文章基本信息

标题：A Novel Method for Person Tracking Based K-NN : Comparison with Sift and Mean Shift Method
本地全文：下载
作者：Asmaa AIT MOULAY ; Aouatif AMINE
期刊名称：Signal & Image Processing : An International Journal (SIPIJ)
印刷版ISSN：2229-3922
电子版ISSN：0976-710X
出版年度：2017
卷号：8
期号：1
页码：45
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Object tracking can be defined as the process of detecting an object of interest from a video scene andkeeping track of its motion, orientation, occlusion etc. in order to extract useful information. It is indeed achallenging problem and it’s an important task. Many researchers are getting attracted in the field ofcomputer vision, specifically the field of object tracking in video surveillance. The main purpose of thispaper is to give to the reader information of the present state of the art object tracking, together withpresenting steps involved in Background Subtraction and their techniques. In related literature we foundthree main methods of object tracking: the first method is the optical flow; the second is related to thebackground subtraction, which is divided into two types presented in this paper, then the temporaldifferencing and the SIFT method and the last one is the mean shift method. We present a novel approachto background subtraction that compare a current frame with the background model that we have setbefore, so we can classified each pixel of the image as a foreground or a background element, then comesthe tracking step to present our object of interest, which is a person, by his centroid. The tracking step isdivided into two different methods, the surface method and the K-NN method, both are explained in thepaper. Our proposed method is implemented and evaluated using CAVIAR database.
关键词：Video Surveillance; Object Tracking; Feature Extraction; Background Subtraction.