Fatigue driving early warning method, device, equipment, medium and product

Abstract

The invention discloses a fatigue driving early warning method, device and equipment, a medium and a product. The method comprises the following steps: in response to a fatigue driving detection request, determining candidate detection features according to visual information, vehicle state information and vehicle environment information, and performing normalization processing to obtain target detection features; determining a preliminary risk value according to the target detection features and feature weights corresponding to the target detection features, and adjusting the preliminary risk value according to the visual information and the vehicle state information in combination with a preset screening rule under the condition that the screening rule is satisfied to determine a target risk value; and according to an association relationship between the target risk value and a preset risk threshold value, determining an early warning strategy so as to perform early warning on the driver and / or the passenger according to the early warning strategy. According to the technical scheme, the information of the vehicle and the driver can be comprehensively evaluated, the fatigue driving condition can be recognized in time, early warning can be made, therefore, the driving safety is improved, and risk events are greatly reduced.

Description

Technical Field

[0001] This invention relates to the fields of big data and vehicle driving, and in particular to a fatigue driving warning method, device, equipment, medium, and product. Background Technology

[0002] With the increasing popularity of car ownership, self-driving tours have become the primary choice for people's travel, and road traffic safety issues are becoming increasingly prominent. Among them, dangerous behaviors such as driver fatigue and distracted driving are one of the main causes of traffic accidents.

[0003] Therefore, there is an urgent need for a high-precision, low-latency fatigue / dangerous driving recognition solution to improve driving safety and greatly reduce the occurrence of risk events. Summary of the Invention

[0004] This invention provides a fatigue driving warning method, device, equipment, medium, and product to comprehensively assess vehicle and driver information, promptly identify fatigue driving situations and issue warnings, thereby improving driving safety and greatly reducing the occurrence of risk events.

[0005] According to one aspect of the present invention, a fatigue driving warning method is provided, comprising:

[0006] In response to a fatigue driving detection request, candidate detection features are determined and normalized based on visual information, vehicle status information, and vehicle environment information to obtain target detection features.

[0007] Based on the target detection features and the feature weights corresponding to each target detection feature, a preliminary risk value is determined. Then, based on visual information and vehicle status information, and in conjunction with preset screening rules, the preliminary risk value is adjusted to determine the target risk value if the screening rules are met.

[0008] Based on the correlation between the target risk value and the preset risk threshold, an early warning strategy is determined to issue warnings to drivers and / or passengers in accordance with the early warning strategy.

[0009] According to another aspect of the present invention, a driver fatigue warning device is provided, comprising:

[0010] The processing module is used to respond to fatigue driving detection requests, determine candidate detection features based on visual information, vehicle status information and vehicle environment information, and perform normalization processing to obtain target detection features;

[0011] The determination module is used to determine the initial risk value based on the target detection features and the feature weights corresponding to each target detection feature, and to adjust the initial risk value based on visual information and vehicle status information, combined with preset screening rules, if the screening rules are met, so as to determine the target risk value.

[0012] The early warning module is used to determine an early warning strategy based on the correlation between the target risk value and the preset risk threshold, so as to issue early warnings to the driver and / or passengers according to the early warning strategy.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the fatigue driving warning method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the fatigue driving warning method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer program product is also provided, the computer program product including a computer program that, when executed by a processor, implements the fatigue driving warning method of any embodiment of the present invention.

[0019] The technical solution of this invention, in response to a fatigue driving detection request, determines candidate detection features based on visual information, vehicle status information, and vehicle environmental information, and performs normalization processing to obtain target detection features. Based on the target detection features and their corresponding feature weights, a preliminary risk value is determined. Then, based on visual information and vehicle status information, and in conjunction with preset screening rules, the preliminary risk value is adjusted to determine a target risk value if the screening rules are met. Finally, based on the correlation between the target risk value and a preset risk threshold, a warning strategy is determined to issue warnings to the driver and / or passengers. By comprehensively evaluating vehicle and driver information, fatigue driving situations can be identified and warnings issued in a timely manner, thereby improving driving safety and significantly reducing the occurrence of risk events.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a fatigue driving warning method provided in an embodiment of the present invention;

[0023] Figure 2 This is a flowchart of a fatigue driving warning method provided in an embodiment of the present invention;

[0024] Figure 3 This is a structural block diagram of a fatigue driving warning device provided in an embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," "target," "candidate," and "alternative," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the invention described herein can be practiced in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The acquisition, storage, use, and processing of data in the technical solutions of this application comply with relevant laws and regulations.

[0028] It should be noted that the user information collected in this invention is information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, and necessary confidentiality measures have been taken. This process does not violate public order and good morals, and corresponding operation entry points are provided for users to choose to authorize or reject automated decision-making results. If the user chooses to reject, the process proceeds to the expert decision-making process. In other words, the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of this data comply with the relevant laws, regulations, and standards of the relevant regions.

[0029] It should be noted that existing driver fatigue and dangerous driving detection technologies primarily rely on vision-based facial feature analysis. However, these methods are easily affected by changes in ambient light and obstructions such as sunglasses or masks worn by the driver, leading to decreased recognition accuracy. Furthermore, algorithms relying solely on facial features struggle to distinguish between fatigue and normal eye-closing actions, such as blinking or brief gaze shifts, increasing the likelihood of false alarms. Additionally, some technologies utilize vehicle behavior data analysis, such as steering wheel angle, lane departure, or speed fluctuations. However, these methods may produce false alarms in complex road conditions (such as curves, bumpy surfaces, or emergency maneuvers), failing to accurately differentiate between dangerous driving and normal operation. Moreover, most existing fatigue detection systems only issue warnings to the driver, lacking a warning mechanism for passengers, preventing timely intervention or evasive action and reducing the system's active safety. While recent research has attempted to incorporate multimodal data, these solutions often rely on costly biosensors with complex installation processes, hindering widespread application in ordinary vehicles.

[0030] To address the aforementioned issues, this invention proposes a robust, low-false-reporting detection scheme that effectively links passenger fatigue and dangerous driving detection, thereby overcoming the shortcomings of existing technologies. The specific implementation will be described in detail in subsequent embodiments.

[0031] Example 1

[0032] Figure 1 This is a flowchart of a fatigue driving warning method provided by an embodiment of the present invention. This embodiment is applicable to situations where the state of the vehicle and driver is assessed when the vehicle is in motion or parked, and a timely warning is issued upon identifying a risk of fatigue driving. This method can be executed by a fatigue driving warning device, which can be implemented in hardware and / or software. The fatigue driving warning device can be configured in an electronic device, such as in a vehicle. Figure 1As shown, the fatigue driving warning method includes:

[0033] S101. In response to the fatigue driving detection request, candidate detection features are determined and normalized based on visual information, vehicle status information and vehicle environment information to obtain target detection features.

[0034] Among them, a fatigue driving detection request refers to a request to detect the driver and the driving status of the vehicle in order to issue a warning when the driver is found to be fatigued.

[0035] Visual information includes at least one of the following: eyelid closure degree, blinking frequency, gaze deviation information, and yawning frequency; gaze deviation information includes gaze deviation angle and duration; vehicle status information includes lane departure information and vehicle driving status; vehicle driving status includes sharp turning, rapid acceleration, emergency braking, or stopping; vehicle environment information can be following distance information, which can be obtained through front radar or camera, as an auxiliary basis for judging whether the driver is fatigued.

[0036] Candidate detection features include at least one of the following: visual features, abnormal vehicle behavior features, lane departure features, abnormal driving behavior features, and following distance features; target detection features refer to the features obtained after normalizing the candidate detection features.

[0037] Optionally, while the vehicle is in motion or temporarily parked, data can be continuously collected by sensors deployed inside the vehicle to obtain visual information, vehicle status information, and vehicle environment information.

[0038] Optionally, an infrared camera installed on the steering wheel, A-pillar, or dashboard can be used to periodically collect facial video streams of the driver for a preset duration to analyze and determine visual information. The infrared camera must have infrared illumination capabilities to ensure normal operation in low-light environments.

[0039] Optionally, real-time vehicle data can be acquired via the controller area network bus, including but not limited to: vehicle speed, acceleration, steering wheel angle, turn signal status, lane departure warning signal, and driving time (to determine whether the driving is prolonged), and vehicle status information can be determined based on the real-time vehicle data.

[0040] Optionally, the feature values ​​in the candidate detection features can be normalized to the interval [0,1] to normalize the candidate detection features and obtain the target detection features.

[0041] Optionally, candidate detection features are determined based on visual information, vehicle status information, and vehicle environment information, including: visual features are determined based on eyelid closure degree, blinking frequency, gaze deviation information, and yawning frequency in the visual information; lane departure features and abnormal vehicle behavior features are determined based on lane departure information and vehicle driving status in the vehicle status information; abnormal driving behavior features are determined based on the driver's driving time and a preset time threshold, and following distance features are determined based on the vehicle environment information; and visual features, abnormal vehicle behavior features, lane departure features, abnormal driving behavior features, and following distance features are determined as candidate detection features.

[0042] The percentage of eyelid closure over the pull-up time (PERCLOS) refers to the percentage of time the eyes are closed per unit of time. Blink frequency refers to the number of blinks per unit of time; a frequency that is too fast or too slow is abnormal. Eye deviation information refers to the angle and duration at which the driver's gaze deviates from the road ahead. Yawning frequency can include the degree of mouth opening and the frequency of yawning.

[0043] Optionally, the captured facial video stream can be processed in real time. Specifically, computer vision algorithms can be used to locate key areas such as the face, eyes, and mouth, and calculate feature parameters such as eyelid closure degree, blinking frequency, gaze deviation information, and yawning frequency to generate visual features.

[0044] Optionally, lane departure characteristics can be determined based on the LDW (Lane Departure Warning) signal, excluding normal lane changes when the turn signal is activated.

[0045] S102. Based on the target detection features and the feature weights corresponding to each target detection feature, determine the preliminary risk value. Based on visual information and vehicle status information, and in conjunction with preset screening rules, adjust the preliminary risk value if the screening rules are met, so as to determine the target risk value.

[0046] The feature weights can be obtained by training on a large amount of driving data, with different target detection features corresponding to different feature weights. The initial risk value can be the sum of the products of each target detection feature and its corresponding feature weight. Preset screening rules can include a first screening rule, a second screening rule, and a third screening rule. The first screening rule evaluates and screens based on the duration of the driver's eye closure. The second screening rule evaluates and screens based on vehicle status information and line-of-sight deviation information in visual information. The third screening rule evaluates and screens based on vehicle status information. The target risk value is the final risk value obtained after adjusting the initial risk value, used to determine the warning strategy. The target risk value can range from, for example, 0 to 100, with a higher value indicating a higher degree of danger.

[0047] It should be noted that the initial risk value can be modified using the preset screening rules stored in the expert rule base to handle extreme or conflicting situations and obtain an accurate and effective target risk value.

[0048] Optionally, based on visual information and vehicle status information, and in conjunction with preset screening rules, the initial risk value is adjusted to determine the target risk value if the screening rules are met. This includes:

[0049] (1) Based on the degree of eyelid closure in the visual information, if the driver's eyes are detected to be closed and the duration of closure exceeds the preset closure duration, then the first screening rule is satisfied, and the target risk value is determined to be the preset maximum risk value; wherein, the preset closure duration can be, for example, 2 seconds. The preset maximum risk value can be 100.

[0050] (2) Based on the line-of-sight deviation information in the vehicle status information and visual information, if the second screening rule is met, the preliminary risk value is increased by a preset magnitude value to obtain the target risk value;

[0051] Optionally, based on the line-of-sight deviation information in the vehicle status information and visual information, and if the second screening rule is met, the initial risk value is increased by a preset magnitude to obtain the target risk value. This includes: based on the line-of-sight deviation information in the vehicle status information and visual information, if the vehicle is in a sharp turn, determining whether the driver's line-of-sight deviation angle is greater than a preset angle threshold; if so, the second screening rule is met, and the initial risk value is increased by the preset magnitude to obtain the target risk value. The preset magnitude refers to a pre-specified risk value that needs to be increased when the second screening condition is met, for example, it could be 10.

[0052] (3) Based on the vehicle status information, if the vehicle is detected to be in a parked state, it is determined that the third screening rule is met, and the target risk value is determined to be the preset minimum risk value. The preset minimum risk value can be 10.

[0053] Optionally, if the vehicle speed is 0 (stopped), the weight of fatigue warning can be temporarily disabled or reduced to determine the minimum risk value. Alternatively, the default minimum risk value can be used to determine the target risk value under the third screening rule.

[0054] Optionally, if, based on visual information and vehicle status information, and combined with preset screening rules, it is determined that none of the preset screening rules are met, the preliminary risk value can be directly determined as the final target risk value.

[0055] S103. Based on the correlation between the target risk value and the preset risk threshold, determine the early warning strategy to issue early warnings to the driver and / or passengers according to the early warning strategy.

[0056] The preset risk thresholds may include a first risk threshold, a second risk threshold, a third risk threshold, and a fourth risk threshold, with the values ​​of the first, second, third, and fourth risk thresholds increasing sequentially. For example, the first, second, third, and fourth risk thresholds could be 0, 30, 60, and 85. The warning strategy can be to not issue a warning, issue a warning only to the driver, issue a warning only to the passenger, issue a basic warning to both the driver and the passenger, or issue a high-level warning to both the driver and the passenger.

[0057] Optionally, based on the correlation between the target risk value and the preset risk threshold, an early warning strategy is determined, including:

[0058] (1) If the target risk value is greater than or equal to the first risk threshold and less than the second risk threshold, then it is determined that the current risk is low and the warning strategy is to not execute the warning.

[0059] Optionally, if the target risk value is greater than or equal to the first risk threshold and less than the second risk threshold, the current state is considered normal and no warning is triggered. After no warning is triggered, the system can periodically send voice messages to passengers to remind them to pay attention to the driver's fatigue status, i.e., only issue warnings to passengers.

[0060] (2) If the target risk value is greater than or equal to the second risk threshold and less than the third risk threshold, then the current risk level is determined to be medium, and the warning strategy is determined to be to warn only the driver.

[0061] Optionally, if the target risk value is greater than or equal to the second risk threshold and less than the third risk threshold, the driver can be determined to be slightly fatigued or distracted. In this case, only a mild warning can be issued to the driver, such as a dashboard icon prompt, a slight beeping sound, or seat vibration, to avoid causing unnecessary interference to passengers.

[0062] (3) If the target risk value is greater than or equal to the third risk threshold and less than the fourth risk threshold, then it is determined that the current risk is high and the warning strategy is to issue a primary warning to both the driver and the passenger at the same time.

[0063] Optionally, a primary warning may be issued to both the driver and passengers simultaneously, including: issuing a primary warning to the driver by emitting a continuous buzzing sound, and simultaneously sending a text or icon reminder to the passenger's smart terminal to issue a primary warning to the passenger.

[0064] Optionally, if the target risk value is greater than or equal to the third risk threshold and less than the fourth risk threshold, it is determined to be moderate fatigue or dangerous driving, that is, currently in a high-risk state. At this time, while issuing a stronger warning to the driver (such as a continuous beeping sound), a hidden text or icon warning can be sent to the passenger's smart terminal (such as a mobile phone), for example: "The driver may be fatigued, please stay alert."

[0065] (4) If the target risk value is greater than or equal to the fourth risk threshold, it is determined that the current risk is extremely high, and the warning strategy is to issue a high-level warning to both the driver and the passenger at the same time.

[0066] Optionally, advanced warnings may be issued to both the driver and passengers simultaneously, including: issuing an advanced warning to the driver by emitting an alarm sound and / or flashing a red light on the dashboard, issuing a voice alarm through the in-vehicle audio system, and sending a red warning icon and warning message to the passengers' smart terminals to issue an advanced warning to the passengers.

[0067] Optionally, if the target risk value is greater than or equal to the fourth risk threshold, it is determined to be an emergency situation where an accident is about to occur (such as a sudden illness or deep sleep of the driver). In this case, the highest level of warning is immediately activated, with a strong audible and visual alarm for the driver (such as a sudden alarm sound and a flashing red light on the dashboard). At the same time, for passengers, on the one hand, a clear voice alarm is played through the in-vehicle audio system (such as: "Warning! The driver may have lost consciousness!"), and on the other hand, a red warning icon and warning message are simultaneously displayed on the passenger's screen (if any) and mobile phone. The goal of this measure is to raise the passengers' awareness to the highest level as soon as possible, so that they can take immediate intervention measures.

[0068] It should be noted that this invention establishes a warning information transmission path that is independent of the driver's warning channel and directly faces the passengers inside the vehicle. This path uses the in-vehicle audio system (playing voice alarms), in-vehicle display terminals (such as the central control screen or rear entertainment screen), or passenger mobile terminals (such as mobile applications) as output interfaces to clearly and perceptibly transmit the driver's risk status determined by the system to the passengers, thereby achieving timely warnings.

[0069] The technical solution of this invention, in response to a fatigue driving detection request, determines candidate detection features based on visual information, vehicle status information, and vehicle environmental information, and performs normalization processing to obtain target detection features. Based on the target detection features and their corresponding feature weights, a preliminary risk value is determined. Then, based on visual information and vehicle status information, and in conjunction with preset screening rules, the preliminary risk value is adjusted to determine a target risk value if the screening rules are met. Finally, based on the correlation between the target risk value and a preset risk threshold, a warning strategy is determined to issue warnings to the driver and / or passengers. By comprehensively evaluating vehicle and driver information, fatigue driving situations can be identified and warnings issued in a timely manner, thereby improving driving safety and significantly reducing the occurrence of risk events.

[0070] Example 2

[0071] Figure 2 This is a flowchart of a fatigue driving warning method provided by an embodiment of the present invention; based on the above embodiments, this embodiment provides a preferred example for comprehensively evaluating vehicle and driver information, timely identifying fatigue driving situations, and issuing warnings, such as... Figure 2 As shown, the method includes:

[0072] S201. In response to a fatigue driving detection request, visual features are determined based on visual information such as eyelid closure degree, blinking frequency, gaze deviation information, and yawning frequency.

[0073] S202. Based on the lane departure information and vehicle driving status in the vehicle status information, determine the lane departure characteristics and abnormal vehicle behavior characteristics.

[0074] S203. Based on the driver's driving time and preset time threshold, determine the characteristics of abnormal driving behavior, and based on vehicle environment information, determine the following distance characteristics.

[0075] S204. Visual features, abnormal vehicle behavior features, lane departure features, abnormal driving behavior features, and following distance features are identified as candidate detection features.

[0076] S205. Normalize the candidate detection features to obtain the target detection features, and determine the preliminary risk value based on the target detection features and the feature weights corresponding to each target detection feature.

[0077] S206. Based on the degree of eyelid closure in the visual information, if the driver's eyes are detected to be closed and the duration exceeds the preset closure time, then the first screening rule is satisfied and the target risk value is determined to be the preset highest risk value.

[0078] Optionally, based on the vehicle status information and the line-of-sight deviation information in the visual information, if it is determined that the second screening rule is met, the preliminary risk value is increased by a preset magnitude value to obtain the target risk value.

[0079] Optionally, based on the vehicle status information, if the vehicle is detected to be in a parked state, it is determined that the third screening rule is met, and the target risk value is determined to be the preset minimum risk value.

[0080] S207. Based on the correlation between the target risk value and the preset risk threshold, determine the early warning strategy to issue early warnings to the driver and / or passengers according to the early warning strategy.

[0081] The technical solution of this invention significantly improves the reliability and accident avoidance success rate of vehicle warning systems. This design constitutes a dual warning path: "system → driver" and "system → passenger." When the "system → driver" path fails due to driver incapacitation, the "system → passenger" path is activated. As a conscious third party, the passenger's perception and response capabilities are far superior to those of a driver in an abnormal state. Once the passenger is awakened by the alarm and aware of the danger, they can immediately take proactive intervention measures such as loudly reminding the driver or assisting with control. This redundant design fundamentally solves the single-point failure problem of existing systems, transforming the success rate of warnings from relying on a single object to double insurance, greatly increasing the possibility of avoiding accidents in the most dangerous scenarios.

[0082] Example 3

[0083] Figure 3 This is a structural block diagram of a fatigue driving warning device provided in an embodiment of the present invention. This embodiment is applicable to situations where the state of the vehicle and driver is assessed while the vehicle is in motion or parked, and a timely warning is issued upon identifying a risk of fatigue driving. The fatigue driving warning device provided by the present invention can execute the fatigue driving warning method provided in any embodiment of the present invention, possessing the corresponding functional modules and beneficial effects of the method. This fatigue driving warning device can be implemented in hardware and / or software and configured in an electronic device with fatigue driving warning functionality, such as in a vehicle. Figure 3 As shown, the fatigue driving warning device may specifically include:

[0084] The processing module 301 is used to respond to the fatigue driving detection request, determine candidate detection features and perform normalization processing based on visual information, vehicle status information and vehicle environment information to obtain target detection features;

[0085] The determination module 302 is used to determine the preliminary risk value based on the target detection features and the feature weights corresponding to each target detection feature, and to adjust the preliminary risk value based on visual information and vehicle status information, combined with preset screening rules, if the screening rules are met, so as to determine the target risk value.

[0086] The early warning module 303 is used to determine an early warning strategy based on the correlation between the target risk value and the preset risk threshold, so as to issue an early warning to the driver and / or passengers according to the early warning strategy.

[0087] The technical solution of this invention, in response to a fatigue driving detection request, determines candidate detection features based on visual information, vehicle status information, and vehicle environmental information, and performs normalization processing to obtain target detection features. Based on the target detection features and their corresponding feature weights, a preliminary risk value is determined. Then, based on visual information and vehicle status information, and in conjunction with preset screening rules, the preliminary risk value is adjusted to determine a target risk value if the screening rules are met. Finally, based on the correlation between the target risk value and a preset risk threshold, a warning strategy is determined to issue warnings to the driver and / or passengers. By comprehensively evaluating vehicle and driver information, fatigue driving situations can be identified and warnings issued in a timely manner, thereby improving driving safety and significantly reducing the occurrence of risk events.

[0088] Furthermore, the processing module 301 is specifically used for:

[0089] Visual features are determined based on visual information such as the degree of eyelid closure, blinking frequency, gaze deviation, and yawning frequency.

[0090] Based on lane departure information and vehicle driving status in the vehicle status information, determine lane departure characteristics and abnormal vehicle behavior characteristics;

[0091] Based on the driver's driving time and preset time threshold, abnormal driving behavior characteristics are determined, and following distance characteristics are determined based on vehicle environmental information.

[0092] Visual features, abnormal vehicle behavior features, lane departure features, abnormal driving behavior features, and following distance features were identified as candidate detection features.

[0093] Furthermore, module 302 is specifically used for:

[0094] Based on the degree of eyelid closure in the visual information, if the driver's eyes are detected to be closed and the duration exceeds the preset closure time, it is determined that the first screening rule is met, and the target risk value is determined to be the preset highest risk value.

[0095] Based on the line-of-sight deviation information in the vehicle status information and visual information, if the second screening rule is met, the preliminary risk value is increased by a preset magnitude value to obtain the target risk value.

[0096] Based on the vehicle status information, if the vehicle is detected to be in a parked state, it is determined that the third screening rule is met, and the target risk value is determined to be the preset minimum risk value.

[0097] Furthermore, the determining module 302 is also used for:

[0098] Based on the vehicle status information and the line-of-sight deviation information in the visual information, when it is determined that the vehicle is in a sharp turn, it is determined whether the driver's line-of-sight deviation angle is greater than a preset angle threshold.

[0099] If so, the second screening rule is satisfied, and the initial risk value is increased by a preset range to obtain the target risk value.

[0100] Furthermore, the early warning module 303 is specifically used for:

[0101] If the target risk value is greater than or equal to the first risk threshold and less than the second risk threshold, then the current risk level is determined to be low, and the warning strategy is determined to be not to issue a warning.

[0102] If the target risk value is greater than or equal to the second risk threshold and less than the third risk threshold, then the current risk level is determined to be moderate, and the warning strategy is determined to be to warn only the driver.

[0103] If the target risk value is greater than or equal to the third risk threshold and less than the fourth risk threshold, then it is determined that the current risk is high, and the warning strategy is to issue a primary warning to both the driver and the passengers simultaneously.

[0104] If the target risk value is greater than or equal to the fourth risk threshold, the current risk level is determined to be extremely high, and the warning strategy is to issue a high-level warning to both the driver and passengers simultaneously.

[0105] Furthermore, the early warning module 303 is also used for:

[0106] A primary warning is given to the driver by emitting a continuous beeping sound, while text or icon reminders are sent to the passengers' smart terminals to provide a primary warning to the passengers.

[0107] The early warning module 303 is also used for:

[0108] Advanced warnings are issued to the driver by emitting an alarm sound and / or flashing a red light on the dashboard, while a voice alarm is issued through the in-vehicle audio system, and a red warning icon and warning message are sent to the passenger's smart terminal to issue an advanced warning to the passenger.

[0109] Example 4

[0110] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Figure 4A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0111] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory 12 or a random access memory 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 12 or loaded from storage unit 18 into the random access memory 13. The random access memory 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, read-only memory 12, and random access memory 13 are interconnected via a bus 14. An input / output interface 15 is also connected to the bus 14.

[0112] Multiple components in electronic device 10 are connected to input / output 15, including: input unit 16, such as a keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as a disk, optical disk, etc.; and communication unit 19, such as a network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0113] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as fatigue driving warning methods.

[0114] In some embodiments, the fatigue driving warning method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory 12 and / or communication unit 19. When the computer program is loaded into random access memory 13 and executed by processor 11, one or more steps of the fatigue driving warning method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the fatigue driving warning method by any other suitable means (e.g., by means of firmware).

[0115] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), system-on-a-chip (SoCs), complex programmable logic devices (PLCs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0117] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube or liquid crystal display) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (e.g., voice input, speech input, or tactile input).

[0119] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0120] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts and virtual reality services, such as high management difficulty and weak business scalability.

[0121] In one embodiment, the present invention further includes a computer program product, which includes a computer program that, when executed by a processor, implements the fatigue driving warning method of any embodiment of the present invention.

[0122] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0123] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0124] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A fatigue driving warning method, characterized in that, include: In response to a fatigue driving detection request, candidate detection features are determined and normalized based on visual information, vehicle status information, and vehicle environment information to obtain target detection features. Based on the target detection features and the feature weights corresponding to each target detection feature, a preliminary risk value is determined. Then, based on visual information and vehicle status information, and in conjunction with preset screening rules, the preliminary risk value is adjusted to determine the target risk value if the screening rules are met. Based on the correlation between the target risk value and the preset risk threshold, an early warning strategy is determined to issue warnings to drivers and / or passengers in accordance with the early warning strategy.

2. The method according to claim 1, characterized in that, Based on visual information, vehicle status information, and vehicle environment information, candidate detection features are determined, including: Visual features are determined based on visual information such as the degree of eyelid closure, blinking frequency, gaze deviation, and yawning frequency. Based on lane departure information and vehicle driving status in the vehicle status information, determine lane departure characteristics and abnormal vehicle behavior characteristics; Based on the driver's driving time and preset time threshold, abnormal driving behavior characteristics are determined, and following distance characteristics are determined based on vehicle environmental information. Visual features, abnormal vehicle behavior features, lane departure features, abnormal driving behavior features, and following distance features were identified as candidate detection features.

3. The method according to claim 1, characterized in that, Based on visual information and vehicle status information, and in conjunction with preset screening rules, the initial risk value is adjusted to determine the target risk value, provided that the screening rules are met. Based on the degree of eyelid closure in the visual information, if the driver's eyes are detected to be closed and the duration exceeds the preset closure time, it is determined that the first screening rule is met, and the target risk value is determined to be the preset highest risk value. Based on the line-of-sight deviation information in the vehicle status information and visual information, if the second screening rule is met, the preliminary risk value is increased by a preset magnitude value to obtain the target risk value. Based on the vehicle status information, if the vehicle is detected to be in a parked state, it is determined that the third screening rule is met, and the target risk value is determined to be the preset minimum risk value.

4. The method according to claim 3, characterized in that, Based on the line-of-sight deviation information from vehicle status information and visual information, and assuming the second screening rule is met, the initial risk value is increased by a preset increment to obtain the target risk value, including: Based on the vehicle status information and the line-of-sight deviation information in the visual information, when it is determined that the vehicle is in a sharp turn, it is determined whether the driver's line-of-sight deviation angle is greater than a preset angle threshold. If so, the second screening rule is satisfied, and the initial risk value is increased by a preset range to obtain the target risk value.

5. The method according to claim 1, characterized in that, Based on the correlation between the target risk value and the preset risk threshold, an early warning strategy is determined, including: If the target risk value is greater than or equal to the first risk threshold and less than the second risk threshold, then the current risk level is determined to be low, and the warning strategy is determined to be not to issue a warning. If the target risk value is greater than or equal to the second risk threshold and less than the third risk threshold, then the current risk level is determined to be moderate, and the warning strategy is determined to be to warn only the driver. If the target risk value is greater than or equal to the third risk threshold and less than the fourth risk threshold, then it is determined that the current risk is high, and the warning strategy is to issue a primary warning to both the driver and the passengers simultaneously. If the target risk value is greater than or equal to the fourth risk threshold, the current risk level is determined to be extremely high, and the warning strategy is to issue a high-level warning to both the driver and passengers simultaneously.

6. The method according to claim 5, characterized in that, At the same time, a preliminary warning is given to the driver and passengers, including: A primary warning is given to the driver by emitting a continuous beeping sound, while text or icon reminders are sent to the passengers' smart terminals to provide a primary warning to the passengers. Correspondingly, advanced warnings are simultaneously issued to both the driver and passengers, including: Advanced warnings are issued to the driver by emitting an alarm sound and / or flashing a red light on the dashboard, while a voice alarm is issued through the in-vehicle audio system, and a red warning icon and warning message are sent to the passenger's smart terminal to issue an advanced warning to the passenger.

7. A fatigue driving warning device, characterized in that, include: The processing module is used to respond to fatigue driving detection requests, determine candidate detection features based on visual information, vehicle status information and vehicle environment information, and perform normalization processing to obtain target detection features; The determination module is used to determine the initial risk value based on the target detection features and the feature weights corresponding to each target detection feature, and to adjust the initial risk value based on visual information and vehicle status information, combined with preset screening rules, if the screening rules are met, so as to determine the target risk value. The early warning module is used to determine an early warning strategy based on the correlation between the target risk value and the preset risk threshold, so as to issue early warnings to the driver and / or passengers according to the early warning strategy.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that is executed by the at least one processor to enable the at least one processor to perform the fatigue driving warning method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the fatigue driving warning method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the fatigue driving warning method according to any one of claims 1-6.

Images