一种面向密集目标群的双目视觉目标匹配方法
By combining the optimal matching algorithm and epipolar constraints, the problems of accuracy and real-time performance in target matching in dense target groups are solved, achieving fast and accurate target matching.
CN117314979BActive Publication Date: 2026-07-17NAT UNIV OF DEFENSE TECH
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NAT UNIV OF DEFENSE TECH
- Filing Date
- 2023-09-26
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies struggle to effectively distinguish different targets within a dense group of targets, and feature-point-based methods are time-consuming and cannot meet real-time requirements.
Method used
An optimal matching algorithm combined with binocular epipolar constraints is used to perform matching based on the spatial location information of the target. The optimal matching algorithm and the Hungarian algorithm are used to find the best match, and the epipolar constraints are used to eliminate false matching results.
Benefits of technology
It improves the accuracy and real-time performance of target matching, with an algorithm execution time of only 2ms, and can effectively eliminate false matching results, thus improving the robustness of the system.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN117314979B_ABST
Abstract
本发明公开了一种面向密集目标群的双目视觉目标匹配方法，利用双目相机获取含有低小慢目标的左、右目图像；将所述左、右目图像输入目标检测模块，获得双目检测结果，根据双目检测结果确定目标在左、右目图像中的像素坐标。本发明采用最优匹配结合双目极线约束的方法，利用目标的空间位置关系进行对应目标匹配。一方面，提高了系统的鲁棒性，在匹配过程中，可能存在双目相机检测到的目标数量不一致的情况，利用匹配结果的距离阈值和极线约束可以剔除无法匹配的目标；另一方面，算法运行时间仅需2ms，运行速度快且准确率高。
Need to check novelty before this filing date? Find Prior Art