基于假设理论的序列图像中多目标检测和跟踪 multiple motion object detection and tracking based on hypothesis theory in sequence image.pdfVIP

第 35 卷第 5 期 光电工程 Vol.35, No.5 2008 年 5 月 Opto-Electronic Engineering May, 2008 文章编号：1003-501X(2008)05-0055-06 Multiple Motion Object Detection and Tracking Based on Hypothesis Theory in Sequence Image TONG Wu-qin，LING Yong-shun ，YANG Hua ，YANG Xing ( Key Lab of Infrared and Low Temperature Plasma of Anhui Province, Hefei Electronic Engineering Institute, Hefei 230037, China ) Abstract : A multiple hypothesis method for tracking multiple motion objects is proposed based on the object detection, which is robust to changes illumination and shadow conditions in image sequence. After video preprocessing including background suppression, temporal filter and clutter removal, the initial results of object detection is obtained in each frame image. Based on the detection results which may have missing and/or false detection, the multiple object tracking algorithm accepts the probabilities of initial object detection and keeps multiple hypotheses of object in a graph structure. Through extending and pruning the graph based on the previous image information, the multiple object tracking method gives feedbacks which are predictions of object locations to th e object detection module. Therefore, the method integrates object detection and tracking tightly. The most possible hypothesis provides the multiple motion object tracking results. The experiment and evaluation results illustrate the validity and advantage of the proposed algorithm. Key words : multiple object detection; hypothesis tracking; background suppression; object trajectory CLC number : V556, TP391.4 Document code :