Affordable Access

Access to the full text

Tracking topology structure adaptively with deep neural networks

Authors
  • Shi, Xueying1
  • Chen, Guangyong2
  • Heng, Pheng Ann2
  • Yi, Zhang1
  • 1 Sichuan University, Machine Intelligence Laboratory, College of Computer Science, Chengdu, People’s Republic of China , Chengdu (China)
  • 2 Chinese University of Hong Kong, Department of Computer Science and Engineering, Hongkong, People’s Republic of China , Hongkong (China)
Type
Published Article
Journal
Neural Computing and Applications
Publisher
Springer London
Publication Date
Mar 08, 2017
Volume
30
Issue
11
Pages
3317–3326
Identifiers
DOI: 10.1007/s00521-017-2906-y
Source
Springer Nature
Keywords
License
Yellow

Abstract

Object tracking still remains challenging in computer vision because of the severe object variation, e.g., deformation, occlusion, and rotation. To handle the object variation and achieve robust object tracking performance, we propose a novel relationship-based tracking algorithm using neural networks in this paper. Compared with existing approaches in the literature, our method assumes the targeted object to be consisted of several parts and considers the evolution of the topology structure among these parts. After training a candidate neural network for predicting the probable areas each part may locate at in the successive frame, we then design a novel collaboration neural network to determine the precise area each part will locate at with account for the topology structure among these individual parts, which is learned from their historical physical locations during online tracking process. Experimental results show that the proposed method outperforms state-of-the-art trackers on a benchmark dataset, yielding the significant improvements in accuracy on high-distorted sequences.

Report this publication

Statistics

Seen <100 times