CN-115690197-B - Road disease position determining method, system, device and computer equipment

CN115690197BCN 115690197 BCN115690197 BCN 115690197BCN-115690197-B

Abstract

The application relates to a road disease position determining method, a system, a device and computer equipment. The method comprises the steps of obtaining a vehicle position and a vehicle azimuth angle of a vehicle, which are measured by vehicle-mounted positioning equipment of the vehicle, of obtaining a digital image and a depth image, which are obtained by shooting a road disease by a vehicle-mounted camera of the vehicle, determining a first distance between the road disease and the vehicle according to the digital image and the depth image, correcting the first distance according to equipment distance between the vehicle-mounted positioning equipment and the vehicle-mounted camera to obtain a second distance between the road disease and the vehicle, and determining the position of the road disease according to the vehicle position, the vehicle azimuth angle and the second distance. The method can ensure that the determined road disease position has higher accuracy.

Inventors

CHEN JIE
YANG WEIMIN
TANG BISHENG
LV JIANGBO
SHEN XIAOYONG

Assignees

深圳思谋信息科技有限公司
上海思谋科技有限公司

Dates

Publication Date: 20260505
Application Date: 20221027

Claims (10)

1. A method for determining a position of a road disease, the method comprising: Acquiring a vehicle position and a vehicle azimuth angle of a vehicle, which are measured by vehicle-mounted positioning equipment of the vehicle, and acquiring a digital image and a depth image which are obtained by shooting road diseases by a vehicle-mounted camera of the vehicle; Determining a first distance between the road fault and the vehicle according to the digital image and the depth image; Correcting the first distance according to the equipment distance between the vehicle-mounted positioning equipment and the vehicle-mounted camera to obtain a second distance between the road disease and the vehicle; Determining a position of the road fault according to the vehicle position, the vehicle azimuth angle and the second distance; wherein the determining a first distance between the road fault and the vehicle from the digital image and the depth image comprises: determining the position of the disease area in the depth image according to the mapping relation between the digital image and the depth image by the position of the disease area in the digital image; acquiring depth information corresponding to the position of the disease area in the depth image, wherein the depth information represents the distance between the disease area on the road and the vehicle-mounted camera on the vehicle; determining a first distance between the road fault and the vehicle according to the depth information; Correcting the first distance according to the equipment distance between the vehicle-mounted positioning equipment and the vehicle-mounted camera to obtain a second distance between the road disease and the vehicle, wherein the correcting comprises the following steps: And correcting the first distance by using the equipment distance to obtain the distance between the road disease area and the vehicle-mounted positioning equipment, and taking the distance between the road disease area and the vehicle-mounted positioning equipment as the second distance between the road disease and the vehicle.
2. The method of claim 1, wherein the onboard camera comprises a first onboard camera for capturing the digital image and a second onboard camera for capturing the depth image, wherein determining a first distance between the roadway hazard and the vehicle based on the digital image and the depth image comprises: determining pixel coordinates of the road disease in the digital image; determining depth coordinates corresponding to the pixel coordinates in the depth image according to the mapping relation between the digital image and the depth image; And determining a first distance between the road fault and the vehicle according to the depth value corresponding to the depth coordinate.
3. The method of claim 2, wherein determining the first distance between the road fault and the vehicle based on the depth value corresponding to the depth coordinate comprises: Determining a depth value corresponding to the depth coordinate as a shooting distance for shooting the road disease by the vehicle-mounted camera; determining a projection distance corresponding to the shooting distance according to the shooting distance and the shooting height of the vehicle-mounted camera; and determining a projection distance corresponding to the shooting distance as a first distance between the road disease and the vehicle.
4. The method of claim 1, wherein correcting the first distance based on the device distance between the in-vehicle positioning device and the in-vehicle camera results in a second distance between the road hazard and the vehicle, comprising: And adding the first distance and the equipment distance to obtain a second distance between the road disease and the vehicle.
5. The method of claim 1, wherein the vehicle location includes longitude and latitude coordinates of the vehicle, and wherein determining the location of the roadway hazard based on the vehicle location, the vehicle azimuth, and the second distance comprises: Determining a tangent plane radius corresponding to the latitude coordinate of the vehicle, and determining the horizontal displacement of the road disease relative to the vehicle according to the azimuth angle of the vehicle and the second distance; determining a longitude change value of the road fault relative to the vehicle according to the horizontal displacement and the tangent plane radius; And adding the longitude coordinate of the vehicle and the longitude change value to obtain the longitude coordinate of the road disease.
6. The method of claim 5, wherein said determining the location of the roadway hazard based on the vehicle location, the vehicle azimuth angle, and the second distance further comprises: Determining a vertical displacement of the road fault relative to the vehicle according to the vehicle azimuth and the second distance; determining a latitude change value of the road disease relative to the vehicle according to the vertical displacement and a preset average radius of the earth; And adding the latitude coordinate of the vehicle with the latitude change value to obtain the latitude coordinate of the road disease.
7. The road disease position determining system is characterized by comprising vehicle-mounted positioning equipment, a vehicle-mounted camera and a controller, wherein the vehicle-mounted positioning equipment and the vehicle-mounted camera are arranged on a vehicle; the vehicle-mounted positioning device is used for measuring the vehicle position and the vehicle azimuth angle of the vehicle and sending the vehicle position and the vehicle azimuth angle to the controller; the vehicle-mounted camera is used for shooting road diseases to obtain a digital image and a depth image, and sending the digital image and the depth image to the controller; The controller is configured to acquire the vehicle position, the vehicle azimuth angle, the digital image and the depth image, determine a first distance between the road disease and the vehicle according to the digital image and the depth image, correct the first distance according to a device distance between the vehicle-mounted positioning device and the vehicle-mounted camera, obtain a second distance between the road disease and the vehicle, and determine a position of the road disease according to the vehicle position, the vehicle azimuth angle and the second distance; wherein the determining a first distance between the road fault and the vehicle from the digital image and the depth image comprises: determining the position of the disease area in the depth image according to the mapping relation between the digital image and the depth image by the position of the disease area in the digital image; acquiring depth information corresponding to the position of the disease area in the depth image, wherein the depth information represents the distance between the disease area on the road and the vehicle-mounted camera on the vehicle; determining a first distance between the road fault and the vehicle according to the depth information; Correcting the first distance according to the equipment distance between the vehicle-mounted positioning equipment and the vehicle-mounted camera to obtain a second distance between the road disease and the vehicle, wherein the correcting comprises the following steps: And correcting the first distance by using the equipment distance to obtain the distance between the road disease area and the vehicle-mounted positioning equipment, and taking the distance between the road disease area and the vehicle-mounted positioning equipment as the second distance between the road disease and the vehicle.
8. A road disease position determining apparatus, characterized by comprising: the parameter acquisition module is used for acquiring the vehicle position and the vehicle azimuth angle of the vehicle, which are measured by the vehicle-mounted positioning equipment of the vehicle, and acquiring a digital image and a depth image which are obtained by shooting road diseases by the vehicle-mounted camera of the vehicle; A distance determining module for determining a first distance between the road fault and the vehicle based on the digital image and the depth image; The distance correction module is used for correcting the first distance according to the equipment distance between the vehicle-mounted positioning equipment and the vehicle-mounted camera to obtain a second distance between the road disease and the vehicle; a position determining module for determining a position of the road fault based on the vehicle position, the vehicle azimuth and the second distance; The distance determining module is also used for determining the position of the disease area in the depth image according to the mapping relation between the digital image and the depth image, obtaining depth information corresponding to the position of the disease area in the depth image, wherein the depth information represents the distance between the disease area on the road and the vehicle-mounted camera on the vehicle; The distance correction module is further used for correcting the first distance by using the equipment distance to obtain the distance between the road disease area and the vehicle-mounted positioning equipment, and taking the distance between the road disease area and the vehicle-mounted positioning equipment as the second distance between the road disease and the vehicle.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

Description

Road disease position determining method, system, device and computer equipment Technical Field The application relates to the technical field of artificial intelligence, in particular to a method, a system, a device and computer equipment for determining the position of a road disease. Background In the road disease detection process, the disease position needs to be accurately recorded, so that the road disease area can be conveniently tracked, treated and maintained according to the accurately recorded disease position. In the prior art, the disease position can be solved based on a PNP (PERSPECTIVE-n-Point) method, and the position of the disease region in a world coordinate system can be obtained by shooting the disease region on a road by using a camera and solving the pose of the camera coordinate system relative to the world coordinate system. However, due to the influence of calculation accuracy, the position of the disease solved by the PNP method usually has a large error, the position error is usually 1-5m on a flat uniform-speed driving road section according to an actual test, and the position error can reach 5-8m on a downhill road section with a hollow. Therefore, the current road disease position determination technology has the problem of low accuracy. Disclosure of Invention In view of the foregoing, it is desirable to provide a road disease position determining method, apparatus, computer device, and computer-readable storage medium capable of improving accuracy. In a first aspect, the present application provides a road disease position determining method. The method comprises the following steps: Acquiring a vehicle position and a vehicle azimuth angle of a vehicle, which are measured by vehicle-mounted positioning equipment of the vehicle, and acquiring a digital image and a depth image which are obtained by shooting road diseases by a vehicle-mounted camera of the vehicle; Determining a first distance between the road fault and the vehicle according to the digital image and the depth image; Correcting the first distance according to the equipment distance between the vehicle-mounted positioning equipment and the vehicle-mounted camera to obtain a second distance between the road disease and the vehicle; And determining the position of the road disease according to the vehicle position, the vehicle azimuth angle and the second distance. In one embodiment, the vehicle-mounted camera comprises a first vehicle-mounted camera and a second vehicle-mounted camera, wherein the first vehicle-mounted camera is used for shooting the digital image, the second vehicle-mounted camera is used for shooting the depth image, and the determining the first distance between the road disease and the vehicle according to the digital image and the depth image comprises the following steps: determining pixel coordinates of the road disease in the digital image; determining depth coordinates corresponding to the pixel coordinates in the depth image according to the mapping relation between the digital image and the depth image; And determining a first distance between the road fault and the vehicle according to the depth value corresponding to the depth coordinate. In one embodiment, the determining the first distance between the road fault and the vehicle according to the depth value corresponding to the depth coordinate includes: Determining a depth value corresponding to the depth coordinate as a shooting distance for shooting the road disease by the vehicle-mounted camera; determining a projection distance corresponding to the shooting distance according to the shooting distance and the shooting height of the vehicle-mounted camera; and determining a projection distance corresponding to the shooting distance as a first distance between the road disease and the vehicle. In one embodiment, the correcting the first distance according to the device distance between the vehicle-mounted positioning device and the vehicle-mounted camera to obtain the second distance between the road disease and the vehicle includes: And adding the first distance and the equipment distance to obtain a second distance between the road disease and the vehicle. In one embodiment, the vehicle position includes longitude and latitude coordinates of the vehicle, and the determining the location of the road fault based on the vehicle position, the vehicle azimuth, and the second distance includes: Determining a tangent plane radius corresponding to the latitude coordinate of the vehicle, and determining the horizontal displacement of the road disease relative to the vehicle according to the azimuth angle of the vehicle and the second distance; determining a longitude change value of the road fault relative to the vehicle according to the horizontal displacement and the tangent plane radius; And adding the longitude coordinate of the vehicle and the longitude change value to obtain the longitude coordinate of the road disease. In one emb