Fatigue driving detection method and device, electronic equipment and storage medium

Abstract

The application relates to the technical field of vehicle safe driving, and provides a fatigue driving detection method and device, an electronic device and a storage medium. The method comprises the following steps: acquiring current driving scene feature information, and determining a current monitoring mode according to the driving scene feature information; acquiring a first action frequency of a target driver watching a rearview mirror within monitoring time corresponding to the current monitoring mode; calculating a driving score according to the first action frequency of the target driver watching the rearview mirror; and performing fatigue driving detection on the target driver according to the driving score, a pre-determined initial value and a second action frequency of the driver watching the rearview mirror on a current road section. The method can reduce load demand and power consumption demand, is suitable for mobile terminals such as mobile phones, can effectively utilize the computing power consumption of the mobile terminal, and is simple and easy to implement.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle safe driving, and in particular to a fatigue driving detection method and device, an electronic device and a storage medium. BACKGROUND

[0002] Traffic accidents are one of the serious social problems faced by people. At present, many traffic accidents are caused by dangerous driving habits, behaviors and fatigue driving of drivers. Therefore, how to solve the problem of driver fatigue driving, dangerous driving and unsafe driving has become an important issue.

[0003] In related technologies, there are various driving detection schemes based on eye tracking, blinking and vehicle acceleration analysis. The system is complex and runs slowly. When the above scheme is used in mobile terminals such as mobile phones, the mobile phone cannot meet the demand for computing power and load of the above scheme. SUMMARY

[0004] Therefore, it is necessary to provide a fatigue driving detection method, device, electronic device and storage medium which can reduce the load demand and power consumption demand and is suitable for mobile terminals such as mobile phones.

[0005] The embodiment of the present application provides a fatigue driving detection method, which comprises the following steps:

[0006] obtaining current driving scene feature information, and determining a current monitoring mode according to the driving scene feature information;

[0007] obtaining a first action frequency of a target driver watching a rearview mirror within a monitoring time corresponding to the current monitoring mode;

[0008] calculating a driving score according to the first action frequency of the target driver watching the rearview mirror;

[0009] detecting fatigue driving of the target driver according to the driving score, a predetermined initial value and a second action frequency of the driver watching the rearview mirror on a current road section.

[0010] In one embodiment, the step of determining the current monitoring mode according to the driving scene feature information comprises the following steps:

[0011] when it is detected that the current driving scene feature information meets a preset trigger condition, a first monitoring mode of full-time monitoring is adopted;

[0012] when it is detected that the current driving scene feature information does not meet the trigger condition, a second monitoring mode of monitoring according to a set duty cycle is adopted.

[0013] In one embodiment, the condition includes:

[0014] if the current vehicle speed is greater than a preset speed, it is determined that the condition is met; and / or,

[0015] if the current driving time is greater than a preset time, it is determined that the condition is met; and / or,

[0016] if the current road section is a preset dangerous road section, it is determined that the condition is met; and / or,

[0017] if the current weather is a preset severe weather, it is determined that the condition is met.

[0018] In one embodiment, the fatigue driving detection on the target driver based on the driving score, a predetermined initial value and a second action frequency of the drivers on the current road section checking the rearview mirror includes:

[0019] if the driving score is less than or equal to a preset score, comparing the first action frequency of the target driver checking the rearview mirror with the initial value;

[0020] if the first action frequency of the target driver checking the rearview mirror is less than a product of the initial value and a preset coefficient, it is determined that the target driver is in a fatigue driving state;

[0021] if the driving score is greater than the preset score, obtaining an average value of the second action frequency of the drivers on the current road section checking the rearview mirror;

[0022] if the first action frequency of the target driver checking the rearview mirror is less than a product of the average value and a preset coefficient, it is determined that the target driver is in a fatigue driving state.

[0023] In one embodiment, the method further includes:

[0024] obtaining a preset minimum threshold value and a maximum threshold value, and detecting a third action frequency of the target driver checking the rearview mirror;

[0025] if the third action frequency is less than the minimum threshold value or the third action frequency is greater than the maximum threshold value, generating prompt information for prompting the driver to improve driving habits;

[0026] if the third action frequency is greater than or equal to the minimum threshold value and the third action frequency is less than or equal to the maximum threshold value, the third action frequency is taken as the initial value.

[0027] In an embodiment, the current monitoring mode is a second monitoring mode, and the method further comprises:

[0028] obtaining an average score of driving scores of driving personnel on the current road section;

[0029] if the driving score of the target driving personnel is less than the average score, increasing a duty cycle of the second monitoring mode by a preset value.

[0030] In an embodiment, the calculating of the driving score according to the first action frequency of the target driving personnel watching the rearview mirror comprises:

[0031] determining a target value according to the minimum threshold and the maximum threshold, wherein the target value is less than the maximum threshold and greater than the minimum threshold;

[0032] in a case where the first action frequency is less than or equal to the target value, calculating the driving score according to a difference between the first action frequency and the minimum threshold;

[0033] in a case where the first action frequency is greater than the target value, calculating the driving score according to a difference between the maximum threshold and the first action frequency.

[0034] Embodiments of the present application provide a fatigue driving detection device, the device comprising:

[0035] a determination module configured to obtain current driving scene feature information and determine a current monitoring mode according to the driving scene feature information;

[0036] an obtaining module configured to obtain a first action frequency of a target driving personnel watching a rearview mirror within a monitoring time corresponding to the current monitoring mode;

[0037] a scoring module configured to calculate a driving score according to the first action frequency of the target driving personnel watching the rearview mirror;

[0038] a detection module configured to perform fatigue driving detection on the target driving personnel according to the driving score, a predetermined initial value, and a second action frequency of driving personnel on a current road section watching the rearview mirror.

[0039] Embodiments of the present application provide an electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing steps of a fatigue driving detection method provided by any embodiment of the present application when executing the computer program.

[0040] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the fatigue driving detection method provided by any embodiment of the present application.

[0041] Compared with the prior art, the technical scheme provided by the embodiment of the present application has the following advantages:

[0042] The current driving scene feature information is used to determine the current monitoring mode, the first action frequency of the target driver watching the rearview mirror is obtained in the monitoring time corresponding to the current monitoring mode, then, the driving score is calculated according to the first action frequency of the target driver watching the rearview mirror, so as to detect the fatigue driving of the target driver according to the driving score, the initial value determined in advance and the second action frequency of the driver watching the rearview mirror on the current road section, thereby reducing the load demand and the power consumption demand while ensuring the fatigue driving detection accuracy, being suitable for mobile terminals such as mobile phones, and effectively utilizing the computing power and power consumption of the mobile terminal and being simple and easy to implement. BRIEF DESCRIPTION OF DRAWINGS

[0043] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the application.

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced as follows, and obviously, other drawings can also be obtained by those skilled in the art without creative labor under the premise of the drawings.

[0045] Figure 1 A flowchart of a fatigue driving detection method provided by the embodiment of the present application is shown in the figure.

[0046] Figure 2 A schematic diagram of determining a driving score provided by the embodiment of the present application is shown in the figure.

[0047] Figure 3 A flowchart of determining a current monitoring mode provided by the embodiment of the present application is shown in the figure.

[0048] Figure 4 A structural schematic diagram of a fatigue driving detection device provided by the embodiment of the present application is shown in the figure.

[0049] Figure 5 A structural schematic diagram of an electronic device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0050] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0051] In one embodiment, as shown in Figure 1 a fatigue driving detection method is provided, and the present embodiment takes the method applied to a terminal as an example. It should be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is realized through the interaction of the terminal and the server. In the present embodiment, the method includes the following steps:

[0052] In step 102, current driving scene feature information is acquired, and a current monitoring mode is determined according to the driving scene feature information.

[0053] The method of the present embodiment can be used for fatigue driving detection of a mobile terminal to determine whether a driver is in a fatigue driving state.

[0054] In the present embodiment, multiple monitoring modes and triggering conditions can be set, and a current monitoring mode is determined from the multiple monitoring modes according to driving scene feature information and a preset triggering condition, wherein the multiple monitoring modes can correspond to different duty cycles. Specifically, when the current driving scene feature information meets the preset triggering condition, a first monitoring mode of full-time monitoring is adopted; when the current driving scene feature information does not meet the triggering condition, a second monitoring mode of monitoring according to a set duty cycle is adopted.

[0055] The driving scene feature information includes but is not limited to vehicle speed, driving time, current road section and current weather.

[0056] In step 104, a first action frequency of a target driver watching a rearview mirror is acquired within a monitoring time corresponding to the current monitoring mode.

[0057] In the present embodiment, the monitoring time is determined according to the current monitoring mode, and facial posture information of the target driver is acquired through a collection device within the monitoring time. The number of times the target driver watches the rearview mirror is determined according to the facial posture information, and the first action frequency of the target driver watching the rearview mirror is determined by detecting the number of times the target driver watches the rearview mirror within a certain time. The facial posture information includes, for example, left and right head shaking frequency, angle, field of view and number of times.

[0058] In step 106, a driving score is calculated according to the first action frequency of the target driver watching the rearview mirror.

[0059] In this embodiment, the driving score corresponding to the first action frequency can be determined according to a preset mapping relationship between the action frequency and the driving score. As an example, the first action frequency is directly proportional to the driving score.

[0060] In an embodiment of the present application, a minimum threshold and a maximum threshold are preset, and the target value is determined according to the minimum threshold and the maximum threshold. For example, the target value is the average of the minimum threshold and the maximum threshold.

[0061] Further, in the case where the first action frequency is less than or equal to the target value, the driving score is calculated according to the difference between the first action frequency and the minimum threshold. In the case where the first action frequency is greater than the target value, the driving score is calculated according to the difference between the maximum threshold and the first action frequency. Optionally, in the case where the first action frequency is less than or equal to the target value, the driving score is calculated by the formula L = M1 + (X-A) x K. In the case where the first action frequency is greater than the target value, the driving score is calculated by the formula L = M2 + (B-X) x K. Wherein, L is the driving score, X is the first action frequency, A is the minimum threshold, B is the maximum threshold, M1, M2 and K are preset values. For example, as shown in the table below, the minimum threshold is 1 time / minute, the maximum threshold is 11 times / minute, the target value is 6 times / minute, the first action frequency is 4 times / minute, and the driving score is 50 + (4-1) x 10 = 80. Figure 2

[0062] Step 108, according to the driving score, the initial value determined in advance, and the second action frequency of the driving personnel watching the rearview mirror on the current road section, the target driving personnel is detected for fatigue driving.

[0063] In this embodiment, the initial value is the action frequency of watching the rearview mirror of the target driving personnel detected in the non-fatigue driving state in advance, and the second action frequency is the action frequency of watching the rearview mirror of the driving personnel on the current road section. The acquisition method of the second action frequency can refer to the first action frequency. The action frequency of the driving personnel watching the rearview mirror in the driving process is acquired through the mobile terminal, and the action frequency and the position information are uploaded to the cloud server, so that the second action frequency of other driving personnel on the current road section can be acquired when the target driving personnel is detected for fatigue. Specifically, the first action frequency can be compared with the initial value and the second action frequency respectively according to the comparison between the driving score and the preset score, and the target driving personnel is determined to be in the fatigue driving state when the preset condition is met.

[0064] ​In an embodiment of the present application, in the case that the driving score is less than or equal to a preset score, the first action frequency of the target driver looking at the rearview mirror is compared with an initial value, and if the first action frequency of the target driver looking at the rearview mirror is less than the product of the initial value and a preset coefficient, it is determined that the target driver is in a fatigue driving state. For example, the initial value detected by a certain driver in a non-fatigue driving state is 4 times per minute, and after driving for three hours, the system monitors that the first action frequency of the driver looking at the rearview mirror is 0.5 times per minute. The driving score is lower than 50 points, and the first action frequency is lower than one half of the initial value, so it is determined that the driver is in a fatigue driving state.

[0065] Further, in the case that the driving score is greater than the preset score, the average value of the second action frequency of the driver looking at the rearview mirror on the current road section is obtained, and if the first action frequency of the target driver looking at the rearview mirror is less than the product of the average value and a preset coefficient, it is determined that the target driver is in a fatigue driving state. For example, a certain driver drives on a dangerous road section, the system monitors that the first action frequency of the driver looking at the rearview mirror is 1.5 times per minute, and the driving score is higher than 50 points, and the average value of the second action frequency of other drivers looking at the rearview mirror on the dangerous road section is determined to be 4 times per minute through cloud data, so it is determined that the driver is in a fatigue driving state.

[0066] Optionally, in the case that it is determined that the driver is in a fatigue driving state, voice prompt information can be generated to prompt the driver to rest or pay attention to driving safety, so as to avoid fatigue driving and dangerous driving.

[0067] According to the fatigue driving detection method of the embodiments of the present application, the current driving scene feature information is used to determine the current monitoring mode, the first action frequency of the target driver looking at the rearview mirror is obtained within the monitoring time corresponding to the current monitoring mode, and then the driving score is calculated according to the first action frequency of the target driver looking at the rearview mirror, so as to detect the fatigue driving of the target driver according to the driving score, the initial value determined in advance, and the second action frequency of the driver looking at the rearview mirror on the current road section. Thus, by setting different duty cycles of the monitoring mode, the action frequency of the driver looking at the rearview mirror is monitored, and the cloud data of other drivers looking at the rearview mirror on the current road section and the driving score are used to determine the fatigue driving, so as to reduce the demand for computing power and power consumption, solve the problem that the system complexity and running speed of the fatigue driving detection scheme in the related art are relatively high, and it is difficult to meet the demand for power consumption and load when used in mobile phones and other devices, reduce the load demand while ensuring the fatigue driving detection accuracy, and be suitable for mobile terminals such as mobile phones, effectively utilize the computing power and power consumption of the mobile terminal, and be simple and easy to implement.

[0068] Based on the above embodiments, the determination of the current monitoring mode according to the driving scene feature information is described as follows.

[0069] Figure 3 A flowchart for determining the current monitoring mode provided by the embodiments of the present application is shown in FIG. 3, which includes the following steps. Figure 3

[0070] In step 302, it is detected whether the current driving scene feature information meets the preset triggering condition.

[0071] In the embodiments, the driving scene feature information can include the vehicle speed, the driving time, the current road section, and the current weather.

[0072] In step 304, when it is detected that the current driving scene feature information meets the preset triggering condition, the first monitoring mode of the full-time monitoring is adopted.

[0073] As a possible implementation manner, if it is detected that the current vehicle speed is greater than the preset speed, it is determined that the triggering condition is met. For example, if it is detected that the current vehicle speed is greater than 100 km / h, it is determined that the first monitoring mode of the full-time monitoring is adopted. Optionally, in the driving scene, voice prompt information such as "please watch the left and right rearview mirrors and keep the frequency at about 6 times per minute" is generated.

[0074] As another possible implementation manner, if it is detected that the current driving time is greater than the preset time, it is determined that the triggering condition is met. For example, if it is detected that the current driving time is greater than 3 hours, it is determined that the first monitoring mode of the full-time monitoring is adopted. Optionally, in the driving scene, voice prompt information such as "please rest and watch the left and right rearview mirrors at any time" is generated.

[0075] As another possible implementation manner, the current road section can be determined through the vehicle position information and the preset map data, and if it is detected that the current road section is a preset dangerous road section, it is determined that the triggering condition is met. For example, if it is detected that the current road section belongs to the preset dangerous road section, it is determined that the first monitoring mode of the full-time monitoring is adopted. Optionally, in the driving scene, voice prompt information such as "the road section is a dangerous road section, please keep a certain frequency to watch the left and right rearview mirrors" is generated.

[0076] As another possible implementation manner, if it is detected that the current weather is a preset severe weather, it is determined that the triggering condition is met. For example, if it is detected that the current weather is rain, snow, or hail weather, it is determined that the first monitoring mode of the full-time monitoring is adopted. Optionally, in the driving scene, voice prompt information such as "the weather is extreme, please pay attention to the rearview mirrors at any time" is generated.

[0077] ​It should be noted that the above implementation manners can be implemented alone or in combination to determine whether the trigger condition is met, which is not limited here.

[0078] At step 306, when it is detected that the current driving scene feature information does not meet the trigger condition, a second monitoring mode for monitoring according to a set duty cycle is adopted.

[0079] In this embodiment, the second monitoring mode is for monitoring according to a set duty cycle. For example, the duty cycle is set to 1 / 10, that is, in one hour, 6 minutes are the monitoring time, and the action frequency of the driver for watching the rearview mirror is monitored in the monitoring time.

[0080] Optionally, in the case that the current monitoring mode is the second monitoring mode, an average score of driving scores of drivers on the current road section can be obtained, wherein the driving score of the driver in the driving process is calculated by the mobile terminal, and the driving score is uploaded to the cloud server, so that the driving scores of other drivers on the current road section can be obtained when the fatigue of the target driver is detected. Further, if the driving score of the target driver is less than the average score, the duty cycle of the second monitoring mode is increased by a preset value. For example, in the case that the driving score of the target driver is greater than or equal to the average score, the current duty cycle is maintained, and in the case that the driving score is less than the average score, the duty cycle is increased by 1 / 10, and a voice prompt "Please improve driving habits and pay attention to watching the left and right rearview mirrors" is given. Thus, the duty cycle of the second monitoring mode can be gradually increased according to the driving score.

[0081] In the embodiments of the present application, the first monitoring mode of full-time monitoring and the second monitoring mode of duty cycle monitoring are set, and the current monitoring mode is determined based on the scene, so as to reduce the system power consumption and workload, reduce the demand for computing power and power consumption, and be suitable for mobile terminals.

[0082] Based on the above embodiments, the initialization setting is described below.

[0083] In an embodiment of the present application, before obtaining the current driving scene, the fatigue detection method further includes the following steps:

[0084] The third action frequency of the target driver for watching the rearview mirror is detected. If the third action frequency is less than the minimum threshold value or the third action frequency is greater than the maximum threshold value, prompt information for prompting the driver to improve driving habits is generated. If the third action frequency is greater than or equal to the minimum threshold value and the third action frequency is less than or equal to the maximum threshold value, the third action frequency is taken as the initial value.

[0085] As an example, the mobile terminal is aimed at the face and eyes of the driver, and the driver is prompted by the mobile terminal voice to adjust the face posture, the number of times the driver looks at the rearview mirror in ten minutes is detected, and a third action frequency of the driver looking at the rearview mirror is obtained. If the third action frequency is less than the minimum threshold, the voice prompt is "Please pay attention to the rearview mirror and improve driving habits", and if the third action frequency is greater than the maximum threshold, the voice prompt is "Driving is tense, improve driving habits".

[0086] In this embodiment, the third action frequency of the driver looking at the rearview mirror is detected as an initial value, the difference between different individuals is considered, and the fatigue driving detection is further used to improve the fatigue driving detection accuracy.

[0087] Optionally, in the above initialization process, the number of times the driver blinks in ten minutes can also be detected by the mobile terminal to determine the blinking frequency, and prompt information for prompting the driver to improve driving habits is generated when the blinking frequency is not in the preset range. Further, after determining the monitoring mode, the number of times the driver blinks and the driving habit can be monitored while monitoring the action frequency of looking at the rearview mirror, and voice prompts can be made according to the monitoring results and the initial value. Thus, the driver can be assisted to improve driving habits, and the function of the product can be expanded.

[0088] Optionally, a danger score value can also be set, and after the driving score is calculated, if the driving score is less than or equal to the danger score value, an alarm information is sent to a preset terminal, for example, the system automatically calls the insurance company to intervene, to ensure driving safety, which can be applied to multiple scenarios such as drunk driving, fatigue driving, and dangerous driving.

[0089] It should be understood that, although Figure 1 and 3 the flowcharts show the steps in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, Figure 1 and 3 at least some of the steps can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be alternately or alternately executed with other steps or sub-steps or stages of other steps.

[0090] In one embodiment, as shown in Figure 4 , a fatigue driving detection device is provided, comprising a determination module 41, an acquisition module 42, a scoring module 43, and a detection module 44.

[0091] The determination module 41 is configured to acquire current driving scene feature information and determine a current monitoring mode according to the driving scene feature information.

[0092] The acquisition module 42 is configured to acquire a first action frequency of the target driver watching the rearview mirror within a monitoring time corresponding to the current monitoring mode.

[0093] The scoring module 43 is configured to calculate a driving score according to the first action frequency of the target driver watching the rearview mirror.

[0094] The detection module 44 is configured to detect fatigue driving of the target driver according to the driving score, a predetermined initial value, and a second action frequency of the driver watching the rearview mirror on a current road section.

[0095] In an embodiment, the determination module 41 includes a first determination unit configured to adopt a first monitoring mode of full-time monitoring when it is detected that the current driving scene feature information meets a preset triggering condition, and a second determination unit configured to adopt a second monitoring mode of monitoring according to a preset duty cycle when it is detected that the current driving scene feature information does not meet the triggering condition.

[0096] In an embodiment, the first determination unit is specifically configured to determine that the triggering condition is met if it is detected that a current vehicle speed is greater than a preset speed, and / or if it is detected that a current driving time is greater than a preset time, and / or if it is detected that a current road section is a preset dangerous road section, and / or if it is detected that a current weather is a preset severe weather.

[0097] In an embodiment, the detection module 41 is specifically configured to compare the first action frequency of the target driver watching the rearview mirror with the initial value in a case where the driving score is less than or equal to a preset score, and determine that the target driver is in a fatigue driving state if the first action frequency of the target driver watching the rearview mirror is less than a product of the initial value and a preset coefficient; and acquire an average value of the second action frequency of the driver watching the rearview mirror on the current road section in a case where the driving score is greater than the preset score, and determine that the target driver is in the fatigue driving state if the first action frequency of the target driver watching the rearview mirror is less than a product of the average value and the preset coefficient.

[0098] In an embodiment, the fatigue driving detection apparatus further comprises an initialization module configured to obtain a preset minimum threshold value and a maximum threshold value, and detect a third action frequency of the target driver looking at the rearview mirror; if the third action frequency is less than the minimum threshold value or the third action frequency is greater than the maximum threshold value, generate a prompt information for prompting the driver to improve driving habits; if the third action frequency is greater than or equal to the minimum threshold value and the third action frequency is less than or equal to the maximum threshold value, take the third action frequency as an initial value.

[0099] In an embodiment, the fatigue driving detection apparatus further comprises an updating module configured to obtain an average score of driving scores of the driver on a current road section; if the driving score of the target driver is less than the average score, control the duty cycle of the second monitoring mode to increase by a preset value.

[0100] In an embodiment, the scoring module 43 is specifically configured to: determine a target value according to the minimum threshold value and the maximum threshold value, wherein the target value is less than the maximum threshold value and greater than the minimum threshold value; in a case where the first action frequency is less than or equal to the target value, calculate the driving score according to a difference between the first action frequency and the minimum threshold value; in a case where the first action frequency is greater than the target value, calculate the driving score according to a difference between the maximum threshold value and the first action frequency.

[0101] The specific limitations of the fatigue driving detection apparatus can refer to the limitations of the fatigue driving detection method in the above, have the corresponding function modules and beneficial effects of the execution method, and will not be repeated here. Each module in the fatigue driving detection apparatus described above can be realized by software, hardware and a combination thereof in whole or in part. The above each module can be embedded in or independent of the processor in the electronic device in hardware form, or can be stored in the memory in the electronic device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0102] In an embodiment, an electronic device is provided, which can be a terminal, and the internal structure diagram thereof can be as shown in Figure 5As shown, the electronic device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a fatigue driving detection method. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the device's casing, or an external keyboard, touchpad, or mouse.

[0103] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0104] In one embodiment, the fatigue driving detection device provided in this application can be implemented as a computer program, and the computer program can be implemented in the form of, for example, Figure 5 The device operates on the electronic device shown. The electronic device's memory can store the various program modules that make up the fatigue driving detection device, for example, Figure 4 The diagram shows a determining module 41, an acquiring module 42, a scoring module 43, and a detection module 44. The computer program comprised of these modules causes the processor to execute the steps in the fatigue driving detection methods of the various embodiments of this application described in this specification.

[0105] For example, Figure 5 The electronic device shown can be used as follows Figure 4 The determination module 41 in the fatigue driving detection device shown acquires the current driving scenario feature information and determines the current monitoring mode based on the driving scenario feature information. The electronic device can acquire the first action frequency of the target driver looking at the rearview mirror within the monitoring time corresponding to the current monitoring mode through the acquisition module 42. The electronic device can calculate a driving score based on the first action frequency of the target driver looking at the rearview mirror through the scoring module 43. The electronic device can perform fatigue driving detection on the target driver through the first detection module 44 based on the driving score, a pre-determined initial value, and the second action frequency of drivers looking at the rearview mirror on the current road segment.

[0106] In one embodiment, an electronic device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program: obtaining current driving scene feature information, and determining a current monitoring mode according to the driving scene feature information; obtaining a first action frequency of a target driver looking at a rearview mirror within a monitoring time corresponding to the current monitoring mode; calculating a driving score according to the first action frequency of the target driver looking at the rearview mirror; and performing fatigue driving detection on the target driver according to the driving score, a predetermined initial value, and a second action frequency of a driver looking at the rearview mirror on a current road section.

[0107] In one embodiment, the processor can further implement the following steps when executing the computer program: when it is detected that the current driving scene feature information meets a preset triggering condition, a first monitoring mode of full-time monitoring is adopted; and when it is detected that the current driving scene feature information does not meet the triggering condition, a second monitoring mode of monitoring according to a preset duty cycle is adopted.

[0108] In one embodiment, the processor can further implement the following steps when executing the computer program: if it is detected that a current vehicle speed is greater than a preset speed, it is determined that the triggering condition is met; and / or, if it is detected that a current driving time is greater than a preset time, it is determined that the triggering condition is met; and / or, if it is detected that a current road section is a preset dangerous road section, it is determined that the triggering condition is met; and / or, if it is detected that a current weather is a preset severe weather, it is determined that the triggering condition is met.

[0109] In one embodiment, the processor can further implement the following steps when executing the computer program: in a case where the driving score is less than or equal to a preset score, the first action frequency of the target driver looking at the rearview mirror is compared with the initial value; if the first action frequency of the target driver looking at the rearview mirror is less than a product of the initial value and a preset coefficient, it is determined that the target driver is in a fatigue driving state; and in a case where the driving score is greater than the preset score, an average value of the second action frequency of the driver looking at the rearview mirror on the current road section is obtained; if the first action frequency of the target driver looking at the rearview mirror is less than a product of the average value and the preset coefficient, it is determined that the target driver is in the fatigue driving state.

[0110] In one embodiment, the processor can further implement the following steps when executing the computer program: obtaining a preset minimum threshold value and a maximum threshold value, and detecting a third action frequency of the target driver looking at the rearview mirror; if the third action frequency is less than the minimum threshold value or the third action frequency is greater than the maximum threshold value, prompt information for prompting the driver to improve driving habits is generated; and if the third action frequency is greater than or equal to the minimum threshold value and the third action frequency is less than or equal to the maximum threshold value, the third action frequency is taken as the initial value.

[0111] In one embodiment, the processor, when executing the computer program, can also implement the following steps: obtaining an average score of driving scores of driving personnel on the current road section; and controlling the duty cycle of the second monitoring mode to increase by a preset value if the driving score of the target driving personnel is less than the average score.

[0112] In one embodiment, the processor, when executing the computer program, can also implement the following steps: determining a target value according to the minimum threshold and the maximum threshold, wherein the target value is less than the maximum threshold and greater than the minimum threshold; calculating the driving score according to a difference between the first action frequency and the minimum threshold if the first action frequency is less than or equal to the target value; and calculating the driving score according to a difference between the maximum threshold and the first action frequency if the first action frequency is greater than the target value.

[0113] According to the electronic device provided in the embodiments of the present application, when the processor executes the computer program, the following steps are implemented, the action frequency of the driver watching the rearview mirror is monitored by setting the monitoring mode with different duty cycles, and the fatigue driving is determined based on the cloud data of other drivers watching the rearview mirror on the current road section and the driving score, so as to reduce the demand for computing power and power consumption, solve the problem that the fatigue driving detection scheme in the related art is complex in system and slow in operation, and is difficult to meet the demand for power consumption and load when used in a mobile phone or the like, and ensure the fatigue driving detection accuracy while reducing the load demand, which is suitable for mobile terminals such as mobile phones, can effectively utilize the computing power and power consumption of the mobile terminal, and is simple and easy to implement.

[0114] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the following steps: obtaining current driving scene feature information, and determining a current monitoring mode according to the driving scene feature information; obtaining a first action frequency of a target driving personnel watching a rearview mirror within a monitoring time corresponding to the current monitoring mode; calculating a driving score according to the first action frequency of the target driving personnel watching the rearview mirror; and performing fatigue driving detection on the target driving personnel according to the driving score, a predetermined initial value, and a second action frequency of driving personnel watching the rearview mirror on a current road section.

[0115] In one embodiment, the computer program, when executed by the processor, can also implement the following steps: when it is detected that the current driving scene feature information meets a preset triggering condition, a first monitoring mode of full-time monitoring is adopted; and when it is detected that the current driving scene feature information does not meet the triggering condition, a second monitoring mode of monitoring according to a set duty cycle is adopted.

[0116] In one embodiment, the computer program, when executed by the processor, further comprises the steps of: determining that the triggering condition is met if it is detected that the current vehicle speed is greater than the preset speed; and / or determining that the triggering condition is met if it is detected that the current driving time is greater than the preset time; and / or determining that the triggering condition is met if it is detected that the current road section is the preset dangerous road section; and / or determining that the triggering condition is met if it is detected that the current weather is the preset severe weather.

[0117] In one embodiment, the computer program, when executed by the processor, further comprises the steps of: comparing the first action frequency of the target driver looking at the rearview mirror with the initial value in the case that the driving score is less than or equal to the preset score; determining that the target driver is in the fatigue driving state if the first action frequency of the target driver looking at the rearview mirror is less than the product of the initial value and the preset coefficient; obtaining an average value of the second action frequency of the driver looking at the rearview mirror on the current road section in the case that the driving score is greater than the preset score; and determining that the target driver is in the fatigue driving state if the first action frequency of the target driver looking at the rearview mirror is less than the product of the average value and the preset coefficient.

[0118] In one embodiment, the computer program, when executed by the processor, further comprises the steps of: obtaining a preset minimum threshold value and a maximum threshold value, and detecting a third action frequency of the target driver looking at the rearview mirror; generating prompt information for prompting the driver to improve the driving habit if the third action frequency is less than the minimum threshold value or the third action frequency is greater than the maximum threshold value; and taking the third action frequency as the initial value if the third action frequency is greater than or equal to the minimum threshold value and the third action frequency is less than or equal to the maximum threshold value.

[0119] In one embodiment, the computer program, when executed by the processor, further comprises the steps of: obtaining an average score of the driving score of the driver on the current road section; and increasing the duty cycle of the second monitoring mode by a preset value if the driving score of the target driver is less than the average score.

[0120] In one embodiment, the computer program, when executed by the processor, further comprises the steps of: determining a target value according to the minimum threshold value and the maximum threshold value, wherein the target value is less than the maximum threshold value and greater than the minimum threshold value; calculating the driving score according to the difference between the first action frequency and the minimum threshold value in the case that the first action frequency is less than or equal to the target value; and calculating the driving score according to the difference between the maximum threshold value and the first action frequency in the case that the first action frequency is greater than the target value.

[0121] The computer readable storage medium according to the embodiment of the present application, when executed by a processor, realizes the following steps through a computer program stored thereon, monitors the action frequency of the driver watching the rearview mirror through setting different duty cycle monitoring modes, and realizes fatigue driving judgment based on the cloud data of other drivers watching the rearview mirror on the current road section and the driving score, reduces the algorithm requirement and power consumption requirement, solves the problems in the related art that the fatigue driving detection scheme system is complex, the operation speed is slow, and when used for mobile phones and the like, it is difficult to meet the power consumption and load requirements, reduces the load requirement while ensuring the fatigue driving detection accuracy, is suitable for mobile phones and the like, can effectively utilize the algorithm power consumption of the mobile terminal, and is simple and easy to implement.

[0122] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, the computer program can include the processes of the above-mentioned embodiments. Any reference to a memory, a database or other medium used in the embodiments provided in the present application can include at least one of a non-volatile and a volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory or an optical memory. The volatile memory can include a random access memory (RAM) or an external cache memory. As an illustration but not limitation, the RAM is available in various forms, such as a static random access memory (SRAM) and a dynamic random access memory (DRAM).

[0123] Any combination of the technical features of the above embodiments can be combined. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0124] The above embodiments only express several implementation manners of the present application, the description is more specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those of ordinary skill in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the patent protection scope of the present application should be subject to the appended claims.

Claims

1. A method of detecting fatigue driving, characterized by, The method comprises the following steps: acquiring current driving scene characteristic information, and determining a current monitoring mode according to the driving scene characteristic information; acquiring a first action frequency of a target driver watching a rearview mirror within a monitoring time corresponding to the current monitoring mode; calculating a driving score according to the first action frequency of the target driver watching the rearview mirror; detecting fatigue driving of the target driver according to the driving score, a predetermined initial value, and a second action frequency of a driver watching the rearview mirror on a current road section; wherein the step of determining the current monitoring mode according to the driving scene characteristic information comprises: when it is detected that the current driving scene characteristic information meets a preset triggering condition, a first monitoring mode of full-time monitoring is adopted; when it is detected that the current driving scene characteristic information does not meet the triggering condition, a second monitoring mode of monitoring according to a set duty cycle is adopted; wherein the step of detecting that the current driving scene characteristic information meets the preset triggering condition comprises: if it is detected that a current vehicle speed is greater than a preset speed, it is determined that the triggering condition is met; and / or, if it is detected that a current driving time is greater than a preset time, it is determined that the triggering condition is met; and / or, if it is detected that a current road section is a preset dangerous road section, it is determined that the triggering condition is met; and / or, if it is detected that a current weather is a preset severe weather, it is determined that the triggering condition is met; the current monitoring mode is the second monitoring mode, and the method further comprises: acquiring an average score of the driving score of the driver on the current road section; if the driving score of the target driver is less than the average score, the duty cycle of the second monitoring mode is increased by a preset value; the duty cycle is initially set to 1 / 10, and the preset value is 1 / 10; wherein the step of detecting fatigue driving of the target driver according to the driving score, the predetermined initial value, and the second action frequency of the driver watching the rearview mirror on the current road section comprises: in a case where the driving score is less than or equal to a preset score, comparing the first action frequency of the target driver watching the rearview mirror with the initial value; if the first action frequency of the target driver watching the rearview mirror is less than a product of the initial value and a preset coefficient, it is determined that the target driver is in a fatigue driving state; in a case where the driving score is greater than the preset score, acquiring an average value of the second action frequency of the driver watching the rearview mirror on the current road section; if the first action frequency of the target driver watching the rearview mirror is less than a product of the average value and a preset coefficient, it is determined that the target driver is in a fatigue driving state.

2. The method of claim 1, wherein, The method further comprises: acquiring a preset minimum threshold value and a maximum threshold value, and detecting a third action frequency of the target driver watching the rearview mirror; if the third action frequency is less than the minimum threshold value or greater than the maximum threshold value, prompt information for prompting the driver to improve driving habits is generated. If the third action frequency is greater than or equal to the minimum threshold value and less than or equal to the maximum threshold value, the third action frequency is taken as the initial value.

3. The method of claim 2, wherein, The driving score is calculated according to the first action frequency of the target driver watching the rearview mirror. A target value is determined according to the minimum threshold value and the maximum threshold value, wherein the target value is less than the maximum threshold value and greater than the minimum threshold value. In a case where the first action frequency is less than or equal to the target value, the driving score is calculated according to a difference between the first action frequency and the minimum threshold value. In a case where the first action frequency is greater than the target value, the driving score is calculated according to a difference between the maximum threshold value and the first action frequency.

4. A drowsy driving detection device characterized by comprising: The method comprises the following steps: A determination module is configured to acquire current driving scene characteristic information and determine a current monitoring mode according to the driving scene characteristic information; An acquisition module is configured to acquire a first action frequency of a target driver watching a rearview mirror within a monitoring time corresponding to the current monitoring mode; A scoring module is configured to calculate a driving score according to the first action frequency of the target driver watching the rearview mirror; A detection module is configured to detect fatigue driving of the target driver according to the driving score, a pre-determined initial value and a second action frequency of a driver watching the rearview mirror on a current road section; The determination of the current monitoring mode according to the driving scene characteristic information comprises: when it is detected that the current driving scene characteristic information meets a pre-set trigger condition, a first monitoring mode of full-time monitoring is adopted; when it is detected that the current driving scene characteristic information does not meet the trigger condition, a second monitoring mode of monitoring according to a set duty cycle is adopted; When it is detected that the current driving scene characteristic information meets the pre-set trigger condition, the following conditions are met: if it is detected that a current vehicle speed is greater than a pre-set speed, it is determined that the trigger condition is met; and / or, if it is detected that a current driving time is greater than a pre-set time, it is determined that the trigger condition is met; and / or, if it is detected that a current road section is a pre-set dangerous road section, it is determined that the trigger condition is met; and / or, if it is detected that a current weather is a pre-set severe weather, it is determined that the trigger condition is met; An updating module is configured to acquire an average score of driving scores of drivers on the current road section; if the driving score of the target driver is less than the average score, a duty cycle of the second monitoring mode is increased by a pre-set value; the duty cycle is initially set as 1 / 10 and the pre-set value is 1 / 10; The detection of fatigue driving of the target driver according to the driving score, the pre-determined initial value and the second action frequency of the driver watching the rearview mirror on the current road section comprises: In a case where the driving score is less than or equal to a pre-set score, the first action frequency of the target driver watching the rearview mirror and the initial value are compared; If the first action frequency of the target driver watching the rearview mirror is less than a product of the initial value and a pre-set coefficient, it is determined that the target driver is in a fatigue driving state. In a case where the driving score is greater than the preset score, an average value of a second action frequency of the driver looking at the rearview mirror on the current road section is obtained; If the first action frequency of the target driver looking at the rearview mirror is less than a product of the average value and a preset coefficient, it is determined that the target driver is in a fatigue driving state. 5.An electronic device comprising a memory and a processor, the memory storing a computer program, wherein, The processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 3.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 3.

Images