354 0

Robust visual tracking through deep learning-based confidence evaluation

Title
Robust visual tracking through deep learning-based confidence evaluation
Author
임종우
Keywords
Target tracking; Neural networks; Detectors; Robustness; Visualization; deep learning tracking; tracking; detection
Issue Date
2015-10
Publisher
URAI - Ubiquitous Robots and Ambient Intelligence
Citation
Ubiquitous Robots and Ambient Intelligence (URAI), 2015 12th International Conference on , Page. 1-4
Abstract
In this paper, we propose an object tracking method through deep learning-based confidence evaluation, aiming at correctly updating an object template and on-line training a deep neural network. Our method updats both a deep neural network and a detector in Tracking-Learning-Detection(TLD) framework by robustly finding object regions highly similar to the target. We detect tracking failure points by measuring spatiotemporal similarity from Forward-Backward Error and output of the deep neural network. In addition, the proposed method adaptively updates the templates of tracker by finding the region with highest confidence of neural network within both tracking and detection results. Our experiment results demonstrate the effectiveness of the proposed method in severe environmental changes.
URI
http://ieeexplore.ieee.org/document/7358836/http://hdl.handle.net/20.500.11754/27970
ISBN
978-1-4673-7971-7
DOI
10.1109/URAI.2015.7358836
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE AND ENGINEERING(컴퓨터공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE