Traffic safety monitoring method and device based on real-time data flow and medium
By collecting vehicle operation data and driver facial images in real time, identifying abnormal attitudes and calculating driving risk coefficients, the problems of real-time risk monitoring and information islands in traditional traffic safety monitoring methods are solved, and the accuracy and effectiveness of early warning are significantly improved.
Patent Information
- Application Number
- CN202411373091.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional traffic safety monitoring methods are difficult to monitor vehicle safety risks in real time. Information islands and simple rules judgments lead to false alarms or missed reports, reducing the effectiveness of early warnings.
The traffic safety monitoring method based on real-time data flow is adopted to collect vehicle operation data and driver facial images, identify driver attitude characteristics, calculate driving risk coefficients, and correct them according to environmental parameters to provide safety warnings.
It realizes comprehensive real-time monitoring of the vehicle's travel process, reduces the false alarm and missed rate, and improves the accuracy and effectiveness of early warnings.
Smart Images

Figure CN118968815A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of traffic safety monitoring, and in particular to a traffic safety monitoring method, device and medium based on real-time data stream. Background Art
[0002] With the acceleration of urbanization and the increasing complexity of transportation networks, traffic safety issues have become the focus of social attention. Traditional traffic safety monitoring methods often rely on manual inspections, accident statistics and post-event analysis, which makes it difficult to monitor and handle safety risks during driving in real time, resulting in an inability to respond in time when an accident occurs. In addition, vehicle transportation data is usually scattered in different systems and devices, forming information islands, which limits the ability to comprehensively evaluate vehicle safety risks and provide real-time warnings. Existing monitoring methods mostly use simple rules or thresholds for safety warnings, which cannot make accurate judgments based on complex and changeable traffic environments and operating conditions, and are prone to false alarms or missed alarms, reducing the effectiveness of warnings. Summary of the invention
[0003] In order to solve the above problems, this application proposes a traffic safety monitoring method based on real-time data stream, including:
[0004] According to a preset collection interval, real-time operation data of the vehicle is collected, and a facial image of the driver during the driving of the vehicle is collected through a preset image collection device; wherein the real-time operation data includes at least one or more of the following: vehicle speed, lane deviation, vehicle acceleration, and braking status;
[0005] Based on the facial image, determining a plurality of positioning points on the driver's face, and determining a posture feature area for positioning the driver's posture according to the positioning points;
[0006] Identifying the position attribute of the posture feature area, and determining whether the driver has an abnormal posture according to the change frequency of the position attribute;
[0007] If yes, obtain the following distance between the vehicle and the previous vehicle, and calculate the driving risk coefficient corresponding to the vehicle according to the change frequency, the real-time operation data and the following distance;
[0008] Acquire environmental parameters around the vehicle, correct the driving risk coefficient according to the environmental parameters to obtain a corrected driving risk coefficient, and issue a safety warning to the vehicle according to the corrected driving risk coefficient.
[0009] In one implementation of the present application, the position attribute includes length and direction angle, and identifying the position attribute of the posture feature area specifically includes:
[0010] Initializing the posture feature area to determine an initial length and an initial direction angle between adjacent positioning points;
[0011] Identifying the posture feature area in the continuously collected facial images, determining the changed specified position attribute and the corresponding specified position attribute change amount;
[0012] The posture type corresponding to the driver is determined according to the designated position attribute; wherein the posture type includes a rotation posture, a swing posture and a pitch posture.
[0013] In one implementation of the present application, determining whether the driver has an abnormal posture according to the change frequency of the position attribute specifically includes:
[0014] Determining whether the change amount of the specified position attribute exceeds a preset change amount; wherein the preset change amount corresponding to the swing posture is greater than the preset change amounts corresponding to the rotation posture and the pitch posture;
[0015] If so, the designated position attribute is used as an abnormal position attribute, and a change frequency corresponding to the abnormal position attribute is determined. When the change frequency is greater than a preset frequency, it is determined that the driver has an abnormal posture.
[0016] In one implementation of the present application, the driving risk coefficient corresponding to the vehicle is calculated according to the change frequency, the real-time operation data and the following distance, specifically including:
[0017] According to the roadside equipment of the road section where the vehicle is located, the number of vehicles in the buffer area where the vehicle is located is collected; wherein the buffer area is a circular area formed with the vehicle as the center and the buffer distance as the radius, and the buffer distance is positively correlated with the speed of the vehicle;
[0018] Calculating the vehicle density in the buffer area according to the number of vehicles, and determining a first weight coefficient corresponding to the vehicle density according to a mapping relationship between the vehicle density and the weight coefficient; wherein the vehicle density and the first weight coefficient are positively correlated;
[0019] Matching the real-time operation data with a safe operation value range corresponding to the vehicle to determine whether the real-time operation data conforms to the safe operation value range, and assigning a corresponding state evaluation value to the real-time operation data;
[0020] A driving risk coefficient corresponding to the vehicle is calculated according to the state evaluation value, the change frequency and the following distance.
[0021] In one implementation of the present application, the driving risk coefficient corresponding to the vehicle is calculated according to the state evaluation value, the change frequency and the following distance, specifically including:
[0022] Calculating the product of the state evaluation values, and weighting the product according to the first weight coefficient to obtain a first weighted value;
[0023] Allocating a corresponding second weight coefficient to the change frequency, weighting the change frequency according to the second weight coefficient to obtain a second weight value, and determining a ratio between the second weight value and the following vehicle distance;
[0024] The sum of the ratio and the first weighted value is used as the driving risk coefficient corresponding to the vehicle.
[0025] In one implementation of the present application, the driving risk coefficient is corrected according to the environmental parameter to obtain a corrected driving risk coefficient, specifically including:
[0026] Obtaining a parameter range corresponding to each environmental parameter, and comparing the collected environmental parameter with the parameter range to determine whether the environmental parameter falls within the parameter range;
[0027] If not, calculating the difference between the environmental parameter and the upper limit or the lower limit of the parameter range, and determining the correction coefficient corresponding to the environmental parameter according to the difference interval to which the difference belongs;
[0028] The driving risk coefficient is corrected according to the correction coefficient to obtain a corrected driving risk coefficient.
[0029] In one implementation of the present application, before collecting the facial image of the driver during the driving of the vehicle at a preset collection interval, the method further includes:
[0030] The current driving time of the vehicle is obtained, and the collection interval of the real-time operation data and the facial image is adjusted according to the current driving time; wherein the current driving time and the collection interval are negatively correlated.
[0031] In one implementation of the present application, a safety warning is provided to the vehicle according to the corrected driving risk coefficient, specifically including:
[0032] When the driving risk coefficient exceeds a preset value, a safety warning is issued to the vehicle, and the vehicle positions of the vehicle and its surrounding vehicles are obtained, and a guidance path for the vehicle is generated according to the vehicle positions, so that the vehicle can enter a safe zone according to the guidance path.
[0033] The embodiment of the present application provides a traffic safety monitoring device based on real-time data stream, the device comprising:
[0034] at least one processor;
[0035] and, a memory communicatively coupled to the at least one processor;
[0036] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:
[0037] According to a preset collection interval, real-time operation data of the vehicle is collected, and a facial image of the driver during the driving of the vehicle is collected through a preset image collection device; wherein the real-time operation data includes at least one or more of the following: vehicle speed, lane deviation, vehicle acceleration, and braking status;
[0038] Based on the facial image, determining a plurality of positioning points on the driver's face, and determining a posture feature area for positioning the driver's posture according to the positioning points;
[0039] Identifying the position attribute of the posture feature area, and determining whether the driver has an abnormal posture according to the change frequency of the position attribute;
[0040] If yes, obtain the following distance between the vehicle and the previous vehicle, and calculate the driving risk coefficient corresponding to the vehicle according to the change frequency, the real-time operation data and the following distance;
[0041] Acquire environmental parameters around the vehicle, correct the driving risk coefficient according to the environmental parameters to obtain a corrected driving risk coefficient, and issue a safety warning to the vehicle according to the corrected driving risk coefficient.
[0042] The embodiment of the present application provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:
[0043] According to a preset collection interval, real-time operation data of the vehicle is collected, and a facial image of the driver during the driving of the vehicle is collected through a preset image collection device; wherein the real-time operation data includes at least one or more of the following: vehicle speed, lane deviation, vehicle acceleration, and braking status;
[0044] Based on the facial image, determining a plurality of positioning points on the driver's face, and determining a posture feature area for positioning the driver's posture according to the positioning points;
[0045] Identifying the position attribute of the posture feature area, and determining whether the driver has an abnormal posture according to the change frequency of the position attribute;
[0046] If yes, obtain the following distance between the vehicle and the previous vehicle, and calculate the driving risk coefficient corresponding to the vehicle according to the change frequency, the real-time operation data and the following distance;
[0047] Acquire environmental parameters around the vehicle, correct the driving risk coefficient according to the environmental parameters to obtain a corrected driving risk coefficient, and issue a safety warning to the vehicle according to the corrected driving risk coefficient.
[0048] The traffic safety monitoring method based on real-time data stream proposed in this application can bring the following beneficial effects:
[0049] By collecting various data such as vehicle operation data, driver behavior, environmental parameters, etc. in real time, a continuous data stream is formed to ensure the real-time and accuracy of the data, and the vehicle's driving process can be fully monitored, thereby improving safety. The use of image processing and data analysis technology can identify the driver's abnormal posture and dynamically calculate the driving risk factor based on the complex and changing traffic environment and operating conditions. Compared with simple rules or threshold judgments, it significantly reduces the false alarm and missed alarm rates and improves the effectiveness and accuracy of early warnings. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0051] Figure 1 A flow chart of a traffic safety monitoring method based on real-time data stream provided in an embodiment of the present application;
[0052] Figure 2 A schematic diagram of the structure of a traffic safety monitoring device based on real-time data stream provided in an embodiment of the present application. DETAILED DESCRIPTION
[0053] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0054] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0055] like Figure 1 As shown, a traffic safety monitoring method based on real-time data stream provided in an embodiment of the present application includes:
[0056] S101: Collecting real-time operation data of the vehicle at a preset collection interval, and collecting a facial image of the driver during the driving of the vehicle through a preset image collection device; wherein the real-time operation data includes at least one or more of the following: vehicle speed, lane deviation, vehicle acceleration, and braking status.
[0057] Vehicles are usually equipped with sensors and image acquisition devices that can collect real-time vehicle operation data and driver's facial images at preset collection intervals. Real-time operation data includes at least one or more of the following: vehicle speed, lane deviation, vehicle acceleration, and braking status. Real-time operation data and facial images can be used to conduct a comprehensive analysis of the current vehicle's traffic safety status. Facial images can be used to analyze whether the driver's driving behavior is risky, such as dozing off, frequently looking at the phone, etc. Real-time operation data can further evaluate the vehicle's driving risk based on whether there are any abnormalities in the current vehicle's operating status. The traffic safety monitoring method based on real-time data streams and image acquisition uses a variety of technical means to achieve all-round monitoring and analysis of vehicle driving status and driver behavior, providing strong support for improving road traffic safety.
[0058] It should be noted that the collection interval will be adjusted in real time according to the vehicle's current driving time. According to the negative correlation between the current driving time and the collection interval, the longer the driving time, the shorter the collection interval should be; the shorter the driving time, the longer the collection interval can be. This strategy aims to balance the relationship between data accuracy and system resource consumption, ensuring that sufficient data can be obtained during long driving to support safety analysis, which helps to more accurately assess driving risks, while avoiding wasting too much computing resources and storage space when driving short distances.
[0059] S102: Based on the facial image, determine a number of positioning points on the driver's face, and determine a posture feature area for positioning the driver's posture according to the positioning points.
[0060] Based on several positioning points used for posture positioning on the facial image, it is possible to identify whether the driver has abnormal posture during driving. The positioning points refer to the left eye, right eye and nose. Based on the selected positioning points, a triangular area formed by the eyes and nose can be constructed as a posture feature area. This posture feature area can effectively retain the key information of facial posture while better reflecting the changes in the driver's head posture, such as nodding and turning the head.
[0061] S103: Identify the position attribute of the posture feature area, and determine whether the driver has an abnormal posture according to the change frequency of the position attribute.
[0062] The position, shape and size of the posture feature area will change with the change of the driver's head posture. Therefore, the driver's posture can be identified based on the position attributes of the posture feature area. In this process, the two key parameters of the length and direction angle of the posture feature area are mainly concerned. By monitoring the change frequency of these position attributes, it is possible to effectively determine whether the driver has an abnormal posture.
[0063] In one embodiment, the driver's head is taken as the initial state, and the posture feature area is initialized based on the initial state, and the initial length of the side between adjacent positioning points and the initial direction angle between each inner angle in the posture feature area when the driver is looking forward are calculated respectively. After the continuous facial images are acquired by the image acquisition device, the posture feature area and its positioning points are relocated in each facial image. By identifying the posture feature area, it is necessary to determine the specified position attributes that have changed. These attributes may include the distance between certain positioning points (such as the change in width between the two eyes) or the direction angle (such as the change in the angle between the face and the horizontal direction caused by the rotation of the head), and calculate the change between the above-mentioned specified position attributes and the initial value, that is, the change in the specified position attribute. According to the change in the specified position attribute, especially the change in the direction angle, it can be preliminarily determined whether the driver's head has swung, rotated or pitched. For example, if the angle between the face and the horizontal direction changes significantly, it may be a pitching posture. By analyzing the distance change between the key positioning points and their position changes relative to the facial center line or the reference direction, the rotation posture and the swinging posture can be further distinguished. For example, a change in the relative position between the left and right eye corners may indicate a head rotation, while a length between the left and right eye corners that is no longer parallel to the x-axis but has a certain angle indicates a head swing.
[0064] In order to more accurately determine whether the driver has an abnormal posture according to the frequency of change of the position attribute, a large amount of facial image data of the driver under normal driving conditions is collected and analyzed, and the normal change range of the specified position attribute under different posture types is statistically calculated. Based on the results of historical data analysis, a reasonable preset change amount is set for each posture type. Considering that the swinging posture may be a related driving habit of the driver, treating this posture as an abnormal posture usually involves a larger head movement, so its corresponding preset change amount should be greater than the preset change amount of the rotation posture and pitch posture. The calculated change amount is compared with the corresponding preset change amount. If the change amount of the specified position attribute exceeds the preset change amount, the position attribute is regarded as an abnormal position attribute. For the specified position attribute marked as an abnormal position attribute, its change frequency is calculated. The change frequency here actually refers to the frequency of occurrence of the specified position attribute, which can be obtained by counting the number of occurrences of the specified position attribute in a unit time (such as every five minutes, ten minutes, etc.). The calculated change frequency is compared with the preset frequency. The preset frequency is set based on the statistical results of the driver's posture changes under normal driving conditions, and is used to distinguish between normal posture changes and abnormal posture changes. If the frequency of change of the abnormal position attribute is greater than the preset frequency, it is determined that the driver has an abnormal posture, which may indicate that the driver is distracted, fatigued or has other unsafe driving behaviors.
[0065] S104: If yes, obtain the following distance between the vehicle and the previous vehicle, and calculate the driving risk coefficient corresponding to the vehicle according to the change frequency, real-time operation data and the following distance.
[0066] When the driver has an abnormal posture, it may indicate distraction, fatigue or other unsafe factors, but this alone is not enough to fully assess driving risks. Because the risk during driving is not only related to the driver's state, but also closely related to multiple factors such as the vehicle's operating environment, speed, acceleration, and following distance. Therefore, combining the vehicle's real-time operating data can provide a more comprehensive and accurate driving risk assessment.
[0067] In one embodiment, the number of vehicles in the buffer area where the vehicle is located is collected based on the roadside equipment of the road section where the vehicle is located. The buffer area refers to the safe driving range of the vehicle, which is a circular area formed with the vehicle as the center and the buffer distance as the radius. The buffer distance is positively correlated with the speed of the vehicle. The faster the speed, the greater the risk of a safety accident for the vehicle, and the required safe driving range needs to be expanded accordingly. After determining the number of vehicles in the buffer area, the vehicle density in the buffer area is calculated based on the number of vehicles, and the first weight coefficient corresponding to the vehicle density is determined based on the mapping relationship between the vehicle density and the weight coefficient. Among them, the mapping relationship is usually established based on historical data and expert knowledge, and there is a positive correlation between the vehicle density and the first weight coefficient. That is to say, the higher the vehicle density, the greater the impact of the traffic conditions in the area on the driving risk of the current vehicle.
[0068] Match the real-time operation data with the safe operation numerical range corresponding to the vehicle to determine whether the real-time operation data meets the safe operation numerical range, and assign the corresponding state evaluation value to the real-time operation data. Generally, the state evaluation value has a certain numerical range. When assigning the state evaluation value to the real-time operation data, the discrimination of the real-time operation data on the driving risk assessment results can be improved by assigning an upper limit value and a lower limit value. For example, the numerical range of the state evaluation value is [1,10]. For the real-time operation data that meets the safe operation numerical range, the corresponding state evaluation value is 1, and for the real-time operation data that does not meet the safe operation numerical range, the corresponding state evaluation value is 10.
[0069] After determining the state evaluation value, the state evaluation value, change frequency and following distance are combined to calculate the driving risk coefficient corresponding to the vehicle. Specifically, first, the product between the state evaluation values is calculated, and the product is weighted according to the first weight coefficient to obtain the first weight value. The purpose of weighting is to take into account the impact of vehicle density on driving risk, because a high-density traffic environment usually means a higher risk of collision. The second weight coefficient corresponding to the change frequency is assigned. The second weight coefficient is derived based on historical data analysis and reflects the degree of impact of the change frequency on driving risk. The change frequency is weighted according to the second weight coefficient to obtain a second weighted value, and the ratio between the second weighted value and the following distance is determined. This ratio can reflect whether the driver maintains a sufficient safety distance from the vehicle in front when the driving state changes rapidly. The sum of the ratio and the first weighted value is used as the driving risk coefficient corresponding to the vehicle.
[0070] S105: Obtain environmental parameters around the vehicle, and correct the driving risk coefficient according to the environmental parameters to obtain a corrected driving risk coefficient, so as to issue a safety warning to the vehicle according to the corrected driving risk coefficient.
[0071] In addition to the driving risks caused by the vehicle and the driver themselves, it is also possible to consider introducing environmental parameters to further correct the vehicle's driving risk coefficient, such as weather conditions (rain, snow, haze, visibility, etc.), road types (road slipperiness, road curvature, slope), etc. The corrected driving risk coefficient can more comprehensively reflect the safety risk level under the current driving state. According to the final driving risk coefficient, the vehicle can be given a real-time safety warning and trigger corresponding safety warning measures.
[0072] In one embodiment, for each environmental parameter, it is necessary to predefine its valid parameter range, which can be determined based on safety standards, historical data or expert advice. The collected environmental parameters are compared with the parameter range to determine whether the environmental parameters belong to the parameter range. If the environmental parameter is not within the normal range, it is necessary to calculate the difference between it and the upper or lower limit of the parameter range. The difference reflects the degree to which the environmental parameter deviates from the normal range. According to the size of the difference, it is divided into different difference intervals. For each difference interval, one or more correction coefficients are predefined, and the correction coefficient reflects the degree of influence of the environmental parameter deviating from the normal range on the driving risk. Among them, the correction coefficient is a positive value, which is used to increase the driving risk of the vehicle, and its size is proportional to the risk level of the difference interval. After determining the correction coefficient, the correction coefficient is added to the original driving risk coefficient to complete the correction of the driving risk coefficient and obtain the corrected driving risk coefficient.
[0073] When the driving risk factor exceeds the preset value, the vehicle needs to be given a safety warning, which can be given through visual prompts, voice alarms, seat vibrations, steering wheel vibrations, etc. At the same time, since the driver may take a more dangerous driving route when he is tired or distracted, it is necessary to obtain the vehicle position and the vehicle's surrounding vehicles' position, and generate a guidance path for the vehicle based on the vehicle position, so that the vehicle can enter the safety zone according to the guidance path, thereby helping the driver to respond quickly and gradually restore normal driving status through a safer driving route.
[0074] The above are embodiments of the method proposed in this application. Based on the same idea, some embodiments of this application also provide devices and non-volatile computer storage media corresponding to the above methods.
[0075] Figure 2 The following is a schematic diagram of the structure of a traffic safety monitoring device based on real-time data stream provided in an embodiment of the present application. Figure 2 As shown, including:
[0076] at least one processor; and,
[0077] at least one processor is communicatively connected to a memory; wherein,
[0078] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that the at least one processor can execute a traffic safety monitoring method based on real-time data stream as described in any one of the above items.
[0079] An embodiment of the present application provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as: a traffic safety monitoring method based on real-time data stream as described in any one of the above items.
[0080] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0081] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.
[0082] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0083] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0084] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0085] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0086] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0087] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0088] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0089] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0090] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A traffic safety monitoring method based on real-time data stream, characterized in that: The method comprises: According to a preset collection interval, real-time operation data of the vehicle is collected, and a facial image of the driver during the driving of the vehicle is collected through a preset image collection device; wherein the real-time operation data includes at least one or more of the following: vehicle speed, lane deviation, vehicle acceleration, and braking status; Based on the facial image, determining a plurality of positioning points on the driver's face, and determining a posture feature area for positioning the driver's posture according to the positioning points; Identifying the position attribute of the posture feature area, and determining whether the driver has an abnormal posture according to the change frequency of the position attribute; If yes, obtain the following distance between the vehicle and the previous vehicle, and calculate the driving risk coefficient corresponding to the vehicle according to the change frequency, the real-time operation data and the following distance; Acquire environmental parameters around the vehicle, correct the driving risk coefficient according to the environmental parameters to obtain a corrected driving risk coefficient, and issue a safety warning to the vehicle according to the corrected driving risk coefficient.
2. A traffic safety monitoring method based on real-time data stream according to claim 1, characterized in that: The position attributes include length and direction angle, and the position attributes of the posture feature area are identified, specifically including: Initializing the posture feature area to determine an initial length and an initial direction angle between adjacent positioning points; Identifying the posture feature area in the continuously collected facial images, determining the changed specified position attribute and the corresponding change amount of the specified position attribute; The posture type corresponding to the driver is determined according to the designated position attribute; wherein the posture type includes a rotation posture, a swing posture and a pitch posture.
3. A traffic safety monitoring method based on real-time data stream according to claim 2, characterized in that: Determining whether the driver has an abnormal posture according to the change frequency of the position attribute includes: Determining whether the change amount of the specified position attribute exceeds a preset change amount; wherein the preset change amount corresponding to the swing posture is greater than the preset change amounts corresponding to the rotation posture and the pitch posture; If so, the designated position attribute is used as an abnormal position attribute, and a change frequency corresponding to the abnormal position attribute is determined. When the change frequency is greater than a preset frequency, it is determined that the driver has an abnormal posture.
4. A traffic safety monitoring method based on real-time data stream according to claim 1, characterized in that: Calculating a driving risk coefficient corresponding to the vehicle according to the change frequency, the real-time operation data and the following distance, specifically includes: According to the roadside equipment of the road section where the vehicle is located, the number of vehicles in the buffer area where the vehicle is located is collected; wherein the buffer area is a circular area formed with the vehicle as the center and the buffer distance as the radius, and the buffer distance is positively correlated with the speed of the vehicle; Calculating the vehicle density in the buffer area according to the number of vehicles, and determining a first weight coefficient corresponding to the vehicle density according to a mapping relationship between the vehicle density and the weight coefficient; wherein the vehicle density and the first weight coefficient are positively correlated; Matching the real-time operation data with a safe operation value range corresponding to the vehicle to determine whether the real-time operation data conforms to the safe operation value range, and assigning a corresponding state evaluation value to the real-time operation data; A driving risk coefficient corresponding to the vehicle is calculated according to the state evaluation value, the change frequency and the following distance.
5. A traffic safety monitoring method based on real-time data stream according to claim 4, characterized in that: Calculating a driving risk coefficient corresponding to the vehicle according to the state evaluation value, the change frequency, and the following distance, specifically includes: Calculating the product of the state evaluation values, and weighting the product according to the first weight coefficient to obtain a first weighted value; Allocating a corresponding second weight coefficient to the change frequency, weighting the change frequency according to the second weight coefficient to obtain a second weight value, and determining a ratio between the second weight value and the following vehicle distance; The sum of the ratio and the first weighted value is used as the driving risk coefficient corresponding to the vehicle.
6. A traffic safety monitoring method based on real-time data stream according to claim 1, characterized in that: Correcting the driving risk coefficient according to the environmental parameter to obtain a corrected driving risk coefficient specifically includes: Obtaining a parameter range corresponding to each environmental parameter, and comparing the collected environmental parameter with the parameter range to determine whether the environmental parameter falls within the parameter range; If not, calculating the difference between the environmental parameter and the upper limit or the lower limit of the parameter range, and determining the correction coefficient corresponding to the environmental parameter according to the difference interval to which the difference belongs; The driving risk coefficient is corrected according to the correction coefficient to obtain a corrected driving risk coefficient.
7. A traffic safety monitoring method based on real-time data stream according to claim 1, characterized in that: Before collecting the facial image of the driver during the driving of the vehicle at a preset collection interval, the method further includes: The current driving time of the vehicle is obtained, and the collection interval of the real-time operation data and the facial image is adjusted according to the current driving time; wherein the current driving time and the collection interval are negatively correlated.
8. The traffic safety monitoring method based on real-time data stream according to claim 1 is characterized in that: According to the corrected driving risk coefficient, a safety warning is given to the vehicle, specifically including: When the driving risk coefficient exceeds a preset value, a safety warning is issued to the vehicle, and the vehicle positions of the vehicle and its surrounding vehicles are obtained, and a guidance path for the vehicle is generated according to the vehicle positions, so that the vehicle can enter a safe zone according to the guidance path.
9. A traffic safety monitoring device based on real-time data stream, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a traffic safety monitoring method based on real-time data stream as described in any one of claims 1-8.
10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to: A traffic safety monitoring method based on real-time data stream as described in any one of claims 1 to 8.
Citation Information
Patent Citations
Identification alarm method and system for dangerous driving
CN108230616A
Vehicle braking method, device, system and equipment
CN111959503A
Driver behavior anomaly detection method and device
CN115690749A
Vehicular warning system and method
US20130162791A1
Cited By
Road traffic safety intelligent detection system and method
CN119694137A
Mobile phone management and control method and control system in driving process
CN119854407A
