Road safety monitoring method, device and equipment and storage medium

Abstract

The application relates to a road safety monitoring method, device and equipment and a storage medium; in the application, road detection information sent by a UAV needs to be acquired during road safety monitoring; the road detection information is information acquired by a vehicle in a detection range of a current driving path; a target object is detected from the road detection information; whether a road risk exists is determined according to the road detection information; the road risk is a risk generated by the target object in the current driving path; if yes, a processing suggestion corresponding to the road risk is generated; and warning information is generated according to the processing suggestion. It can be seen that the road risk detection is performed through the road detection information acquired by the UAV, various risks existing in the current driving path can be discovered in time and comprehensively, the safety of the road is improved, and the installation and maintenance costs are greatly reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of road safety monitoring, and particularly relates to a road safety monitoring method, device, equipment and storage medium. BACKGROUND

[0002] Road safety monitoring technology is a technical field that has attracted much attention in recent years. Road safety monitoring technology refers to installing monitoring devices on roads to monitor road conditions in real time, and timely discovering and handling various problems on the road, such as natural disasters, weather and environment influences, and encountering animals on high-speed roads, so as to improve the safety of road travel. However, in the traditional road safety monitoring technology, the monitoring devices such as cameras and sensors installed on the road are mainly used to collect on-site information. However, these monitoring devices have problems such as inconvenient installation and high maintenance cost, and the monitoring devices cannot cover all roads and cannot timely and comprehensively monitor road safety.

[0003] Therefore, how to timely and comprehensively monitor road safety is a problem to be solved by those skilled in the art. SUMMARY

[0004] The present application provides a road safety monitoring method, device, equipment and storage medium to timely and comprehensively monitor road safety.

[0005] In a first aspect, the present application provides a road safety monitoring method, comprising:

[0006] obtaining road detection information sent by a drone; the road detection information is information obtained by a vehicle in a detection range of a current driving path;

[0007] detecting a target object from the road detection information;

[0008] determining whether there is a road risk according to the road detection information; the road risk is a risk generated by the target object on the current driving path;

[0009] if yes, generating a processing suggestion corresponding to the road risk;

[0010] generating warning information according to the processing suggestion.

[0011] Optionally, the determining whether there is a road risk according to the road detection information comprises:

[0012] judging whether the target object is in a motion state by using the road detection information;

[0013] if yes, predicting a motion trajectory of the target object by using the road detection information; and judging whether there is a first road risk according to the motion trajectory;

[0014] If no, it is determined whether there is a second road risk according to the road detection information.

[0015] Optionally, the determining whether there is a road risk according to the road detection information comprises:

[0016] detecting whether the target object is an animal by using the road detection information;

[0017] If yes, basic information of the animal is determined, and it is determined whether there is a third road risk according to the basic information and the road detection information.

[0018] Optionally, the generating the processing suggestion corresponding to the road risk comprises:

[0019] generating a switching road suggestion; wherein the switching road suggestion comprises a first driving path for avoiding the road risk.

[0020] Optionally, after the generating the target driving path to be switched, the method further comprises:

[0021] detecting whether the target object is an animal by using the road detection information;

[0022] If yes, a repellent measure option is generated according to the basic information of the animal.

[0023] Optionally, the generating the warning information according to the processing suggestion comprises:

[0024] displaying the road risk and the processing suggestion in a head-up display system and / or a display screen of the vehicle.

[0025] Optionally, after the displaying the road risk and the processing suggestion, the method further comprises:

[0026] receiving a user-triggered selection instruction;

[0027] If the selection instruction is a path selection instruction, a second driving path corresponding to the path selection instruction is determined, and a current driving path is switched to the second driving path;

[0028] If the selection instruction is a repellent measure selection instruction, the repellent measure selection instruction is sent to the unmanned aerial vehicle, so that the unmanned aerial vehicle performs a repellent measure corresponding to the repellent measure selection instruction to drive the animal away from the current driving path.

[0029] In a second aspect, the present application provides a road safety monitoring device, comprising:

[0030] acquire road detection information sent by a UAV; the road detection information is information acquired by a vehicle in a detection range of a current driving path;

[0031] detect a target object from the road detection information;

[0032] determine whether there is a road risk according to the road detection information; the road risk is a risk caused by the target object in the current driving path; if yes, trigger a first generation module;

[0033] generate a processing suggestion corresponding to the road risk;

[0034] generate warning information according to the processing suggestion.

[0035] In a third aspect, the present application provides an electronic device, comprising:

[0036] a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the road safety monitoring method according to the present application through the computer program.

[0037] In a fourth aspect, the present application further provides a computer storage medium, which stores computer executable instructions for executing the steps of the road safety monitoring method according to the present application.

[0038] The above technical solution provided by the embodiments of the present application has the following advantages compared with the prior art: in the road safety monitoring according to the present application, road detection information sent by a UAV needs to be acquired; the road detection information is information acquired by a vehicle in a detection range of a current driving path; a target object is detected from the road detection information; it is determined whether there is a road risk according to the road detection information; the road risk is a risk caused by the target object in the current driving path; if yes, a processing suggestion corresponding to the road risk is generated; and warning information is generated according to the processing suggestion. It can be seen that the road risk detection is performed by using the road detection information acquired by the UAV, various risks existing in the current driving path can be discovered in time and comprehensively, the safety of the road is improved, and the installation and maintenance costs are greatly reduced. BRIEF DESCRIPTION OF DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0040] In order to make the technical solutions of the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, for those skilled in the field, other drawings can also be obtained based on these drawings without any creative effort.

[0041] One or more embodiments are illustrated by way of example in the drawings in which like reference numerals indicate similar elements, and as such, catchwords introducing elements of the drawings do not limit the scope of the embodiments. The drawings in the accompanying drawings are not to scale.

[0042] Figure 1 A road safety monitoring method flow chart provided for the embodiments of the present application;

[0043] Figure 2 Another road safety monitoring method flow chart provided for the embodiments of the present application;

[0044] Figure 3 A display schematic diagram provided for the embodiments of the present application;

[0045] Figure 4 A road safety monitoring device structure schematic diagram provided for the embodiments of the present application;

[0046] Figure 5 An electronic device structure schematic diagram provided for the embodiments of the present application. DETAILED DESCRIPTION

[0047] In order to make the technical solutions of the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, for those skilled in the field, other drawings can also be obtained based on these drawings without any creative effort.

[0048] The following disclosure provides many different embodiments, or examples, for implementing different structures of the present application. For the purpose of simplifying the present application, the components and settings of specific examples are described in the following. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeatedly refer to numbers and / or letters in different examples. Such repetition is for the purpose of simplification and clarity, and does not indicate the relationship between the various embodiments and / or settings discussed.

[0049] The embodiments of the present application disclose a road safety monitoring method, device, equipment and storage medium, so as to timely and comprehensively monitor road safety

[0050] Referring to Figure 1 , Figure 1 A road safety monitoring method provided by the embodiment of the application is shown in a flowchart, and the method specifically comprises the following steps:

[0051] S101, acquiring road detection information sent by a UAV; the road detection information is information acquired by a vehicle in a detection range of a current driving path;

[0052] It should be noted that the UAV remote sensing technology is a means of collecting spatial remote sensing information by using a UAV, and it has the advantages of fast collection speed, wide coverage, low cost, etc., and can acquire high-resolution remote sensing images and videos in real time. Meanwhile, with the development of artificial intelligence and machine learning technology, the UAV remote sensing technology has made great breakthroughs in data processing, modeling and analysis, and can realize automatic and intelligent remote sensing information acquisition and analysis. Therefore, in the present application, in order to timely and comprehensively monitor road safety, the UAV remote sensing technology can be used to acquire road detection information acquired by a vehicle in a detection range of a current driving path, so as to realize real-time monitoring of road conditions and timely discovery and processing of various problems on the road.

[0053] When acquiring the road detection information, the UAV can use a sensor carried by the UAV to acquire the road detection information, and the sensor can be a camera, a LiDAR (Light Laser Detection and Ranging), or other environment perception devices. When acquiring the road detection information, a detection period and a detection range can be set, the detection period refers to the period of acquiring the road detection information, and the detection range is determined according to the current driving path, which can be a detection range centered on the vehicle or a detection range starting from the vehicle, and is not specifically limited herein, for example, the detection period is set to 5 minutes, and the detection range is set to 3 kilometers, then the UAV acquires the road detection information every 5 minutes, and the detection range is the road range within 3 kilometers along the current driving path starting from the current position of the vehicle.

[0054] Specifically, the road detection information in the embodiment specifically includes real-time collected road condition information and animal activity information, and the road condition information can be traffic signs on the road, obstacles on the road, etc., and the traffic signs can be speed limit signs, no parking signs, etc., which are helpful to determine the restrictions and regulations of the current road; the obstacles on the road can be other vehicles, pedestrians, bicycles, falling rocks, etc. The animal activity information refers to the detected animals, including animal appearance, animal behavior, animal activity range, etc. The type of road detection information can be picture data, video data, temperature data, humidity data, sound data, etc., and is not specifically limited herein.

[0055] After obtaining the road detection information, the unmanned aerial vehicle can transmit the road detection information to the vehicle through the wireless communication module of the unmanned aerial vehicle and the wireless communication module of the vehicle. The wireless communication module can be a 4G / 5G module, so as to realize real-time data transmission and control instruction transmission between the unmanned aerial vehicle and the vehicle, ensure that the emergency can be handled in time, and improve the safety of road driving. In addition, the unmanned aerial vehicle is loaded with a GPS (Global Positioning System) module, so as to perform accurate positioning and automatically adjust the position when necessary to obtain clearer images and data. Further, the unmanned aerial vehicle in the application can also be automatically maintained through an automatic detection and diagnosis system, including battery charging, sensor calibration, etc., which can greatly reduce the maintenance cost and prolong the service life of the unmanned aerial vehicle.

[0056] S102, detecting a target object from the road detection information;

[0057] It should be noted that the target object detected from the road detection information in the application can be a vehicle, a person, a bicycle, an animal, etc., which is not specifically limited here. Here, the detection process is described by taking the road detection information as an image, which includes four parts, namely feature extraction, target detection, semantic segmentation and instance segmentation. The feature extraction is used to extract features such as color, texture, shape, etc. from the image. The target detection is to identify specific objects in the image, such as vehicles, pedestrians or animals, by using deep learning techniques such as graph convolution neural networks (GCN). The semantic segmentation is to segment the image into different regions and label each region with a class label, which helps to determine the road and non-road regions. The instance segmentation is to further distinguish different individuals in the same class based on the semantic segmentation, and to determine the specific objects to be tracked.

[0058] In addition, when identifying the road, the application can separate the road from the surrounding environment by using image processing techniques such as edge detection, contour extraction, color segmentation, etc. At the same time, the application can also use machine learning algorithms to learn and classify the features of the road, to improve the accuracy of identification. The application can also identify traffic signs on the road by using image processing techniques such as template matching, character segmentation, feature extraction, etc.

[0059] S103, determining whether there is a road risk according to the road detection information; the road risk is a risk generated by the target object on the current driving path;

[0060] If yes, S104 is executed; if no, S101 is continuously executed;

[0061] In this embodiment, the road risk determined according to the road detection information can be specifically a road congestion risk caused by the target object, a collision risk between the target object and the vehicle, and the like. When determining whether there is a road risk by using the road detection information, the application can detect different road risks according to the type of the target object. For example, if the target object is a vehicle, it can be determined that there is a road congestion risk by using the image information in the road detection information, because there are many vehicles on the road in front and congestion has occurred. If the target object is a child running on the roadside, it can be determined that there is a collision risk because the child is unstable and can easily cross the road during running and playing. If the target object is a speed limit sign, it can be determined whether there is a speeding risk by combining the vehicle speed.

[0062] S104, generating a processing suggestion corresponding to the road risk;

[0063] It can be understood that the processing suggestion of the application needs to be generated according to a pre-set processing strategy, and the processing strategy sets factors to be considered for generating the processing suggestion, so as to generate a final processing suggestion according to each factor. The factors to be considered can specifically include the type of the road risk, the risk degree, whether the path can be changed, and the like. For example, if the road risk is a road congestion risk and the processing strategy allows the path to be changed, the generated processing suggestion can be to suggest changing a new path for driving and generating multiple new paths for the user to select. If the road risk is a collision risk and the risk degree is high, but the path cannot be changed, the generated processing suggestion can be to suggest slowing down.

[0064] S105, generating warning information according to the processing suggestion.

[0065] In this embodiment, the warning information is used to warn the user in the vehicle that there is a road risk in front, and the warning information can include the road risk and the processing suggestion. The warning information specifically includes at least one implementation form such as voice, text, picture, video, and the like. For example, if it is detected by analyzing the road detection information that there is a collision risk 3 kilometers in front, the user can be reminded by voice that there is a collision risk 3 kilometers in front, and it is suggested to change the driving path. Pictures of the 3 kilometers in front and the suggested driving path for changing are displayed on the display screen for the user to select.

[0066] As can be seen from the above, in the road safety monitoring, the road detection information sent by the unmanned aerial vehicle needs to be acquired; the road detection information is information acquired in the detection range of the current driving path of the vehicle; the target object is detected from the road detection information; it is determined whether there is a road risk according to the road detection information; the road risk is a risk generated by the target object in the current driving path; if yes, a processing suggestion corresponding to the road risk is generated; and the warning information is generated according to the processing suggestion. It can be seen that the road risk detection is performed by using the road detection information acquired by the unmanned aerial vehicle, various risks existing in the current driving path can be discovered in time and comprehensively, the safety of the road is improved, and the installation and maintenance costs are greatly reduced.

[0067] Based on the above method embodiment, in the present embodiment, when it is determined whether there is a road risk according to the road detection information, the following two aspects can be used for determination:

[0068] I. determining whether the target object is in a motion state by using the road detection information;

[0069] If yes, the motion trajectory of the target object is predicted by using the road detection information; it is determined whether there is a first road risk according to the motion trajectory; if no, it is determined whether there is a second road risk according to the road detection information.

[0070] In the present embodiment, the target object on the road can be recognized by using the image processing technology, and the attributes and behaviors of the target object can be predicted and analyzed by using the machine learning algorithm. The image processing technology specifically can be target detection, background subtraction, motion analysis and the like. When it is determined whether the target object is in a motion state, the moving target object can be detected by comparing the differences between the continuous frames, the future motion trajectory of the target object is predicted based on the historical position and speed, and the road risk is recognized by analyzing the motion trajectory. In the present embodiment, the road risk existing in the target object in the motion state is referred to as a first road risk, which can be a collision risk, a road congestion risk and the like, which is not specifically limited herein. For example, if there is a motorcycle with a high speed behind the vehicle, the target object is the motorcycle, the motion trajectory of the motorcycle can be predicted according to the driving speed and driving direction of the motorcycle, and if the motion trajectory of the motorcycle is likely to collide with the vehicle, it can be determined that there is a collision risk.

[0071] It should be noted that if the target object is in a stationary state, it can be determined whether there is a second road risk according to the road detection information. The road risk existing in the target object in the stationary state is referred to as a second road risk. For example, there are a large number of falling rocks in a curve with poor visibility in front of the vehicle, the falling rocks are the target objects in the stationary state, the range of the falling rocks is large and the vehicle cannot pass through, and it can be determined that there is a road congestion risk.

[0072] II. Detecting whether the target object is an animal by using the road detection information;

[0073] If yes, basic information of the animal is determined, and whether there is a third road risk is judged according to the basic information and the road detection information.

[0074] In the embodiment, the animal on the road can be recognized by an image processing technology, which can be a target detection, feature extraction, classifier training and the like. Then, whether there is a third road risk is determined according to the basic information of the animal. In the embodiment, the basic information refers to basic data of the animal, such as the type of the animal, the protection type, the natural enemy, the behavior prone to appear, the running speed, whether the animal is aggressive and the like. Whether there is a road risk can be determined by combining the basic information of the animal with the road detection information. For example, the target object is an animal, and it is found by recognition that the animal is a deer, and it is recorded in the basic information that the deer will suddenly run after being frightened. At this time, it can be determined that there is a collision risk, which refers to the risk that the deer and the vehicle will collide. However, if it is detected by the road detection information that the deer is far away from the road, and according to the running speed of the deer and the driving speed of the vehicle, it is calculated that even if the deer runs, it cannot collide with the vehicle. At this time, it can be determined that there is no collision risk.

[0075] As can be seen from the above, after the target object is detected by the road detection information, whether there is a road risk can be determined according to the running state, type of the target object and the road detection information. If there is a road risk, an alarm information is generated in time to remind the driver. In this way, the safety of the road can be improved.

[0076] Referring to Figure 2 , Figure 2 Another road safety monitoring method provided by the embodiment of the application is provided, and a flowchart of the method is shown. The method specifically includes the following steps:

[0077] S201, acquiring road detection information sent by a UAV; the road detection information is information acquired by a vehicle in a detection range of a current driving path;

[0078] S202, detecting a target object from the road detection information;

[0079] S203, determining whether there is a road risk according to the road detection information; the road risk is a risk generated by the target object in the current driving path;

[0080] If yes, S204 is executed; if no, S201 is continuously executed;

[0081] S204, generating a road switching suggestion; wherein the road switching suggestion includes a first driving path for avoiding the road risk;

[0082] S205, detecting whether the target object is an animal by using the road detection information;

[0083] If yes, S206 is performed; if no, S207 is performed;

[0084] S206, generating a repelling measure option according to the basic information of the animal;

[0085] S207, displaying the road risk and the processing suggestion in the head-up display system and / or the display screen of the vehicle.

[0086] In the embodiment, if it is determined that there is a road risk according to the road detection information, a processing suggestion corresponding to the road risk can be generated. In the embodiment, the processing suggestion includes a switching road suggestion, which is used to suggest the user to avoid the road risk by switching a new path. In the embodiment, the generated new path is referred to as a first driving path, and the number of the generated first driving paths can be multiple, so as to be selected by the user.

[0087] It should be noted that the animal repelling technology in the conventional scheme is mainly realized by physical isolation and sound wave driving. For example, a fence is arranged beside a highway to prevent animals from entering the highway, or a sound wave device is arranged beside the highway to drive animals away by emitting high-frequency sound waves. However, these methods often have poor effects and cannot fundamentally solve the problem. Therefore, in the present application, if it is detected that the road risk is caused by animals, a targeted repelling measure option can be generated according to the basic information of the animals when generating the processing suggestion. The repelling measure option refers to a measure option for driving animals away. For example, if the type of the animal is recorded as a deer in the basic information of the animal, the generated repelling measure option can be releasing deer repelling liquid, emitting ultrasonic waves, emitting the roar of an animal predator (such as a lion or a tiger), and the like, so as to efficiently drive the animals away.

[0088] Further, after the processing suggestion is generated, the application can also generate warning information according to the processing suggestion. In the embodiment, the processing suggestion can be displayed on the head-up display system and / or display screen of the vehicle to timely alert the user and let the user select the corresponding processing suggestion. The head-up display system is specifically a HUD (Head Up Display), which can project the speed, navigation and other important driving information onto the windshield in front of the driver, so that the driver can see the speed, navigation and other important driving information without looking down or turning his head. Therefore, the application displays the road risk and processing suggestion on the head-up display system, so that the driver can more conveniently obtain the required information and improve the driving experience. For example, there is a deer in front of the road, and it is determined that there is a collision risk by analysis. At this time, the relevant information can be displayed on the HUD in picture-in-picture, and the displayed information specifically includes the 3D model of the animal, the type of the animal, the distance between the animal and the vehicle, the existing road risk, and the processing suggestion: switching road suggestion and evading measure option. Further, the warning information generated by the embodiment can also be in the form of voice, which alerts the driver through voice that there is a road risk in front of the road and the corresponding processing suggestion.

[0089] It should be noted that after the application displays the road risk and processing suggestion, it also needs to receive a selection instruction triggered by the user. If the selection instruction is a path selection instruction, a second driving path corresponding to the path selection instruction is determined, and the current driving path is switched to the second driving path. If the selection instruction is an evading measure selection instruction, the evading measure selection instruction is sent to the unmanned aerial vehicle to make the unmanned aerial vehicle execute the evading measure corresponding to the evading measure selection instruction to drive the animal away from the current driving path. The path selection instruction can be a selection instruction triggered by the user through the processing suggestion displayed on the touch screen, a selection instruction output by the user in the form of voice, or a selection instruction triggered by the user through a gesture, which is not specifically limited here. The user can select which processing suggestion to execute according to actual needs. If the user triggers the path selection instruction, the second driving path to be switched can be determined according to the path selection instruction, and the current driving path is switched to the second driving path. For example, the switching road suggestion includes path 1, path 2 and path 3, the user can directly output the voice "switch path 2" to trigger the selection instruction of path 2, so the second driving path to be switched determined by the instruction is path 2, and path 2 is taken as the current driving path.

[0090] If the user selects the trigger the repellent measure selection instruction, the repellent measure selection instruction needs to be sent to the drone, the instruction includes the user selected repellent measure, and the selected repellent measure can be one or more. After the drone receives the repellent measure selection instruction, it needs to execute the repellent measure corresponding to the repellent measure selection instruction to drive the animals away from the current driving path, for example: the repellent measure options include: 1: release deer repellent, 2: emit ultrasonic waves, 3: emit the roar of the animal's natural enemy. At this time, the user selects options 1 and 2, and the selection instruction is sent to the drone. The drone can drive animals away by releasing deer repellent and emitting ultrasonic waves.

[0091] Here, a specific road safety monitoring method is provided. In this embodiment, a DJI Mavic Pro drone is specifically selected, which carries a camera with a resolution of 4K, a flight height of up to 6000 meters, and a maximum flight time of up to 27 minutes. A GPS module is loaded on the drone for accurate positioning. Wireless communication modules are installed on the drone and the vehicle to realize real-time data transmission and control instruction transmission between the two. The drone is deployed above the road to achieve accurate positioning through GPS navigation. The drone performs a cruise every 5 minutes, covering a range of 3 kilometers each time. When the drone's power reaches 20%, it returns to the top of the vehicle for wireless charging. During the cruise, the drone collects road conditions and animal activity information in real time through the camera and sensors mounted on it, and transmits these road detection information to the vehicle in real time through the wireless communication module. After receiving the data transmitted by the drone, the vehicle processes it automatically through the built-in intelligent algorithm, including image recognition, modeling and analysis, etc. These algorithms can quickly identify road risks and animal shapes and match the corresponding repellent measures.

[0092] Specifically, if the drone detects animals in front, it collects image data or video data and sends it to the vehicle. The processing process performed by the intelligent algorithm of the vehicle is as follows:

[0093] 1. Data preprocessing: preprocessing specifically includes filtering noise and format conversion; Because the drone may encounter problems such as light changes and obstructions when shooting, it needs to perform image enhancement, denoising and other operations on the data; and convert the original data into an easy-to-process format, such as common image or video file format.

[0094] 2. Feature extraction: Use computer vision techniques to identify the contours, textures, and other key features of the animal. In this embodiment, OpenCV (Open Source Computer Vision Library) can be used for image processing, and deep learning methods can be used to extract features from the image. Convolutional Neural Networks (CNN) can be used to extract features in this embodiment.

[0095] 3. Model training: In this embodiment, a labeled animal image is used to train an animal recognition model that can accurately identify different types of animals and estimate their position, posture, etc. The animal recognition model can be a classifier or a detector.

[0096] 4. 3D modeling and rendering (Blender creates 3D models): After identifying the specific animal through the above steps, appropriate models can be selected from the existing 3D model library, or new 3D models can be created using point cloud data and structured light technology. Rendering techniques are used to place the 3D model in the actual environment, making it look realistic.

[0097] 5. Display: Integrate the animal's 3D model, basic information, road hazards, and handling suggestions into virtual reality (VR) or directly display them on the HUD.

[0098] 6. Interaction: Users can choose and execute corresponding handling suggestions through touchscreens, gesture recognition, or voice commands.

[0099] Reference Figure 3 , Figure 3 A display schematic provided by the embodiments of the present application; through Figure 3 It can be seen that the present application displays the species, distance, protection type, size, animal natural enemy, and avoidance measures of the animal on the HUD, and displays the animal 3D model, avoidance route, and vehicle driving information on the HUD. At the same time, it also prompts through voice and central control display screen: 2 kilometers ahead, an animal is found, please slow down and drive carefully; after playing the above information, it can also prompt through voice and central control display screen: it is recommended to choose avoidance measure 1 to change route, if the user triggers the instruction to choose avoidance measure 1 at this time, the path is changed; if the user triggers other solutions at this time, it is reminded again: the current route can be changed to avoid, please change the route. If there is no suitable avoidance route, the user can choose avoidance measure 2 and avoidance measure 3 to release deer repellent and ultrasonic drive. The avoidance measures of the present application can be used in combination according to specific conditions to improve the repellent effect.

[0100] In summary, the present application can obtain high-resolution remote sensing images and videos of the road in real time through unmanned aerial vehicle remote sensing technology when monitoring road safety, thereby discovering and handling various problems on the road, such as natural disasters and animals, in a timely manner, and improving the safety of road travel. Compared with traditional camera and sensor devices, unmanned aerial vehicle remote sensing technology has the advantages of fast collection speed, wide coverage, low cost, and the like, and therefore has a broad application prospect in the field of road safety monitoring. Secondly, the present application can identify road risks and animal morphology through an unmanned aerial vehicle when driving away animals, and match corresponding driving measures, such as spraying deer driving water, ultrasonic waves, and the roar of animal natural enemies, thereby effectively solving the problems of poor effect and inability to fundamentally solve the problem of traditional animal driving methods. Finally, the present application realizes automatic and intelligent rapid acquisition of spatial remote sensing information, completes remote sensing data processing, modeling and analysis, and displays on the vehicle HUD, thereby improving the application efficiency and accuracy of unmanned aerial vehicle remote sensing technology. The technical scheme combines unmanned aerial vehicle remote sensing technology, road safety monitoring technology, and animal driving system technology, and realizes efficient and accurate road safety monitoring and animal driving.

[0101] Referring to Figure 4 , Figure 4 A road safety monitoring device structure schematic diagram is provided for an embodiment of the present application, and the device specifically includes:

[0102] The acquisition module 11 is configured to acquire road detection information sent by an unmanned aerial vehicle; the road detection information is information acquired by a vehicle in a detection range of a current driving path;

[0103] The first detection module 12 is configured to detect a target object from the road detection information;

[0104] The second detection module 13 is configured to determine whether there is a road risk according to the road detection information; the road risk is a risk generated by the target object on the current driving path; if so, the first generation module is triggered;

[0105] The first generation module 14 is configured to generate a processing suggestion corresponding to the road risk;

[0106] The second generation module 15 is configured to generate warning information according to the processing suggestion.

[0107] As an optional embodiment, the second detection module includes:

[0108] The first judgment unit is configured to determine whether the target object is in a motion state by using the road detection information; if so, the prediction unit is triggered; if not, the third judgment unit is triggered;

[0109] The prediction unit is configured to predict a motion trajectory of the target object by using the road detection information;

[0110] a second determining unit, configured to determine whether a first road risk exists according to the motion track;

[0111] a third determining unit, configured to determine whether a second road risk exists according to the road detection information.

[0112] As an optional embodiment, the second detecting module comprises:

[0113] a first detecting unit, configured to detect whether the target object is an animal by using the road detection information, and trigger the determining unit if the target object is the animal;

[0114] a determining unit, configured to determine basic information of the animal;

[0115] a fourth determining unit, configured to determine whether a third road risk exists according to the basic information and the road detection information.

[0116] As an optional embodiment, the first generating module comprises:

[0117] a first generating unit, configured to generate a switching road suggestion, wherein the switching road suggestion comprises a first driving path for avoiding the road risk.

[0118] As an optional embodiment, the first generating module further comprises:

[0119] a second detecting unit, configured to detect whether the target object is an animal by using the road detection information, and trigger the second generating unit if the target object is the animal;

[0120] a second generating unit, configured to generate a repellent measure option according to the basic information of the animal.

[0121] As an optional embodiment, the second generating module is specifically configured to display the road risk and the processing suggestion in a head-up display system and / or a display screen of the vehicle.

[0122] As an optional embodiment, the device further comprises:

[0123] a receiving module, configured to receive a selection instruction triggered by a user, trigger the determining module if the selection instruction is a path selection instruction, and trigger the sending module if the selection instruction is a repellent measure selection instruction;

[0124] a determining module, configured to determine a second driving path corresponding to the path selection instruction, and switch a current driving path to the second driving path;

[0125] The sending module is configured to send the repelling measure selection instruction to the unmanned aerial vehicle, so that the unmanned aerial vehicle performs a repelling measure corresponding to the repelling measure selection instruction to drive the animal away from the current driving path.

[0126] With regard to the apparatus in the above embodiments, the specific manners in which the respective modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0127] Referring to Figure 5 , Figure 5 An electronic device structure schematic diagram is provided for the embodiments of the present application, and the electronic device specifically includes:

[0128] The processor 21, the memory 22, and the computer program stored in the memory 22 and executable on the processor 21, the processor 21 executes the steps of the road safety monitoring method described in any method embodiment above through the computer program.

[0129] The processor 21 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in the form of at least one of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 21 can also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a CPU (Central Processing Unit). The coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 can be integrated with a GPU (Graphics Processing Unit) that is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 can also include an AI (Artificial Intelligence) processor for processing machine learning-related computing operations.

[0130] The memory 22 can include one or more computer-readable storage media. The computer-readable storage media can be non-transitory. The memory 22 can also include high-speed random access memory and can include nonvolatile memory, such as one or more magnetic disk storage devices, optical storage devices, flash memory devices, or other nonvolatile solid-state storage devices. In this embodiment, the memory 22 is at least used to store the following computer program 221, wherein the computer program is loaded and executed by the processor 21, and can implement the related steps in the road safety monitoring method disclosed in any of the preceding embodiments. In addition, the resources stored in the memory 22 can also include an operating system 222, data 223, etc., and the storage mode can be temporary storage or permanent storage. The operating system 222 can include Windows, Unix, Linux, etc.

[0131] In some embodiments, the electronic device can further include a display screen 23, an input / output interface 24, a communication interface 25, a sensor 26, a power supply 27, and a communication bus 28.

[0132] Of course, Figure 5 The structure of the electronic device shown does not constitute a limitation on the electronic device in the embodiments of the present application. In actual applications, the electronic device can include more or fewer components than those shown, or some components can be combined. Figure 5 The structure of the electronic device shown does not constitute a limitation on the electronic device in the embodiments of the present application. In actual applications, the electronic device can include more or fewer components than those shown, or some components can be combined.

[0133] In another exemplary embodiment, a computer storage medium is also provided, and the program instructions are executed by the processor to implement the steps of the road safety monitoring method described in any of the method embodiments. The storage medium can include a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0134] Optionally, the specific examples in the embodiments can refer to the examples described in the above-described embodiments, and the embodiments will not be described here.

[0135] It is to be understood that the terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises", "comprising", "includes", "including" and "has" are inclusive and therefore specify the presence of stated features, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring their performance in the particular order

[0136] The above description is merely that of the specific embodiments of the application and as such is not to be taken in a limiting sense. Various modifications and alterations of the embodiments described herein will become apparent to those skilled in the art from the foregoing description, which does not limit the generality presented. It is the intention that all such modifications and alterations be considered equaliy by the spirit and scope of this application. It is therefore intended to cover in the appended claims all such changes and alterations that come within the scope of this application.

Claims

1. A road safety monitoring method, characterized in that, include: Acquire road detection information sent by the drone; The road detection information is the information obtained by the vehicle within the detection range of its current driving path; Detect target objects from the road detection information; The presence of road risk is determined based on the road detection information; the road risk refers to the risk generated by the target object along its current travel path. If so, then generate a handling suggestion corresponding to the road risk; A warning message is generated based on the processing recommendations; The step of determining whether a road risk exists based on the road detection information includes: The road detection information is used to determine whether the target object is in motion. If so, the road detection information is used to predict the target object's trajectory based on its historical position and speed; the trajectory is then used to determine whether a first road risk exists. If not, then determine whether there is a second road risk based on the road detection information.

2. The road safety monitoring method according to claim 1, characterized in that, The step of determining whether a road risk exists based on the road detection information includes: The road detection information is used to determine whether the target object is an animal; If so, the basic information of the animal is determined, and the presence of a third road risk is determined based on the basic information and the road detection information.

3. The road safety monitoring method according to claim 1, characterized in that, The generation of processing suggestions corresponding to the road risks includes: Generate a road switching suggestion; wherein the road switching suggestion includes a first driving route that avoids the road risk.

4. The road safety monitoring method according to claim 3, characterized in that, After generating the target driving route to be switched, the following is also included: The road detection information is used to determine whether the target object is an animal; If so, then generate avoidance measures options based on the animal's basic information.

5. The road safety monitoring method according to any one of claims 1 to 4, characterized in that, The generation of warning information based on the processing suggestion includes: The road risks and the proposed solutions are displayed on the vehicle's head-up display system and / or screen.

6. The road safety monitoring method according to claim 5, characterized in that, Following the presentation of the road risks and the proposed solutions, the following is also included: Receive selection commands triggered by the user; If the selection instruction is a route selection instruction, then the second driving route corresponding to the route selection instruction is determined, and the current driving route is switched to the second driving route; If the selection instruction is an avoidance measure selection instruction, then the avoidance measure selection instruction is sent to the drone so that the drone executes the avoidance measure corresponding to the avoidance measure selection instruction to drive the animal away from the current travel path.

7. A road safety monitoring device, characterized in that, include: The acquisition module is used to acquire road detection information sent by the drone; The road detection information is the information obtained by the vehicle within the detection range of its current driving path; The first detection module is used to detect target objects from the road detection information; The second detection module is used to determine whether there is a road risk based on the road detection information; the road risk is the risk generated by the target object on the current driving path. If so, then the first generation module is triggered; The first generation module is used to generate processing suggestions corresponding to the road risks; The second generation module is used to generate warning information based on the processing suggestions; The second detection module is used for: The road detection information is used to determine whether the target object is in motion. If so, the road detection information is used to predict the target object's trajectory based on its historical position and speed; the trajectory is then used to determine whether a first road risk exists. If not, then determine whether there is a second road risk based on the road detection information.

8. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor performs the steps of the road safety monitoring method according to any one of claims 1 to 6 of this application through the computer program.

9. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions for performing the steps of the road safety monitoring method according to any one of claims 1 to 6 of this application.

Images