Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Context-Based Occlusion Detection for Robust Visual Tracking

Abstract: 

Occlusion is one of the most challenging factors in visual tracking. In this paper, we propose a novel context-based occlusion detection algorithm for robust visual tracking. The basic idea of our algorithm is that occlusion indicates that
some background points in previous frame move into the target region in current frame. Our algorithm investigates background patches with background trackers. The occlusion is examined by the a occlusion detector. The template updating strategy is that if occlusion is detected, the target template stops updating. Comprehensive experiments in CVPR2013 Online Objecting Tracking Benchmark (OOTB) show that our
tracker achieves comparable performance with other state-ofart trackers.

up
0 users have voted:

Paper Details

Authors:
Yu Qiao
Submitted On:
14 September 2017 - 4:13am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Xiaoguang Niu
Paper Code:
3111
Document Year:
2017
Cite

Document Files

ICIP poster - 钮小光.pdf

(0)

Subscribe

[1] Yu Qiao, "Context-Based Occlusion Detection for Robust Visual Tracking", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1999. Accessed: Sep. 19, 2017.
@article{1999-17,
url = {http://sigport.org/1999},
author = {Yu Qiao },
publisher = {IEEE SigPort},
title = {Context-Based Occlusion Detection for Robust Visual Tracking},
year = {2017} }
TY - EJOUR
T1 - Context-Based Occlusion Detection for Robust Visual Tracking
AU - Yu Qiao
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1999
ER -
Yu Qiao. (2017). Context-Based Occlusion Detection for Robust Visual Tracking. IEEE SigPort. http://sigport.org/1999
Yu Qiao, 2017. Context-Based Occlusion Detection for Robust Visual Tracking. Available at: http://sigport.org/1999.
Yu Qiao. (2017). "Context-Based Occlusion Detection for Robust Visual Tracking." Web.
1. Yu Qiao. Context-Based Occlusion Detection for Robust Visual Tracking [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1999