Expressway disease dynamic early warning system with sensing calculation equipment carried by unmanned aerial vehicle

Abstract

The invention relates to an expressway disease dynamic early warning system with unmanned aerial vehicle-mounted sensing and calculation equipment, and belongs to the technical field of intelligent traffic, the expressway disease dynamic early warning system comprises an operation platform, an unmanned aerial vehicle, a sensing and calculation integrated roadside base station, an unmanned aerial vehicle nest and a vehicle-mounted unit, the unmanned aerial vehicle-mounted sensing and calculation integrated roadside base station collects expressway pavement pictures in real time, and sends the expressway pavement pictures to the unmanned aerial vehicle nest; the image is reported to the unmanned aerial vehicle nest through the image transmission system, and the unmanned aerial vehicle nest transmits the expressway pavement image back to the operation center through the local area network; and the sensing, communication and calculation integrated roadside base station identifies pavement disease information in real time, generates a V2X standard message set containing pavement abnormal information and dynamically broadcasts the V2X standard message set to the vehicle-mounted unit. According to the invention, the unmanned aerial vehicle carries the sensing and calculating intelligent equipment to fly on the expressway, and the sensing and calculating intelligent roadside equipment acquires the expressway pavement picture in real time, so that the inspection efficiency is greatly improved, the traditional mode of finding the roadside by a vehicle is overturned to be the mode of finding the vehicle on the roadside, and accidents are greatly avoided.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a highway disease dynamic early warning system equipped with a sensing and computing device by an unmanned aerial vehicle. Background Art

[0002] As the total mileage of my country's expressways continues to rise, daily inspections of expressways and reminders of abnormal road conditions beyond the visual range are becoming increasingly prominent problems.

[0003] Initial highway inspections were conducted manually, which had problems such as low inspection efficiency, high labor and machinery costs, and a large risk base.

[0004] With the development of drone technology, drones can be used to replace manual inspections, but the following problems still exist:

[0005] 1) Traditional roadside perception system equipment is independent and generally consists of cameras, roadside equipment and edge perception equipment. The data processing delay of the entire system is relatively high.

[0006] 2) Traditional roadside equipment is installed in a fixed position and is deployed in very small numbers due to its high cost. Vehicles equipped with OBUs need to travel within the communication range of the RSU to provide warnings. The communication distance between roadside equipment and on-board equipment is generally around 600 meters, which gives drivers a short reaction time in high-speed scenarios. Summary of the invention

[0007] In order to solve the above-mentioned problems in the prior art, the present invention provides a highway disease dynamic early warning system using an unmanned aerial vehicle equipped with sensing and computing equipment.

[0008] A highway disease dynamic early warning system using a drone equipped with a sensing, communication and computing device, including an operation platform, a drone, a sensing, communication and computing integrated roadside base station, a drone nest and a vehicle-mounted unit;

[0009] The operation platform is responsible for setting the route and timing of the drone patrol mission, and receiving video images and road anomaly information during the drone patrol mission;

[0010] The drone is used to perform patrol tasks and is equipped with a roadside base station that integrates sensing, communication and computing;

[0011] The sensing, communication and computing integrated roadside base station is used to collect video images of the highway road surface in real time and report them to the drone nest, and identify the highway road surface at the same time. When an abnormality is identified, a V2X standard message set containing the abnormal road surface information is generated and dynamically broadcasted;

[0012] The drone nest is responsible for managing the mission execution and maintenance of the drone, and serves as a drone data transfer center to receive the video images collected by the drone's integrated sensing, communication and computing roadside base station and the generated road surface anomaly information, and transmit it back to the operation platform;

[0013] The on-board unit is used to receive the V2X standard message set generated by the sensing, communication and computing integrated roadside base station.

[0014] Furthermore, the drone nest and the drone transmit images of the highway road surface through an image transmission system.

[0015] Furthermore, the drone nest communicates with the operation platform through a local area network to implement the dispatching of drone patrol tasks and the uploading of collected video images and road anomaly information.

[0016] Furthermore, the sensing, communication and computing integrated roadside base station is a device that integrates a camera, a V2X communication module and an edge computing unit.

[0017] Furthermore, when the integrated sensing, communication and computing roadside base station identifies a road surface abnormality, the road surface abnormality information includes disease type information and disease location information. The disease location information outputs longitude and latitude information through the high-precision positioning module of the integrated sensing, communication and computing roadside base station.

[0018] Furthermore, the recognition process of the highway road surface in the sensing, communication and computing integrated roadside base station is specifically as follows:

[0019] First, the sensing, communication and computing integrated roadside equipment mounted on the drone captures images in real time, and obtains the target image by slicing the video frame by frame;

[0020] Then, the target image is identified through the target algorithm recognition model. When a road abnormality is identified, the road abnormality information is conditioned into a V2X standard message set.

[0021] Finally, dynamic broadcasting is carried out according to the V2X standard message set to dynamically remind the driver of abnormal conditions ahead.

[0022] Furthermore, the training process of the target algorithm recognition model is as follows: first, the training materials are collected through the early routine inspections of drones or manual inspections, and then the training materials are labeled and trained to obtain the recognition model; finally, the target model is obtained through model quantization.

[0023] Furthermore, the dynamic broadcast of the V2X standard message set is specifically as follows: when a road abnormality is identified, the warning position is updated according to the real-time position of the roadside base station with integrated sensing and communication computing, and the confidence of the road abnormality event is dynamically calculated based on the distance and time difference between the road abnormality event and the roadside base station with integrated sensing and communication computing.

[0024] The beneficial effects of the present invention are as follows: the present invention utilizes a drone carrying a sensing and computing intelligent device to fly on a highway, and the sensing and computing intelligent roadside device collects images of the highway pavement in real time, greatly improving the inspection efficiency. At the same time, the highly integrated advantages of the sensing and computing intelligent roadside device are utilized to perform image algorithm processing on the collected images locally in real time, dynamically and accurately locate the highway disease information and package it according to the standard message set of LTE-V, utilize the flight capability of the drone, and dynamically broadcast abnormal situations to the rear vehicles over ultra-long distances using LTE-V technology, subverting the traditional "car looking for the roadside" mode to "roadside looking for the car", greatly avoiding the occurrence of accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is the system data flow diagram of the present invention;

[0026] Figure 2 This is the structural diagram of the integrated roadside equipment for sensing, communication and computing;

[0027] Figure 3 This is a flow chart for the recognition of highway pavement by the integrated sensing and computing roadside equipment. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Example 1: Reference Figure 1 As shown, a dynamic early warning system for highway diseases in which a drone is equipped with a sensing, communication and computing device in an embodiment of the present invention comprises an operation platform, a drone, a sensing, communication and computing integrated roadside base station, a drone nest and a vehicle-mounted unit; the operation platform is responsible for setting the route and timing of the drone patrol mission, and receiving video images and road surface abnormality information during the drone patrol mission; the drone is used to perform patrol missions; the sensing, communication and computing integrated roadside base station is used to collect video images of the highway road surface in real time and report them to the drone nest, and at the same time identify the highway road surface, and when a road surface abnormality is identified, a V2X standard message set containing road surface abnormality information is generated and dynamically broadcast; the drone nest is responsible for managing the task execution and maintenance of the drone, and serves as a drone data transfer center, receiving the video images collected by the sensing, communication and computing integrated roadside base station on the drone and the road surface abnormality information generated, and transmitting them back to the operation platform; the vehicle-mounted unit is used to receive the V2X standard message set generated by the sensing, communication and computing integrated roadside base station.

[0030] The drone is equipped with an integrated sensing, communication and computing roadside base station, which collects highway pavement images in real time and reports them to the drone nest through the image transmission system. The drone nest transmits the highway pavement images back to the operation center through the local area network; the integrated sensing, communication and computing roadside base station identifies pavement disease information in real time and outputs the latitude and longitude information of the disease through its own high-precision positioning module. At the same time, it innovatively uses the drone's maneuverability to install a "wing" on the roadside equipment, and dynamically transmits the disease information to the rear vehicle according to the standard V2X message set (RSI, RSM), reminding the driver of abnormalities on the road ahead.

[0031] In this embodiment, if Figure 2 As shown, the sensing, communication and computing integrated roadside base station is a device that integrates a camera, a V2X communication module and an edge computing unit. It breaks the disadvantages of high cost, difficult operation and maintenance, and large latency of traditional split-type perception systems, and performs ultra-low latency perception, calculation and transmission of abnormal targets, greatly improving the driver's confidence in high-speed abnormal situations. The sensing, communication and computing integrated roadside equipment adopts the idea of ​​separate design of the core board and the baseboard, and the two parts are connected by a high-speed backplane connector. The C-V2X module and the NPU module used for calculation are connected through a high-speed Serdes interface, and the connection and communication of the two modules are realized with the help of Xilinx's Serdes IP.

[0032] In this embodiment, when the sensing, communication and computing integrated roadside base station identifies a road surface abnormality, the road surface abnormality information includes disease type information and disease location information. The disease location information is output as longitude and latitude information through the high-precision positioning module of the sensing, communication and computing integrated roadside base station.

[0033] like Figure 3 As shown in the figure, the recognition process of the highway road surface in the sensing, communication and computing integrated roadside base station is as follows:

[0034] First, the sensing, communication and computing integrated roadside equipment mounted on the drone captures images in real time, and obtains the target image by slicing the video frame by frame;

[0035] Then, the target image is identified through the target algorithm recognition model. When a road surface abnormality is identified, the road surface abnormality information is conditioned into a V2X standard message set, that is, the road surface abnormality information is combined according to the format of the V2X standard message set to obtain the V2X standard message set;

[0036] Finally, dynamic broadcasting is carried out according to the V2X standard message set to dynamically remind the driver of abnormal conditions ahead.

[0037] Among them, the training process of the target algorithm recognition model is as follows: first, the training materials are collected through the early daily drone inspections or manual inspections, and then the training materials are labeled and trained to obtain the recognition model; finally, the target model is obtained through model quantification.

[0038] In this embodiment, the maneuverability of the drone is utilized to carry the roadside base station with integrated sensing, communication and computing for dynamic sensing and message publishing. The drone is equipped with the roadside equipment with integrated sensing, communication and computing and flies in the preset reverse traffic direction. The main message parameters are shown in Table 1.

[0039] Table 1

[0040]

[0041] The dynamic broadcast of the V2X standard message set is as follows: when a road abnormality is identified, the warning position is updated according to the real-time position of the roadside base station of the integrated sensing and computing, and the confidence of the road abnormality event is dynamically calculated based on the distance and time difference between the road abnormality event and the roadside base station of the integrated sensing and computing. Subsequent vehicles need to make real-time decisions based on the received message set (such as whether to slow down, change lanes or stop, etc.); confidence, as a quantitative indicator of data reliability, can provide important support for the decision-making process;

[0042] The confidence calculation process is as follows:

[0043] 1) Calculate distance

[0044]

[0045] Where d (unit: km) is the dynamic distance from the sensing and computing equipment to the event, r is the radius of the earth (about 6371 km), (φ1, λ1) and (φ2, λ2) are the latitude and longitude of the sensing and computing integrated roadside equipment location and the event location, respectively.

[0046] 2) Calculate the time difference

[0047] t = t2 – t1,

[0048] Where t (unit: second) is the time that has passed since the event occurred, t2 is the real-time time of the integrated roadside sensing and computing equipment, and t1 is the time when the event occurred.

[0049] 3) Evaluate confidence

[0050] C=w d × t ,

[0051] Among them, W d is the distance weight, W t is the time weight.

[0052] 4) Calculate confidence

[0053] C=w d × t ,

[0054] Where C is the event confidence.

[0055] In the description of the embodiments of the present invention, the terms "first", "second", "third", and "fourth" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", and "fourth" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0056] In the description of the embodiments of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "install", "connect", "connect", and "assemble" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] In the description of the embodiments of the present invention, the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " herein generally indicates that the associated objects before and after are in an "or" relationship.

[0058] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A highway disease dynamic early warning system using drones equipped with sensing and computing equipment, characterized in that: Including operation platform, drone, integrated sensing, communication and computing roadside base station, drone nest and vehicle-mounted unit; The operation platform is responsible for setting the route and timing of the drone patrol mission, and receiving video images and road anomaly information during the drone patrol mission; The drone is used to perform patrol tasks and is equipped with a roadside base station that integrates sensing, communication and computing; The sensing, communication and computing integrated roadside base station is used to collect video images of the highway road surface in real time and report them to the drone nest, and identify the highway road surface at the same time. When an abnormality is identified, a V2X standard message set containing the abnormal road surface information is generated and dynamically broadcasted; The drone nest is responsible for managing the mission execution and maintenance of the drone, and serves as a drone data transfer center to receive the video images collected by the drone's integrated sensing, communication and computing roadside base station and the generated road surface anomaly information, and transmit it back to the operation platform; The on-board unit is used to receive the V2X standard message set generated by the sensing, communication and computing integrated roadside base station.

2. According to claim 1, a highway disease dynamic early warning system using a drone equipped with a sensing and computing device is characterized in that: The drone nest and the drone transmit images of the highway road surface through the image transmission system.

3. According to claim 1, a highway disease dynamic early warning system using a drone equipped with a sensing and computing device is characterized in that: The drone nest communicates with the operation platform through a local area network to implement the dispatching of drone patrol tasks and the uploading of collected video images and road anomaly information.

4. According to claim 1, a highway disease dynamic early warning system using a drone equipped with a sensing and computing device is characterized in that: The sensing, communication and computing integrated roadside base station is a device that integrates a camera, a V2X communication module and an edge computing unit.

5. According to claim 1, a highway disease dynamic early warning system using a drone equipped with a sensing and computing device is characterized in that: When the sensing, communication and computing integrated roadside base station identifies a road surface abnormality, its road surface abnormality information includes disease type information and disease location information. The disease location information is output as longitude and latitude information through the high-precision positioning module of the sensing, communication and computing integrated roadside base station.

6. The highway disease dynamic early warning system using a drone equipped with a sensing and computing device according to claim 1 is characterized in that: The specific process of identifying the highway road surface in the sensing, communication and computing integrated roadside base station is as follows: First, the sensing, communication and computing integrated roadside equipment mounted on the drone captures images in real time, and obtains the target image by slicing the video frame by frame; Then, the target image is identified through the target algorithm recognition model. When a road abnormality is identified, the road abnormality information is conditioned into a V2X standard message set. Finally, dynamic broadcasting is carried out according to the V2X standard message set to dynamically remind the driver of abnormal conditions ahead.

7. According to claim 1, a highway disease dynamic early warning system using a drone equipped with a sensing and computing device is characterized in that: The training process of the target algorithm recognition model is as follows: first, the training materials are collected through daily drone inspections or manual inspections in the early stage, and then the training materials are labeled and trained to obtain the recognition model; finally, the target model is obtained through model quantization.

8. According to claim 1, a highway disease dynamic early warning system using a drone equipped with a sensing and computing device is characterized in that: The dynamic broadcast of the V2X standard message set is specifically as follows: when a road abnormality is identified, the warning position is updated according to the real-time position of the roadside base station with integrated sensing, communication and computing, and the confidence of the road abnormality event is dynamically calculated based on the distance and time difference between the road abnormality event and the roadside base station with integrated sensing, communication and computing.

Images