多分辨率LK光流联合SURF的跟踪方法

发布时间：2018-05-16 17:28

本文选题：光流算法 + 特征提取　；参考：《计算机应用》2017年03期

【摘要】：针对交通监控中运动目标形变、雾霾天气、高速、光照不均、部分遮挡等复杂情况导致Lucas-Kanade(LK)算法跟踪不稳定问题,提出基于多分辨率LK光流算法联合快速鲁棒性特征(SURF)的跟踪算法。所提算法构建图像多分辨率小波金字塔,解决传统LK算法中同一像素点帧间大尺度运动易丢失问题;同时联合SURF尺度不变特征变换算法,提取特征点进行光流跟踪,并制定自适应模板实时更新策略;在减少光流计算量的同时增强运动目标抗复杂环境的能力。实验结果表明,新方法中特征点匹配准确快速,自适应性强,在交通复杂化境中跟踪稳定。
[Abstract]:In view of the complex conditions of moving target deformation, haze weather, high speed, uneven illumination and partial occlusion in traffic monitoring, Lucas-Kanadeen LK) algorithm leads to the unstable tracking problem. A tracking algorithm based on multi-resolution LK optical flow algorithm combined with fast robust feature tracking (surf) is proposed. The proposed algorithm constructs the image multi-resolution wavelet pyramid, solves the problem of losing large scale motion between frames of the same pixel in the traditional LK algorithm, and combines the SURF scale invariant feature transform algorithm to extract the feature points for optical flow tracking. An adaptive template updating strategy is developed to reduce the amount of calculation of optical flow and to enhance the ability of moving target to resist complex environment at the same time. The experimental results show that the new method is accurate, fast, self-adaptive and stable in traffic complex environment.
【作者单位】：徐州工程学院江苏省大型工程装备检测与控制重点建设实验室;徐州工程学院信电工程学院;
【基金】：江苏省高校自然科学研究面上项目(15KJB520033,16KJB510022) 江苏省产学研联合创新资金资助项目(BY2013020) 住房城乡建设部科学技术计划项目(2015-K5-027,2016-R2-060) 江苏省大型工程装备检测与控制重点建设实验室开放课题(JSKLEDC201224)~~
【分类号】：U495;TP391.41

【相似文献】