一种基于光流和二级聚类的移动背景下的目标检测算法  

A Moving Objects Detection Algorithm in Dynamic Scene Based on Optical Flow and Secondary Clustering

作　　者：李凯[1] 吴晓红[1] 刘文璨[1] 张琳[1] 何小海[1] LI Kai;WU Xiao-hong;LIU Wen-can;ZHANG Lin;HE Xiao-hai(College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, P. R. China)

机构地区：[1]四川大学电子信息学院,成都610065

出　　处：《科学技术与工程》2016年第30期108-114,共7页Science Technology and Engineering

基　　金：成都市科技惠民项目(2015-HM01-00293-SF);特殊环境机器人技术四川省重点实验室开放基金(14zxtk03);国家自然科学基金委员会和中国工程物理研究院联合基金(11176018)资助

摘　　要：针对现有的移动背景下的目标检测算法存在检测速度较慢、自适应性差和检测准确度不高的问题,提出了一种基于光流和二级聚类的移动背景下的目标检测算法;该算法融合了阈值自适应规则和基于优化检测结果的反馈机制。首先采用Lucas-Kanade光流跟踪算法和DBSCAN聚类算法提取出前景目标,然后采用改进的凝聚层次聚类算法将前景目标分类。在第一级聚类时建立基于初始聚类结果的自适应规则,实现了自适应地检测目标;在第二级聚类后,通过去除错误匹配特征点和阴影区域特征点优化检测结果;并将优化后的检测结果反馈给第一级聚类过程以更新适用阈值,使目标检测更准确。在多个视频库上进行验证,实验结果证明该算法检测速度快、自适应性良好、检测准确度高。There are several problems that slow detection speed,bad self adaptab-ility and high misjudge rate in existing moving objects detection methods in dynamic scene,so an new algorithm was proposed based on optical flow and secondary clustering,which combined the adaptive threshold and feedback mechanism based on optimizing the detection results.Firstly,Lucas-Kanade optical flow tracking algorithm and DBSCAN clustering algorithm were used to extract the objects in foreground,then we used an improved agglomerate hierarchical clustering algorithm to classify the objects in foreground.When the first-level clustering process run,it adjusted the threshold according to the clustering results to obtain applicable threshold,thus it could detect targets adaptively.The result of the second-level clustering was denoised and optimized and then it was fed back to the first-level clustering process,thus the applicable threshold would be updated to get more accurate detection results.This proposed algorithm was validated on several video library and the experimental results demonstrated its fast detection speed,good self adaptability and low misjudge rate.

关 键 词：目标检测 移动背景 自适应阈值 反馈 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]