C-V2X-based automobile sentry monitoring method and system, electronic equipment and storage medium

Abstract

The invention relates to the technical field of intelligent automobiles, and provides a C-V2X-based automobile sentry monitoring method and system, electronic equipment and a storage medium, and the method comprises the steps: obtaining vehicle surrounding environment information, and carrying out the sentry monitoring based on the environment information; establishing communication connection with surrounding vehicles, infrastructures and pedestrian equipment based on the environment information; based on environment information fusion analysis, whether potential threats exist is judged, and if yes, potential danger result information is output; and according to the potential danger result information, alarm information is sent to surrounding vehicles, a collaborative early warning mechanism of the infrastructure is triggered, and the alarm information is sent to surrounding pedestrian equipment. In this way, the C-V2X is combined with surrounding vehicles, infrastructures and pedestrian equipment to give an alarm, information interaction is carried out on the infrastructures and the pedestrian equipment in the surrounding environment, alarm feedback is formed, the monitoring range in the sentry mode is enlarged, the strategy of aerial alarm of the vehicle sentry is more perfect, and therefore the safety protection performance of the vehicle is improved.

Description

Technical Field

[0001] The present disclosure belongs to the field of intelligent vehicle technology, and in particular, relates to a C-V2X-based vehicle sentinel monitoring method, system, electronic device, and storage medium. Background Art

[0002] With the development of automobile intelligence, the demand for automobile safety protection is growing. The traditional automobile sentinel mode mainly relies on vehicle-mounted cameras and sensors for monitoring. It mainly focuses on monitoring the surrounding environment of the vehicle when it is parked, with the focus on preventing the vehicle from being damaged by collision, scratches, illegal intrusion, etc. during parking.

[0003] When the traditional sentinel mode monitors its surrounding environment and is threatened, it will sound the car alarm or play music at a high volume, and honk the horn and flash the lights to warn potential threat actors. However, the vehicle that is threatened and issues a warning is only the vehicle that is currently threatened. There is no information interaction or feedback from the surrounding environment, which makes the security protection performance of the sentinel mode's monitoring and alarming based on environmental information relatively limited and needs to be improved. Summary of the invention

[0004] To solve the above problems, the present disclosure provides a C-V2X-based vehicle sentinel monitoring method, system, electronic device and storage medium. By combining C-V2X with the vehicle sentinel technology, the vehicle can interact with surrounding vehicles and infrastructure to obtain a wider range of environmental information, which helps to improve the perception range and response capability of the sentinel monitoring strategy, thereby improving the vehicle's safety protection performance.

[0005] The first aspect of the present disclosure provides a C-V2X-based vehicle sentinel monitoring method, the method comprising: acquiring environmental information surrounding the vehicle, and performing sentinel monitoring based on the environmental information; establishing a communication connection with surrounding vehicles, infrastructure, and pedestrian equipment based on the environmental information; judging whether there is a potential threat based on a fusion analysis of the environmental information, and if so, outputting potential danger result information; sending alarm information to surrounding vehicles, triggering a collaborative early warning mechanism of the infrastructure, and sending alarm information to surrounding pedestrian equipment based on the potential danger result information.

[0006] With this setting, when the vehicle is in sentry mode, if a potential threat is detected, it can quickly send alarm information to surrounding vehicles, infrastructure and pedestrian equipment through C-V2X to achieve coordinated early warning, so as to monitor abnormal activities around the vehicle while expanding the perception range and response capabilities, and combine the surrounding vehicles, infrastructure and pedestrian equipment to issue alarms, so as to exchange information with the infrastructure and pedestrian equipment in the surrounding environment and form alarm feedback, thereby increasing the scope of monitoring in sentry mode and making the vehicle sentry overhead alarm strategy more perfect, thereby improving the vehicle's safety protection performance.

[0007] In some embodiments, the environmental information includes image information and distance and speed information, the image information is generated by vehicle surrounding environment data, and the distance and speed information is generated by vehicle speed data and radar data.

[0008] This arrangement allows for comprehensive monitoring based on images of the vehicle's surroundings, the vehicle's own speed, and the distance between the vehicle and surrounding objects, thereby enhancing the precision of sentinel monitoring and improving the accuracy of sentinel monitoring.

[0009] In some embodiments, the acquisition of vehicle surrounding environment information and the performance of sentinel monitoring based on the environment information include: acquiring image data of object features in the vehicle surrounding environment, vehicle speed data and radar data; performing AI algorithm analysis and processing based on the vehicle speed data, image data and radar data to generate analysis results; and determining whether to turn on sentinel monitoring based on the analysis results.

[0010] With this setting, the image data, vehicle speed data and radar data collected through AI algorithm training are used to comprehensively judge whether the current conditions around the vehicle meet the conditions for turning on Sentinel Monitoring, and predict possible collision risks, and then turn on Sentinel Monitoring for precise detection.

[0011] In some embodiments, the AI ​​algorithm analysis and processing is performed based on the image information and the distance and speed information to generate the analysis results, including: determining whether the vehicle speed data is lower than a set threshold, and outputting the vehicle speed determination result; analyzing the object features and motion trends in the image data, and the object distance and speed changes in the radar data, comprehensively determining whether the environment is complex, and outputting the environment determination result; and generating the analysis results based on the vehicle speed determination result and the environment determination result.

[0012] With this setting, the AI ​​algorithm determines that the vehicle speed data is lower than the set threshold, and outputs a judgment result of a lower vehicle speed. The AI ​​algorithm determines that there are more object features and obvious motion trends in the image data, and that the distance in the radar data is closer and the speed changes faster. The environment is comprehensively judged to be complex, and a judgment result of a complex environment is output. If one of the judgment results of a lower vehicle speed and a complex environment is met, the AI ​​algorithm generates analysis results of the image data, vehicle speed data and radar data, which helps to accurately determine the start of sentinel monitoring.

[0013] In some embodiments, judging whether to turn on sentinel monitoring according to the analysis result includes: if the vehicle speed judgment result is lower than a set threshold, turning on sentinel monitoring; if the environment judgment result is complex, turning on sentinel monitoring.

[0014] With this configuration, if the vehicle speed is lower than the set threshold or the environment is complex, the sentinel monitoring will be turned on when either of the two conditions is met, making the turning on of the sentinel monitoring more reasonable and reducing the possibility of the sentinel monitoring being turned on by mistake.

[0015] In some embodiments, the method further includes: establishing a communication connection with a cloud server based on the environmental information; and uploading the vehicle's own status data and real-time data to the cloud server.

[0016] With this setting, remote monitoring and data storage can be achieved by connecting to the cloud server.

[0017] In some embodiments, the vehicle's own status data includes vehicle speed data, location data, and sentry monitoring trigger status, and the vehicle's real-time data includes image data and radar data.

[0018] With this setting, the vehicle's own status data and real-time data are uploaded to the cloud, so that the vehicle status can be checked at any time through a mobile terminal. At the same time, the intelligent algorithm in the cloud can analyze the data to provide a basis for subsequent safety decisions.

[0019] The second aspect of the present disclosure provides a C-V2X-based automobile sentinel monitoring system, the system comprising a monitoring module, for acquiring environmental information surrounding the vehicle and performing sentinel monitoring based on the environmental information; a communication module, for establishing a communication connection with surrounding vehicles, infrastructure, and pedestrian equipment based on the environmental information; an analysis and calculation module, for determining whether there is a potential threat based on a fusion analysis of the environmental information, and if so, outputting potential danger result information; an alarm module, for sending alarm information to surrounding vehicles, triggering a collaborative early warning mechanism of the infrastructure, and sending alarm information to surrounding pedestrian equipment based on the potential danger result information.

[0020] This is done so that the vehicle can send its own status information to surrounding vehicles and receive relevant information from surrounding vehicles, thus realizing functions such as collaborative warning. The connection with infrastructure enables the vehicle to obtain road condition information, traffic signal information, etc., so as to better plan the driving path. The connection with pedestrian equipment may be used to receive information such as the location and movement intention of pedestrians, thus improving the safety of interaction between pedestrians and vehicles.

[0021] A third aspect of the present disclosure provides an electronic device, comprising: a memory for storing a computer program; and a processor for implementing the C-V2X-based vehicle sentinel monitoring method as described in the first aspect when executing the computer program.

[0022] The technical effects brought about by any possible implementation of the third aspect can refer to the technical effects brought about by the above-mentioned first aspect, and will not be repeated here.

[0023] A fourth aspect of the present disclosure provides a computer storage medium having a computer program stored thereon. When the computer program is executed by a processor, the C-V2X-based vehicle sentry monitoring method as described in the first aspect is implemented.

[0024] The technical effects brought about by any possible implementation of the fourth aspect can refer to the technical effects brought about by the above-mentioned first aspect, and will not be repeated here.

[0025] Compared with the prior art, the present invention has the following advantages:

[0026] 1. Analyze the driving trajectory trends of surrounding vehicles, predict possible collision risks, and then trigger the sentinel mode for precise monitoring.

[0027] 2. Use C-V2X to quickly send alerts to surrounding vehicles, infrastructure, and pedestrian equipment, and jointly take countermeasures to achieve coordinated safety protection.

[0028] 3. The vehicle uploads real-time data to the cloud, and users can check the vehicle status at any time through mobile terminals. At the same time, the intelligent algorithm in the cloud can analyze the data to provide a basis for subsequent safety decisions.

[0029] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or be understood by implementing the present disclosure. The purpose and other advantages of the present disclosure can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 A schematic diagram of the integration of C-V2X and vehicle sentry mode provided in an embodiment of the present disclosure;

[0032] Figure 2 A schematic diagram of a C-V2X-based vehicle sentinel monitoring method flow chart provided in an embodiment of the present disclosure;

[0033] Figure 3 A flow chart of a method for enabling sentinel monitoring provided in an embodiment of the present disclosure;

[0034] Figure 4 An example diagram of a resource allocation algorithm provided in an embodiment of the present disclosure;

[0035] Figure 5 A block diagram of a C-V2X-based vehicle sentinel monitoring system provided in an embodiment of the present disclosure;

[0036] Figure 6 An operation flow chart of a C-V2X-based vehicle sentinel monitoring system provided in an embodiment of the present disclosure;

[0037] Figure 7 A structural block diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0039] The following is a brief introduction to some concepts that may be involved in the embodiments of the present disclosure.

[0040] C-V2X stands for Cellular Vehicle-to-everything, which is a communication system that uses cellular network technology (such as 4G, 5G) to connect vehicles with other road users and infrastructure. In the automotive field, C-V2X is mainly used to enhance the safety and efficiency of autonomous driving and intelligent transportation. By exchanging information such as speed, location, pedestrian detection and other data in real time, it can support cooperative driving between vehicles (V2V, Vehicle-to-Vehicle), communication between vehicles and roadside facilities (V2I, Vehicle-to-Infrastructure), and even communication between vehicles and cloud services (V2N, Vehicle-to-Network). It helps reduce traffic accidents, improve traffic flow, and promote the construction of smart cities.

[0041] The current sentinel mode of automobile safety protection has the following problems, for example, the monitoring range is limited. The viewing angle and detection distance of the vehicle camera are limited by its own performance and installation location. The horizontal viewing angle of ordinary vehicle cameras is generally between 120°-180°, and the vertical viewing angle is between 60°-90°, which cannot effectively monitor some blind spots around the vehicle. The effective detection distance of sensors such as ultrasonic sensors is usually short, generally around 2-5 meters, and it is difficult to perceive potential threats at a long distance.

[0042] Another example is untimely data transmission. When an abnormal situation is detected, the traditional data transmission method may be delayed due to network congestion or communication protocol limitations, and the information cannot be transmitted in time.

[0043] To this end, the disclosed embodiment provides a C-V2X-based vehicle sentinel monitoring method. C-V2X technology is an emerging vehicle networking communication technology with the characteristics of low latency, high reliability, and wide coverage, which enables efficient communication between vehicles and various entities in the surrounding environment. By combining it with the vehicle sentinel mode, a new dimension of protection is provided for vehicle safety. The vehicle sentinel mode uses on-board sensors to monitor abnormal activities around the vehicle in real time, while C-V2X expands its perception range and response capabilities.

[0044] For example, Figure 1 As shown, Figure 1 The schematic diagram of the integration of C-V2X and the car sentry mode provided in the embodiment of the present disclosure, the PC5 interface of C-V2X allows the vehicle to communicate directly with other nearby vehicles (V2V), infrastructure (V2I) and pedestrian devices (V2P). When the vehicle is in sentry mode, if a potential threat is detected, it can quickly send an alarm message to surrounding vehicles through C-V2X to achieve coordinated early warning. For example, if a vehicle's sentry system detects a suspicious person approaching, it will immediately notify nearby vehicles through C-V2X, and surrounding vehicles can be more vigilant or help record the incident.

[0045] For example, based on the Uu interface of C-V2X, the vehicle can connect to the cloud server to achieve remote monitoring and data storage. When the sentry mode is triggered, the vehicle uploads real-time data to the cloud, and the user can check the vehicle status at any time through the mobile terminal. At the same time, the intelligent algorithm in the cloud can analyze the data to provide a basis for subsequent safety decisions.

[0046] For example, Figure 1 In the video, a vehicle in sentry mode is shown, which contains multiple key modules. Among them are radars and cameras, which communicate with other parts of the vehicle through the CANFD protocol. The sensor transmits the collected data to the vehicle zone controller through Ethernet and CAN protocol, which may involve the transmission of various vehicle status information, such as speed, temperature, pressure, etc., to provide basic data for vehicle control and decision-making. In addition, the radar and camera are connected to the relevant parts of the vehicle through the CANFD protocol. The radar may be used to detect obstacles around the vehicle and the distance to other vehicles, while the camera is used to obtain image information around the vehicle. Together, they provide support for the safety and intelligent driving functions of the vehicle. The vehicle zone controller may play a control and coordination role in the entire vehicle system.

[0047] On the other hand, the vehicle has the PC5 interface of C-V2X and the Uu interface of C-V2X. Through the PC5 interface, the vehicle is connected to the surrounding V2 (which may represent the other vehicle in vehicle-to-vehicle communication) and infrastructure to achieve information exchange. Through the Uu interface, the vehicle is connected to the cloud server for operations such as data upload and download. At the same time, the possibility of connection with pedestrian devices (V2P) is also demonstrated, reflecting the comprehensiveness of C-V2X communication between vehicles and various entities. Pedestrian devices such as smart phones, smart wearable devices such as smart watches / bracelets, dedicated pedestrian terminal devices, etc.

[0048] It can be understood that the PC5 interface of C-V2X realizes direct communication between the vehicle and surrounding vehicles (V2), infrastructure, and possible pedestrian devices (V2P). For example, the vehicle can send its own status information to surrounding vehicles through the PC5 interface, and at the same time receive relevant information from surrounding vehicles to realize functions such as collaborative early warning. The connection with the infrastructure can enable the vehicle to obtain road condition information, traffic signal information, etc., so as to better plan the driving path. The connection with pedestrian devices may be used to receive information such as the location and movement intention of pedestrians, so as to improve the safety of interaction between pedestrians and vehicles.

[0049] It should be noted that the PC5 interface requires specific RF circuits and antennas to transmit and receive signals. These RF circuits usually include hardware components such as power amplifiers, low-noise amplifiers, and filters to process and amplify wireless signals. The antenna is responsible for radiating RF signals into space and receiving signals from other devices. For example, in the C-V2X device installed on the vehicle, there is a hardware module that matches C-V2X to implement the functions of the PC5 interface. This hardware module will be connected to the vehicle's antenna system to communicate with other vehicles or infrastructure through the antenna.

[0050] It can be understood that the Uu interface of C-V2X is connected to the cloud server, and the vehicle can upload real-time data to the cloud server, such as the vehicle's driving trajectory, sensor data, etc. The cloud server can analyze and process this data and provide services such as remote monitoring and intelligent decision-making suggestions for the vehicle. For example, the cloud server can determine whether the vehicle is in an abnormal state based on the data uploaded by the vehicle, and notify the owner or relevant agencies in a timely manner.

[0051] It should be noted that the Uu interface is a wireless interface based on cellular network technology. In the C-V2X system, it is mainly responsible for connecting vehicles and base stations (such as 4G / 5G base stations). Through this interface, vehicles can access the mobile network and realize information exchange with cloud servers and other network nodes.

[0052] like Figure 2 As shown, Figure 2The present invention provides a flow chart of a C-V2X-based vehicle sentinel monitoring method, wherein a C-V2X module is installed on the vehicle, and the method comprises the following steps:

[0053] S100: Acquire the vehicle's surrounding environment information, and perform sentinel monitoring based on the environment information.

[0054] In this embodiment, the environmental information includes image information and distance and speed information. The image information is generated by the vehicle's surrounding environment data, and the distance and speed information is generated by the vehicle speed data and radar data. When the vehicle is parked or meets specific driving monitoring conditions, such as the vehicle speed is lower than a certain threshold or the surrounding environment is complex, the vehicle sentry mode is activated based on the environmental information to monitor the surroundings of the vehicle. The vehicle then starts the on-board sensors (including cameras, radars, etc.) to start self-checking and initialization, and the C-V2X module is also initialized to prepare for establishing a communication connection.

[0055] In some embodiments, Figure 3 As shown, Figure 3 The method flow chart of enabling sentinel monitoring provided by the embodiment of the present disclosure, S100 also includes steps S101 to S103:

[0056] S101, acquiring image data of object features in the vehicle's surrounding environment, vehicle speed data, and radar data.

[0057] In this embodiment, a large amount of sample data under different vehicle speeds and environmental conditions is collected, including image data, vehicle speed data, and radar data, as well as data that meets or does not meet the conditions for starting the sentinel mode. Each sample is labeled to indicate whether it meets the conditions for starting the sentinel mode, so that the labeled sample data can be compared with the conditions for starting the sentinel mode under the image data, vehicle speed data, and radar data obtained through actual monitoring, and the conditions for starting the sentinel mode can be screened out based on the comparison results.

[0058] S102: Perform AI algorithm analysis and processing based on the vehicle speed data, image data and radar data to generate analysis results.

[0059] In this embodiment, a method combining a convolutional neural network (CNN) and a recurrent neural network (RNN) in deep learning is selected. CNN is used to process image data and extract features of objects in the environment. RNN is used to process time series data, such as changes in vehicle speed data and radar data over time.

[0060] In some embodiments, the vehicle speed data is judged to see whether it is lower than a set threshold, and the vehicle speed judgment result is output; the object features and motion trends in the image data, as well as the object distance and speed changes in the radar data are analyzed, and a comprehensive judgment is made as to whether the environment is complex, and the environment judgment result is output; and the analysis result is generated based on the vehicle speed judgment result and the environment judgment result.

[0061] In this embodiment, the selected AI algorithm is trained using labeled sample data. When the vehicle is running, the vehicle speed data, camera image data, radar data, etc. are input into the trained AI model in real time. The AI ​​model analyzes and processes the input data. For the vehicle speed data, it is determined whether it is lower than the set threshold. For the environmental data, algorithms such as CNN and RNN are used to analyze the object features and motion trends in the image, as well as the object distance and speed changes in the radar data, to comprehensively determine whether the environment is complex.

[0062] In other words, based on deep learning algorithms and neural network architecture, the massive data transmitted by C-V2X is deeply mined and analyzed. The image data is detected and classified through convolutional neural networks (CNN) to identify potential threats, such as abnormally close vehicles and suspicious persons. At the same time, the recurrent neural network (RNN) is used to process time series data, analyze the driving trajectory trends of surrounding vehicles, predict possible collision risks, and then turn on sentinel monitoring for precise monitoring.

[0063] S103: Determine whether to enable sentinel monitoring according to the analysis result.

[0064] In this embodiment, if the vehicle speed judgment result is lower than the set threshold, the sentinel monitoring is turned on; if the environment judgment result is complex, the sentinel monitoring is turned on. As long as one of the two conditions is met, the sentinel monitoring is turned on.

[0065] S200: Establish communication connections with surrounding vehicles, infrastructure, and pedestrian equipment based on environmental information.

[0066] In this embodiment, the C-V2X module establishes direct communication connections with other nearby vehicles (V2V), infrastructure (V2I), and pedestrian devices (V2P) through the PC5 interface. Through C-V2X's V2V and V2I communications, AI can share information and make collaborative decisions with other vehicles and infrastructure. Based on distributed algorithms and federated learning frameworks, the AI ​​systems of multiple vehicles jointly train and optimize safety models to improve the safety of the overall transportation system. When a vehicle's AI detects potential danger, it can quickly send alarms to surrounding vehicles and infrastructure through C-V2X, and jointly take countermeasures to achieve collaborative safety protection.

[0067] In some other embodiments, a communication connection is established with a cloud server based on environmental information; and the vehicle's own status data and real-time data are uploaded to the cloud server.

[0068] In this embodiment, the vehicle's own status data includes speed data, location data, and sentry monitoring trigger status, and the vehicle's real-time data includes image data and radar data. In other words, the vehicle uploads real-time data to the cloud server through the Uu interface of C-V2X. The uploaded data includes local data monitored by the vehicle's sensors (such as camera images, radar data, etc.) and the vehicle's own status data (such as speed, location, sentry mode trigger status, etc.).

[0069] For example, through C-V2X technology, vehicles can exchange information with surrounding vehicles and infrastructure to obtain more extensive environmental information. For example, when a vehicle detects suspicious activity nearby, it can transmit the information to surrounding vehicles through the C-V2X network to jointly increase vigilance (the other vehicle also needs to support the C-V2X network, and joint vigilance means synchronizing the corresponding danger signals to surrounding vehicles). At the same time, using the high-precision positioning function of C-V2X, the location of the incident can be determined more accurately.

[0070] For example, in the calculation of the communication range, it is assumed that the transmission power is P t , the received power is P r , the communication frequency is f, and the transmitting antenna gain is G t , the receiving antenna gain is G r , the path loss index is n, and the distance is d. According to the Friis transmission equation: where λ is the wavelength, c is the speed of light. The expression of communication distance can be derived from this formula: This formula helps determine the vehicle's communication range under different conditions, thereby better achieving enhanced monitoring range.

[0071] S300: Based on the fusion analysis of environmental information, determine whether there is a potential threat, and if so, output potential danger result information.

[0072] In this embodiment, the image information of the camera and the distance and speed information of the radar are processed comprehensively through the fusion and analysis of the vehicle-mounted sensor information to more accurately determine whether there is a potential threat. If a suspicious person approaches, a vehicle approaches abnormally, or other dangerous situations are detected, the coordinated warning process is entered.

[0073] For example, through AI calculations, reinforcement learning algorithms can also be used to optimize the sensor fusion strategy of the Sentinel mode. Combining the data features of different sensors, the fusion weights are adaptively adjusted to achieve more accurate target positioning and state estimation. In complex scenarios, such as low light and severe weather conditions, AI uses technologies such as transfer learning to quickly adapt to environmental changes and improve the reliability and robustness of the Sentinel mode.

[0074] S400: Send alarm information to surrounding vehicles based on the potential danger result information, trigger the coordinated early warning mechanism of the infrastructure, and send alarm information to surrounding pedestrian devices.

[0075] In this embodiment, the PC5 interface of C-V2X quickly sends alarm information to surrounding vehicles. The alarm information includes the vehicle's own location, potential threat type (such as suspicious persons, vehicle collision risks, etc.), danger level assessment (such as high, medium, low), etc. It is worth noting that the collaborative early warning mechanism with the infrastructure is triggered (in certain scenarios, there is a need for information interaction with infrastructure such as traffic lights and roadside units), and the vehicle sends relevant information to the infrastructure through the V2I interface of C-V2X.

[0076] It should be noted that the V2I interface in C-V2X is mainly used for information exchange between vehicles and infrastructure. The PC5 interface in C-V2X (direct short-distance communication between vehicles and infrastructure, suitable for information with high real-time requirements, such as direct communication between vehicles and traffic lights at intersections to obtain real-time signal status) and the Uu interface based on cellular networks (indirect communication between vehicles and infrastructure through base stations, suitable for long-distance or non-real-time information transmission, such as vehicles reporting location information to cloud servers, and cloud servers forwarding relevant information to infrastructure).

[0077] For example, once the car sentry monitoring is turned on, the vehicle can quickly transmit the alarm information to the relevant parties through the C-V2X network, greatly shortening the response time. The relevant parties can refer to the car manufacturer or dealer, and then synchronize the data to the car owner's app, or synchronize to the management system of the traffic management department through the established data link. For example, the car owner can receive the alarm information pushed by the mobile phone at the first time, and the nearby traffic management department can also take quick measures.

[0078] For example, in terms of delay calculation, assume that the data transmission rate is R, the packet size is S, and the propagation delay is t p , the processing delay is t proc Total delay The propagation delay can be calculated based on the distance d and the speed of light c: By analyzing and optimizing the time delay, we can ensure that the alarm information can be transmitted quickly and improve the response speed.

[0079] For example, based on the potential danger result information, alarm information is sent to surrounding vehicles to achieve coordinated protection between vehicles. When a vehicle is attacked, surrounding vehicles can receive warning information and take corresponding protective measures, such as starting cameras to record and reporting to traffic management departments.

[0080] For example, a new resource allocation algorithm is introduced, assuming that the distance between vehicle i and vehicle j is d ij , the relative speed is v ij , use S i and S j Indicates whether vehicles i and j trigger the sentry mode (1 if triggered, 0 if not), and introduces a new weight coefficient k3. The new priority function can be changed to in Indicates the impact of distance on priority. The closer the distance, the higher the priority. ij Represents the relative speed factor. A larger relative speed may mean a higher communication demand. i S j It means that if both vehicles trigger the sentinel mode, there will be an additional priority increase, and k3 controls the magnitude of this increase. Through this resource allocation algorithm, the vehicle that triggers the sentinel mode can obtain a higher communication priority in the collaborative protection, and better realize collaborative protection.

[0081] It should be noted that C-V2X is a communication protocol. Some of its communication equipment is integrated into the vehicle-side TBOX, while others have separate communication equipment modules that can be pre-installed or post-installed.

[0082] See also Figure 4 , Figure 4 An example diagram of a resource allocation algorithm provided for an embodiment of the present disclosure. For example, vehicle numbers are used to distinguish different vehicles, which are vehicle 1, vehicle 2, and vehicle 3 in the example. The distance factor value (1 / d) reflects the impact of the distance factor between vehicles on the priority. The closer the distance, the larger the value of 1 / d, which may mean a higher priority. For example, the distance factor value of vehicle 1 is 0.8, vehicle 2 is 0.4, and vehicle 3 is 0.2, indicating that vehicle 2 is closer to the relevant reference point than vehicle 1, and vehicle 3 is the farthest away.

[0083] For example, the relative speed factor value (v) reflects the impact of the relative speed factor of the vehicle on the priority. The greater the relative speed, the greater the value. For example, the relative speed factor value of vehicle 1 is 0.6, vehicle 2 is 0.9, and vehicle 3 is 0.3, indicating that the relative speed of vehicle 2 is relatively large.

[0084] For example, the sentry mode trigger status (S) indicates whether the vehicle has triggered the sentry mode. If triggered, it is "yes", and if not triggered, it is "no". In the example, vehicle 1 and vehicle 3 are not triggered, and vehicle 2 has triggered the sentry mode.

[0085] For another example, the priority function value (P) is a value calculated according to a specific priority function and is used to determine the final priority of the vehicle.

[0086] Based on the above method, the embodiment of the present disclosure also provides a C-V2X-based vehicle sentinel monitoring system 2000 corresponding to the above method, see Figure 5 and Figure 6 , Figure 5 A block diagram of a C-V2X-based vehicle sentinel monitoring system provided in an embodiment of the present disclosure, Figure 6 The present invention provides an operation flow chart of a C-V2X-based vehicle sentinel monitoring system according to an embodiment of the present invention.

[0087] The system includes a monitoring module 210, a communication module 220, an analysis and calculation module 230, and an alarm module 240. The monitoring module 210 is used to obtain the vehicle's surrounding environment information and perform sentinel monitoring based on the environmental information; the communication module 220 is used to establish a communication connection with surrounding vehicles, infrastructure, and pedestrian equipment based on the environmental information; the analysis and calculation module 230 is used to determine whether there is a potential threat based on the fusion analysis of the environmental information, and if so, output the potential danger result information; the alarm module 240 is used to send alarm information to surrounding vehicles, trigger the coordinated early warning mechanism of the infrastructure, and send alarm information to surrounding pedestrian equipment according to the potential danger result information.

[0088] In this embodiment, the monitoring module 210 may include vehicle-mounted sensors (such as cameras, radars, etc.), the communication module 220 may include a C-V2X module, the analysis and calculation module 230 may include an AI module, and the alarm module 240 may include a speaker, lighting devices, and mobile phone application push notifications. The infrastructure may include road-side units ("Road-Side Unit, RSU), traffic lights, etc., and these facilities need to have C-V2X communication functions.

[0089] In some embodiments, the vehicle-mounted software may include sentinel mode software, C-V2X communication module, AI algorithm module, and the cloud software may include data processing software, machine learning algorithm software, federated learning framework software, etc. Figure 6In the process, the on-board sensors and C-V2X module self-check and initialize, and the sentinel mode is not activated until the vehicle meets specific driving detection conditions to monitor the surrounding area of ​​the vehicle. Then the AI ​​module performs fusion analysis based on the monitored information to detect potential dangers. At the same time, the C-V2X module starts to send potential danger information to surrounding vehicles, infrastructure and pedestrian equipment, and then starts to warn. After the warning, the collected alarm data is uploaded to the cloud to collect sample data.

[0090] Based on the same inventive concept as the above disclosed content, the present disclosure also provides an electronic device 3000. Figure 7 As shown, Figure 7 The electronic device 3000 of the embodiment of the present disclosure includes at least one processor 310 and at least one memory 320 electrically connected to each other. The memory 320 is electrically connected to the processor 310, wherein the memory 320 stores instructions executable by the at least one processor 310, and the instructions are executed by the at least one processor 310 so that the at least one processor 310 can execute the method described above.

[0091] It should be noted that the electrical connection between the above-mentioned units does not necessarily mean the connection between lines. An indirect connection method can be applied to the embodiments of the present disclosure as long as the purpose of the present disclosure is achieved.

[0092] Based on the same inventive concept, the present disclosure also provides a computer storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described above is performed. The storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0093] Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A C-V2X-based vehicle sentinel monitoring method, characterized in that: The method comprises: Acquiring environmental information surrounding the vehicle, and performing sentinel monitoring based on the environmental information; Establishing communication connections with surrounding vehicles, infrastructure and pedestrian devices through C-V2X based on the environmental information; Based on the fusion analysis of the environmental information, determine whether there is a potential threat, and if so, output potential danger result information; According to the potential danger result information, alarm information is sent to surrounding vehicles, the coordinated early warning mechanism of the infrastructure is triggered, and alarm information is sent to surrounding pedestrian equipment.

2. The method according to claim 1, characterized in that The environmental information includes image information and distance and speed information, wherein the image information is generated from vehicle surrounding environment data, and the distance and speed information is generated from vehicle speed data and radar data.

3. The method according to claim 2, characterized in that The acquiring of the vehicle surrounding environment information and performing sentinel monitoring based on the environment information comprises: Acquire image data of features of objects in the vehicle's surrounding environment, vehicle speed data, and radar data; Perform AI algorithm analysis and processing based on the vehicle speed data, image data and radar data to generate analysis results; Determine whether to enable sentinel monitoring based on the analysis results.

4. The method according to claim 3, characterized in that The AI ​​algorithm analysis and processing based on the image information and the distance and speed information to generate the analysis results includes: Determine whether the vehicle speed data is lower than a set threshold value, and output a vehicle speed determination result; Analyze the object features and movement trends in the image data, as well as the distance and speed changes of the objects in the radar data, comprehensively judge whether the environment is complex, and output the environment judgment result; An analysis result is generated based on the vehicle speed determination result and the environment determination result.

5. The method according to claim 4, characterized in that The determining whether to start sentinel monitoring according to the analysis result includes: If the vehicle speed judgment result is lower than the set threshold, the sentinel monitoring is turned on; If the environmental judgment result is complex, the sentinel monitoring is turned on.

6. The method according to claim 1, characterized in that The method further comprises: Establishing a communication connection with a cloud server based on the environmental information; The vehicle's own status data and real-time data are uploaded to the cloud server.

7. The method according to claim 6, characterized in that The vehicle's own status data includes vehicle speed data, location data, and sentry monitoring trigger status, and the vehicle's real-time data includes image data and radar data.

8. The C-V2X-based vehicle sentinel monitoring system is characterized by: The system comprises: A monitoring module, used to obtain environmental information about the vehicle's surroundings and perform sentinel monitoring based on the environmental information; A communication module, used to establish a communication connection with surrounding vehicles, infrastructure and pedestrian equipment based on the environmental information; An analysis and calculation module is used to determine whether there is a potential threat based on the fusion analysis of the environmental information, and if so, output potential danger result information; The alarm module is used to send alarm information to surrounding vehicles, trigger the coordinated early warning mechanism of the infrastructure, and send alarm information to surrounding pedestrian equipment according to the potential danger result information.

9. An electronic device, characterized in that: The electronic device comprises: Memory for storing computer programs; A processor, configured to implement the C-V2X-based vehicle sentinel monitoring method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by the processor, the C-V2X-based vehicle sentinel monitoring method as described in any one of claims 1 to 7 is implemented.

Images