High-precision map acquisition system and method based on Internet of Vehicles

Abstract

The invention discloses a high-precision map acquisition system and method based on the Internet of Vehicles, and belongs to the technical field of map acquisition, and the system comprises M data acquisition vehicles which carry out data interaction with a cloud platform, and M is a natural number greater than 0; a positioning device and N types of image acquisition equipment are mounted on each data acquisition vehicle, and N is a natural number greater than 1; the environment acquisition module performs data interaction with the cloud platform and is used for acquiring light intensity and visibility; the speed acquisition module performs data interaction with the cloud platform and is used for acquiring the speed of the data acquisition vehicle; the curvature acquisition module performs data interaction with the cloud platform and is used for acquiring the curvature of the road; and a logic control module arranged in the cloud platform and used for controlling different types of image acquisition devices to acquire map data according to the light intensity, the visibility, the curvature and the vehicle speed. According to the invention, the Internet of Vehicles technology, the multi-sensor acquisition technology and the logic control technology of the cloud platform are fused, and high-precision map acquisition under different conditions is realized.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of map collection, and particularly relates to a high-precision map collection system and method based on Internet of Vehicles. BACKGROUND

[0002] With the continuous progress and development of intelligent technology, high-precision maps are increasingly widely applied in various fields, and their importance is increasingly highlighted. However, in the traditional high-precision map data collection process, professional single vehicles are usually relied on, which are equipped with high-precision sensing devices and are specially used for data collection. However, this collection method has obvious limitations, especially when encountering bad weather or other complex scene conditions, the traditional collection method often cannot realize real-time data collection, which not only leads to a significant extension of the data collection period, but also greatly reduces the collection efficiency. In addition, due to the need to invest a large number of professional vehicles and high-end equipment, the investment cost of vehicle collection is also high, and these factors comprehensively make the production and development cost of high-precision maps extremely high, which seriously restricts the popularization and application of high-precision maps. SUMMARY

[0003] The purpose of the application is to provide a high-precision map collection system and method based on Internet of Vehicles, which integrates Internet of Vehicles technology, multi-sensor collection technology and cloud platform logical control technology, and can realize high-precision map collection under different conditions.

[0004] To achieve the above purpose, the application provides the following technical scheme:

[0005] The first purpose of the application is to provide a high-precision map collection system based on Internet of Vehicles, comprising:

[0006] M data collection vehicles for data interaction with the cloud platform, M is a natural number greater than 0; a positioning device and N types of image collection equipment are installed on each data collection vehicle, N is a natural number greater than 1;

[0007] An environment collection module for data interaction with the cloud platform, used for acquiring light intensity and visibility;

[0008] A speed collection module for data interaction with the cloud platform, used for acquiring the speed of the data collection vehicle;

[0009] A curvature collection module for data interaction with the cloud platform, used for acquiring the curvature of the road;

[0010] A logical control module arranged in the cloud platform, which controls different types of image collection equipment to acquire map data according to the light intensity, visibility, curvature and speed.

[0011] The second object of the present application is to provide a high-precision map collection method based on vehicle networking, comprising:

[0012] A vehicle networking is established between the cloud platform and M data collection vehicles, M being a natural number greater than 0; a positioning device and N types of image collection equipment are installed on each data collection vehicle, N being a natural number greater than 1;

[0013] The light intensity and visibility are obtained by using the environment collection module;

[0014] The vehicle speed of the data collection vehicle is obtained by using the speed collection module;

[0015] The curvature of the road is obtained by using the curvature collection module;

[0016] The logical control module in the cloud platform controls different types of image collection equipment to obtain map data according to the light intensity, visibility, curvature and vehicle speed.

[0017] Compared with the prior art, the present application has the following advantages:

[0018] The present application combines vehicle networking technology, multi-sensor collection technology and cloud platform logical control technology, and can realize high-precision map collection under different conditions.

[0019] The present application first adds four types of image collection equipment on the data collection vehicle, namely a high-definition camera for obtaining road structure image data, a laser radar for obtaining roadside structure data, an infrared camera for obtaining road surface structure data, and a thermal imaging unit for obtaining road surface structure data; the four types of image collection equipment can meet the image collection requirements under different conditions;

[0020] The present application subsequently adds an environment collection module, a speed collection module and a curvature collection module, which can monitor the current road conditions and environment of the vehicle in real time;

[0021] The present application finally constructs a scientific logical control module in the cloud platform, which can control different types of image collection equipment to obtain map data according to the light intensity, visibility, curvature and vehicle speed, so that the system can efficiently realize high-precision map collection work. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 The system block diagram of the preferred embodiment of the present application;

[0023] Figure 2 The communication principle diagram of the preferred embodiment of the present application;

[0024] Figure 3 The structure schematic diagram of the preferred embodiment of the present application;

[0025] Figure 4 This is a schematic diagram of the curved road surface in a preferred embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of a low-light-intensity road surface in a preferred embodiment of the present invention;

[0027] Figure 6 This is a schematic diagram of the structure of a low-visibility road surface in a preferred embodiment of the present invention;

[0028] Figure 7 This is a schematic diagram of the data acquisition vehicle after instruction 1 is issued in a preferred embodiment of the present invention;

[0029] Figure 8 This is a schematic diagram of the data acquisition vehicle after instruction 2 is issued in a preferred embodiment of the present invention;

[0030] Figure 9 This is a schematic diagram of the data acquisition vehicle after instruction 3 is issued in a preferred embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Please see Figure 1 A high-precision map acquisition system based on vehicle-to-everything (V2X) communication includes:

[0033] M data collection vehicles interact with the cloud platform, where M is a natural number greater than 0; each data collection vehicle is equipped with a positioning device and N types of image acquisition equipment, where N is a natural number greater than 1.

[0034] An environmental acquisition module that interacts with the cloud platform to obtain light intensity and visibility;

[0035] The speed acquisition module, which interacts with the cloud platform, is used to obtain the vehicle speed of the data acquisition vehicle.

[0036] The curvature acquisition module, which interacts with the cloud platform, is used to obtain the curvature of the road.

[0037] The logic control module set up in the cloud platform controls different types of image acquisition devices to acquire map data based on the light intensity, visibility, curvature, and vehicle speed.

[0038] To better understand the concept of this invention, non-limiting examples are given below:

[0039] Please refer to Figures 2 to 9 , the data collection vehicle is an automatic driving vehicle;

[0040] The image acquisition device comprises:

[0041] A high-definition camera unit acquires structural image data of the road;

[0042] For example, the high-definition camera unit is a map acquisition high-definition camera 10 arranged above the front windshield of the automatic driving vehicle, adopts a 12 million pixel high-resolution image sensor, and presents fine structural image data of the road. When no instruction 1 is received, the high-definition camera unit is in a dormant state. After receiving the instruction 1, the high-definition camera unit is awakened by the automatic driving controller, fine image data of the road in front of the automatic driving vehicle is collected, and the image data is transmitted to the map fusion system for road map image fusion processing.

[0043] A laser radar acquires roadside structural data;

[0044] For example, the laser radar is a map acquisition laser radar 11 arranged above the front part of the automatic driving vehicle, reaches 1440 lines, carries a fourth-generation self-developed chip of Hesai, has a ranging distance of 300 meters at 10% reflectivity, and a point frequency of more than 34 million points per second, can accurately capture small objects and slight ups and downs and pits of the road surface of complex urban streets. When no instruction 1 is received, the laser radar is in a dormant state. After receiving the instruction 1, the laser radar is awakened by the automatic driving controller, real-time roadside structural data is collected, and the point cloud data is transmitted to the map fusion system for road map image fusion processing.

[0045] An infrared camera unit acquires road surface structural data;

[0046] For example, the infrared camera unit is a map acquisition infrared camera 12 arranged inside the map acquisition sensor cabin on the inside of the middle roof of the automatic driving vehicle and connected with a telescopic connecting rod. The telescopic connecting rod can extend and retract the sensor cabin under the action of a drive motor. The infrared camera 12 adopts an 850 nm wavelength infrared lamp. When no instruction 2 is received, the infrared camera is in a dormant state inside the sensor cabin 19. When the instruction 2 is received, the controller controls the drive motor 21 to slide the sliding cover 18 above the infrared camera, the telescopic connecting rod 20 is elongated, and the infrared camera is extended 300 mm out of the roof of the automatic driving vehicle. Real-time collection of road surface structural conditions in low-light scenes such as night vision is performed, and the infrared image is transmitted to the map fusion system for supplementary fusion processing of the data collected by the high-definition camera and the laser radar.

[0047] The thermal imaging unit acquires road surface structure data.

[0048] For example, the thermal imaging unit selects the map collection thermal imaging camera 13, which is arranged inside the map collection sensor cabin on the inside of the middle roof of the autonomous vehicle, connected with the telescopic connecting rod, and can extend and retract the sensor cabin under the action of the drive motor. A 50mk temperature resolution sensor is used. When no instruction 3 is received, the thermal imaging camera is in a dormant state inside the sensor cabin. When instruction 3 is received, the controller controls the drive motor to slide the sliding cover above the thermal imaging camera, the telescopic connecting rod is elongated, and the infrared camera is extended 600mm out of the roof of the autonomous vehicle. The infrared camera can collect real-time road surface structure conditions in poor weather scenes such as rain, fog, low visibility, and night vision, and transmit the images to the map fusion system for image data supplement and fusion processing of the high-definition camera, laser radar, and infrared camera.

[0049] The environment collection module includes:

[0050] The photosensitive sensor acquires the light intensity of the roadside environment.

[0051] For example, the photosensitive sensor selects the photosensitive sensor 7, which is arranged above the roadside rod and quickly senses the change of the light intensity of the roadside environment, and outputs the corresponding light signal to the cloud platform in time. It is suitable for judging the map collection instruction in different environment scenes with different light intensities in the daytime and at night.

[0052] The visibility sensor acquires the visibility of the road environment.

[0053] The visibility sensor 8 is arranged above the roadside rod, calculates the visibility by using a transmission algorithm, and feeds back the visibility parameter to the cloud platform. It is suitable for judging the map collection instruction in different scenes with different rain and fog visibility.

[0054] The speed collection module and the curvature collection module include:

[0055] The roadside camera collects the curvature and speed of the road surface, and transmits 2D image sensing data to the edge computing unit.

[0056] The roadside laser radar collects the curvature and speed of the road surface, and transmits 3D image sensing data to the edge computing unit.

[0057] The edge computing unit receives the sensing information transmitted by the roadside camera and the roadside laser radar, and performs visual fusion on the 2D image sensing data and the 3D image sensing data to construct the curvature and speed of the road surface, and sends it to the cloud platform.

[0058] For example: the roadside camera 1 is arranged above the road pole, the field of view angle is 180°, a 100 million pixel high-definition sensor is used, the curvature of the road surface and the motion speed of the autonomous vehicle are collected in real time, and the 2D image sensing data is transmitted to the edge computing unit to calculate the curvature of the current road surface and the motion speed of the vehicle along the longitudinal direction of the road surface;

[0059] The roadside laser radar 2 is arranged above the road pole, a 128-line pure solid-state laser radar is used, the curvature of the road surface and the motion speed of the autonomous vehicle are collected in real time, and the 3D image sensing data is transmitted to the edge computing unit to calculate the curvature of the current road surface and the motion speed of the vehicle along the longitudinal direction of the road surface;

[0060] The edge computing unit 3 receives the sensing information transmitted by the roadside camera and the roadside laser radar, and performs visual fusion on the 2D image information of the camera and the 3D image sensing data (3D point cloud information) of the laser radar, constructs the curvature of the road surface and the motion speed of the autonomous vehicle, and sends it to the cloud platform for judgment of the high-precision map data collection instruction of the autonomous vehicle;

[0061] The logic control module comprises:

[0062] The curvature is defined as a, the vehicle speed is V, the light intensity is b, and the visibility is c;

[0063] When 0

[0064] After sending the instruction 1, the light intensity is logically judged, when b

[0065] After sending the instruction 2, the visibility is logically judged, when c

[0066] It also includes a billing module, which first counts the driving distance of the data collection vehicle when executing three different instructions, then combines the unit price of each instruction to calculate the reward, and finally sends the reward to the data collection vehicle.

[0067] For example: the cloud platform receives the road condition information and autonomous vehicle information input by the edge computing unit, performs logical judgment on the map collection instruction,

[0068] When the road curvature is 0 < a < 250 and the vehicle speed is 0 < V < 30 kph, or a > 250 and 0 < V < 60 kph, the cloud platform sends instruction 1 to the autonomous vehicle controller to turn on the positioning device of the autonomous vehicle, the map collection laser radar, the map collection high-definition camera, collect the position information of the vehicle and the image and point cloud information corresponding to the position information, and perform map image information fusion and labeling, and send the information to the cloud platform through the vehicle OBU.

[0069] After the cloud platform sends instruction 1, the light-sensitive sensor tests the current ambient light intensity. When the light intensity b < 100 lux, instruction 2 is sent to turn on the infrared camera device for road environment collection in night scenes, and the collected infrared image is fused with the image and point cloud information sent by instruction 1 to the vehicle controller for map image information fusion and labeling, and sent to the cloud platform through the vehicle OBU.

[0070] After the cloud platform sends instruction 2, the visibility sensor tests the current ambient light intensity. When the visibility c < 500 m, instruction 3 is sent to turn on the thermal imaging camera device for road environment collection in low-visibility scenes in rain and fog weather, and the collected thermal imaging image is fused with the image, point cloud information and infrared image sent by instruction 2 to the vehicle controller for map image information fusion and labeling, and sent to the cloud platform through the vehicle OBU.

[0071] The cloud platform pays fees according to different map data collection conditions of the autonomous vehicle according to the instructions. The running mileage of the autonomous vehicle is calculated when instruction 1 is turned on, the mileage L1 of the vehicle for high-precision collection of the road surface is counted, and the cloud platform pays the autonomous vehicle according to m yuan / km. When instruction 2 is turned on, the mileage L2 of the vehicle for high-precision collection of the road surface is counted, and the cloud platform pays the autonomous vehicle according to 1.2 m yuan / km. When instruction 3 is turned on, the mileage L3 of the vehicle for high-precision collection of the road surface is counted, and the cloud platform pays the autonomous vehicle according to 1.5 m yuan / km.

[0072] The data interaction between the cloud platform and the autonomous vehicle includes the following components:

[0073] The roadside RSU 5 is arranged above the roadside pole, receives the instruction sent by the cloud platform, and transmits the instruction to the autonomous vehicle controller through the vehicle OBU for instruction control.

[0074] The vehicle OBU 6 is arranged inside the cabin of the autonomous vehicle, interacts with the roadside RSU through LTEV wireless communication, receives the control instruction of the cloud platform transmitted by the roadside RSU, and transmits it to the autonomous controller.

[0075] The automatic driving controller 9 is arranged inside the automatic driving vehicle cabin. When receiving the map acquisition control instruction 1 transmitted by the cloud platform, the automatic driving controller 9 controls the power-on of the map acquisition high-definition camera, the map acquisition laser radar, and the positioning device of the automatic driving vehicle, and transmits real-time data to the map perception fusion system. When receiving the instructions 2 and 3 of the cloud platform, the automatic driving controller 9 controls the driving motor to open the sliding cover above the map acquisition infrared camera and the thermal imaging camera, and extends the telescopic pull rod to drive the infrared camera and the thermal imaging camera to the outside of the roof to collect road image data and transmit the real-time data to the map perception fusion system.

[0076] The map fusion system 14 is used to receive the image data of the map acquisition high-definition camera, the map acquisition laser radar, the map acquisition infrared camera, and the map acquisition thermal imaging camera, and the coordinate data of the positioning device 15, to perform image perception fusion, construct a detailed road high-precision map image model data, and transmit the data to the cloud platform through the vehicle-mounted OBU for the cloud platform to collect the high-precision map data of the road surface.

[0077] The positioning device 15 is arranged at the bottom of the vehicle, and uses an IMU and RTK combined high-precision positioning system to collect real-time position information of the vehicle including longitude, latitude, and angle, and transmit the information to the map fusion system for marking the coordinates of the map data at different positions.

[0078] The payment sending device is arranged above the roadside rod, receives the instructions of the cloud platform, and pays the fees of the automatic driving vehicle according to the instruction mode and the mileage of the automatic driving vehicle for collecting the map in real time, to encourage the map collection operation of the automatic driving vehicle.

[0079] The payment receiving device is used to receive the fees sent by the payment sending device, to encourage the map collection operation of the owner of the automatic driving vehicle.

[0080] A high-precision map collection method based on vehicle networking, which uses the high-precision map collection system based on vehicle networking in the above embodiment to perform the following steps:

[0081] A vehicle networking is established between the cloud platform and M data collection vehicles, M is a natural number greater than 0; a positioning device and N types of image collection equipment are installed on each data collection vehicle, N is a natural number greater than 1;

[0082] The light intensity and visibility are obtained by using the environment collection module;

[0083] The speed of the data collection vehicle is obtained by using the speed collection module;

[0084] The curvature of the road is obtained by using the curvature collection module.

[0085] A logic control module in the cloud platform controls different types of image acquisition devices to acquire map data according to the light intensity, visibility, curvature and vehicle speed.

[0086] The logic control module comprises:

[0087] Table 1 is the control logic of the logic control module

[0088]

[0089] First, define the curvature as a, the vehicle speed as V, the light intensity as b and the visibility as c; then perform the following logical analysis:

[0090] When 0 < a < 250 and 0 < V < 30 kph, or when a > 250 and 0 < V < 60 kph, send instruction 1 to the controller of the data acquisition vehicle, the instruction 1 being: turn on the high-definition camera and laser radar on the data acquisition vehicle;

[0091] After sending the instruction 1, logically judge the light intensity, and when b < 100 lux, send instruction 2 to the controller of the data acquisition vehicle, the instruction 2 being: turn on the infrared camera on the data acquisition vehicle;

[0092] After sending the instruction 2, logically judge the visibility, and when c < 500 m, send instruction 3 to the controller of the data acquisition vehicle, the instruction 3 being: turn on the thermal imaging unit on the data acquisition vehicle.

[0093] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and changes can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A high-precision map collection system based on vehicle networking, characterized in that, Comprise: M data acquisition vehicles for data interaction with the cloud platform, M is a natural number greater than 0; Each data acquisition vehicle is installed with a positioning device and N types of image acquisition equipment, N is a natural number greater than 1; An environmental acquisition module for data interaction with the cloud platform, used for obtaining light intensity and visibility; A speed acquisition module for data interaction with the cloud platform, used for obtaining the speed of the data acquisition vehicle; A curvature acquisition module for data interaction with the cloud platform, used for obtaining the curvature of the road; A logic control module set in the cloud platform, which controls different types of image acquisition equipment to obtain map data according to the light intensity, visibility, curvature and speed. 2.The high-precision map acquisition system based on the Internet of Vehicles according to claim 1, characterized in that, The image acquisition equipment comprises: A high-definition camera for obtaining structural image data of the road; A laser radar for obtaining roadside structure data; An infrared camera for obtaining road surface structure data; A thermal imaging unit for obtaining road surface structure data. 3.The high-precision map acquisition system based on the Internet of Vehicles according to claim 2, characterized in that, The environmental acquisition module comprises: A photosensitive sensor for obtaining the light intensity of the roadside environment; A visibility sensor for obtaining the visibility of the road environment.

4. The high-precision map acquisition system based on the Internet of Vehicles according to claim 3, characterized in that, The speed acquisition module and the curvature acquisition module comprise: A roadside camera for collecting the curvature and speed of the road surface and transmitting 2D image perception data to an edge computing unit; A roadside laser radar for collecting the curvature and speed of the road surface and transmitting 3D image perception data to the edge computing unit; The edge computing unit receives the perception information transmitted by the roadside camera and the roadside laser radar, and performs visual fusion on the 2D image perception data and the 3D image perception data to construct the curvature and speed of the road surface, and sends it to the cloud platform. 5.The high-precision map acquisition system based on the Internet of Vehicles according to claim 4, characterized in that, The logic control module comprises: Defining the curvature as a, the speed as V, the light intensity as b, and the visibility as c; When 0 When instruction 1 is sent, logically judge the light intensity, and when b When instruction 2 is sent, logically judge the visibility, and when c 6.The high-precision map acquisition system based on the Internet of Vehicles according to claim 5, characterized in that, It also includes a billing module, which first counts the driving distance of the data acquisition vehicle when executing three different instructions, then calculates the reward according to the unit price of each instruction, and finally sends the reward to the data acquisition vehicle. 7.The high-precision map acquisition system based on the Internet of Vehicles according to claim 1, characterized in that, The positioning device uses a high-precision positioning system combining IMU and RTK to collect the latitude, longitude and angle of the data acquisition vehicle in real time. 8.A high-precision map collection method based on vehicle networking, characterized in that, Comprise: Establish a vehicle networking between the cloud platform and M data acquisition vehicles, M is a natural number greater than 0; Each data acquisition vehicle is installed with a positioning device and N types of image acquisition equipment, N is a natural number greater than 1; Use the environmental acquisition module to obtain light intensity and visibility; Use the speed acquisition module to obtain the speed of the data acquisition vehicle; Use the curvature acquisition module to obtain the curvature of the road; A logic control module in the cloud platform controls different types of image acquisition devices to acquire map data according to the light intensity, visibility, curvature and vehicle speed. 9.The high-precision map collection method based on the Internet of Vehicles according to claim 8, characterized in that: The logic control module comprises: The curvature is defined as a, the vehicle speed is V, the light intensity is b, and the visibility is c; When 0 After the instruction 1 is sent, the light intensity is logically judged, when b After the instruction 2 is sent, the visibility is logically judged, when c After the instruction 3 is sent, the visibility is logically judged, when c

Images