EK-means Tracker:A Pixel-wise Tracking Algorithm using Kinect
作者单位：Wakayama University930 SakaedaniWakayama City640-8510Japan
会议名称：《2011 Third Chinese Conference on Intelligent Visual Surveillance》
会议日期：2011年
学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程]
基 金：supported by Grants-in-Aid for Scientific Research(C)21500171
关 键 词：Pixel-wise Mahalanobis distance Depth Color Position Tracking
摘 要：This paper describes a novel object-tracking algorithm by classifying the pixels in a search area into target and background with K-means clustering *** improvements are made to the conventional K-means tracker to solve the instability problem that occurs when some background objects show similar colors to the target or the size of the target object changes *** first one is introducing of the depth information as the sixth feature into the original 5D feature space for describing *** second one is to use Mahalanobis distance in order to keep the balance between color and position when evaluating the difference between ***-means Tracker can track non-rigid object and wired object at video *** effectiveness was confirmed through several comparison experiments.