first action information and the second action information.

7. The driver behavior detection method based on vehicle body signals according to claim 5, characterized in that: When the driving behavior detection operation includes a gesture detection operation for the driver, the analyzing the driving behavior of the driver under the current vehicle body signal according to the current position information of the target part includes: Acquire the device position of the monitoring device and the steering wheel position of the steering wheel of the driving test vehicle, and calculate the first distance information between the monitoring device and the steering wheel according to the device position and the steering wheel position, wherein the monitoring device is arranged above the steering wheel; For the current hand position information of the hand included in the current position information of the target part, calculate the second distance information between the monitoring device and the hand according to the current hand position information and the device position; The first distance information and the second distance information are compared to obtain distance difference information, and the driving behavior of the driver under the current vehicle body signal is analyzed according to the distance difference information.

8. A driver behavior detection device based on vehicle body signals, characterized in that: The device comprises: A collection module, used to collect the current body signal of the driving test vehicle driven by the driver in the driving test; A judgment module, used to judge whether the current condition of the driving test vehicle meets the triggering condition for driving behavior detection based on the current vehicle body signal according to the current vehicle body signal; A determination module, configured to determine a driving behavior detection operation to be triggered according to the current vehicle body signal and its corresponding triggering condition when the determination module determines that the current condition of the driving vehicle satisfies the triggering condition for performing driving behavior detection based on the current vehicle body signal; The analysis module is used to analyze the driving behavior of the driver under the current vehicle body signal according to the driving behavior detection operation.

9. A driver behavior detection device based on vehicle body signals, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the driver behavior detection method based on vehicle body signals as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the driver behavior detection method based on vehicle body signals as described in any one of claims 1-7.

Images