当前位置: X-MOL 学术Opt. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Algorithm of object localization applied on high-voltage power transmission lines based on line stereo matching
Optical Engineering ( IF 1.3 ) Pub Date : 2021-02-01 , DOI: 10.1117/1.oe.60.2.023101
Fashuai Tang 1 , Qi Gao 1 , Zongzhan Du 2
Affiliation  

The algorithm designing of object localization is one of the key technologies in the research field of high-voltage power transmission line inspection robot. We present an obstacle localization method based on line stereo matching to solve the problems remaining in the current obstacle localization algorithms such as the weak capacity of resisting distraction, the low localization precision, and the extra prior conditions. The proposed algorithm regards line as the element unit for stereo matching and adopts Earth mover’s distance as similarity measurement criterion. In addition, it can remove false matching points through the condition of distance constraint and the distribution information of depth. Finally, we give all sampling points on obstacle different weights according to the distance between the points and obstacle center, through which the weighted mean depth of obstacle is obtained. The experimental result shows that the mean relative localization error is 2.697% and the fluctuating range is 1.11% to 3.58%, which means the localization precision is high and the error fluctuation is small. So this algorithm can meet the demand of obstacle localization for high-voltage power transmission lines inspection robot efficiently.

中文翻译:

基于线立体匹配的高压输电线路目标定位算法

目标定位的算法设计是高压输电线路检测机器人研究领域的关键技术之一。我们提出了一种基于线立体匹配的障碍物定位方法,以解决当前障碍物定位算法中仍然存在的问题,例如抗干扰能力弱,定位精度低以及额外的先决条件。该算法以线为立体匹配的要素单元,以土方距离作为相似性度量标准。另外,它可以通过距离约束条件和深度分布信息来消除错误的匹配点。最后,我们根据障碍物与障碍物中心之间的距离,为障碍物上的所有采样点赋予不同的权重,通过它可以获得障碍物的加权平均深度。实验结果表明,平均相对定位误差为2.697%,波动范围为1.11%〜3.58%,定位精度高,误差波动小。因此,该算法可以有效满足高压输电线路检测机器人障碍物定位的需求。
更新日期:2021-02-10
down
wechat
bug