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

facebooktwittermailshare

DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY MATCHING WHEN NOT

Abstract: 

Visual tracking frameworks employing Convolutional Neural Networks (CNNs) have shown state-of-the-art performance due to their hierarchical feature representation. While classification and update based deep neural net tracking have shown good performance in terms of accuracy, they have poor tracking speed. On the other hand, recent matching based techniques using CNNs show higher than real-time speed in tracking but this speed is achieved at a considerably lower accuracy. To successfully manage the trade-off between accuracy and speed, we propose a novel CNN architecture for visual tracking. We achieve this trade-off balance by using an approach in which consecutive similar frames are processed with a similarity matching technique, and dissimilar frames are processed with a classification approach within the CNN architecture.
The tracking speed is improved by avoiding unnecessary model updates through the measurement of similarity between adjacent frames, while the accuracy is maintained by adopting a classification approach when needed, with deeper level features.
Extensive evaluation performed on a publicly available benchmark dataset demonstrates our proposed tracker shows competitive performance while maintaining near real-time speed.

up
0 users have voted:

Paper Details

Authors:
Submitted On:
6 October 2018 - 9:51pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Kokul Thanikasalam
Paper Code:
1891
Document Year:
2018
Cite

Document Files

poster_ICIP2.pdf

(213)

Keywords

Additional Categories

Subscribe

[1] , "DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY MATCHING WHEN NOT", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3581. Accessed: May. 25, 2019.
@article{3581-18,
url = {http://sigport.org/3581},
author = { },
publisher = {IEEE SigPort},
title = {DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY MATCHING WHEN NOT},
year = {2018} }
TY - EJOUR
T1 - DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY MATCHING WHEN NOT
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3581
ER -
. (2018). DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY MATCHING WHEN NOT. IEEE SigPort. http://sigport.org/3581
, 2018. DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY MATCHING WHEN NOT. Available at: http://sigport.org/3581.
. (2018). "DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY MATCHING WHEN NOT." Web.
1. . DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY MATCHING WHEN NOT [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3581