利用掩膜和单应矩阵提高LK光流追踪效果  

Improving the performance of LK optical flow tracking using mask and homography matrix

作　　者：杜慧丽 黄劲松[1] DU Huili;HUANG Jinsong(School of Geodesy and Geomatics,Wuhan University,Wuhan 430079,China)

机构地区：[1]武汉大学测绘学院,武汉430079

出　　处：《导航定位学报》2022年第5期25-31,共7页Journal of Navigation and Positioning

摘　　要：针对使用卢卡斯-卡纳德(LK)光流对车载下视相机所拍摄的地面纹理图像追踪时存在的特征误匹配问题,提出一种利用掩膜和单应矩阵来提高光流追踪效果的方法,在室外环境下采集地面纹理图像进行实验验证。实验结果表明,掩膜可以有效提高正确追踪角点的数量,单应矩阵可以剔除帧间光流追踪的错误匹配,对LK光流追踪的精度和鲁棒性有明显提升。The Lucas-Kanade(LK)optical flow tracking has the feature mismatch problem when it is used on the ground texture image taken by a vehicle mounted downward camera.In order to solve this problem,we proposed a method to improve the performance of optical flow tracking by using mask and homography matrix,and the ground texture images were collected in outdoor environment for experimental verification.The results showed that the mask could effectively increase the number of correct tracking corners,and the homography matrix could eliminate the false matching of optical flow tracking between frames,which significantly improved the accuracy and robustness of LK optical flow tracking.

关 键 词：下视相机 地面纹理 卢卡斯-卡纳德光流 掩膜 单应矩阵 

分 类 号：P228[天文地球—大地测量学与测量工程]