Vehicle image stitching method, device, computer equipment and storage medium
By using multiple cameras to collect image data in the autonomous driving system and obtaining virtual points based on the relationship between the vehicle and the ground to convert feature points, the problem of image stitching distortion in autonomous driving is solved, and decision-making accuracy is improved.
CN113610710BActive Publication Date: 2025-03-28GUANGZHOU WERIDE TECH LTD CO
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202110873108.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-07-30
- Publication Date
- 2025-03-28
- Estimated Expiration
- 2041-07-30
AI Technical Summary
Technical Problem
In autonomous driving, there is a significant distortion in image stitching, which affects the accuracy of decision-making.
Method used
By calling multiple cameras to collect image data, obtain virtual points according to the relationship between the vehicle and the ground, and convert them into image data, obtain matching feature points, and then stitch the image data.
Benefits of technology
It reduces distortion in image stitching and improves the accuracy of autonomous driving decisions, especially when remote control, pays more attention to ground conditions to ensure the stitching effect.
✦ Generated by Eureka AI based on patent content.
Abstract
An embodiment of the present invention provides a vehicle image stitching method, apparatus, computer equipment and storage medium, the method comprising: calling a first camera to collect first image data, calling a second camera to collect second image data, obtaining multiple virtual points on the ground on which the vehicle is traveling according to the relationship between the vehicle and the ground, converting the multiple virtual points into the first image data and the second image data respectively according to the relationship between the first camera, the second camera and the vehicle, obtaining multiple groups of matching feature points, and stitching the first image data and the second image data according to the multiple groups of feature points. In the process of automatic driving, especially when the vehicle encounters difficulties and needs remote control, the decision-making pays more attention to the ground. Therefore, when stitching the first image data and the second image data, the stitching effect of the ground is guaranteed, the distortion on the ground is reduced, and the impact on the decision of automatic driving is reduced, thereby ensuring the accuracy of automatic driving.
Need to check novelty before this filing date? Find Prior Art