No Cover Image

Journal article 485 views 176 downloads

Multi-Channel Features Spatio-Temporal Context Learning for Visual Tracking

Xiaoqin Zhou, Xiaofeng Liu, Chenguang Yang, Aimin Jiang, Bin Yan

IEEE Access, Volume: 5, Pages: 12856 - 12864

Swansea University Author: Chenguang Yang

Abstract

Visual tracking is a challenging issue in surveillance, human-computer interaction and intelligent robotics, among others. Managing appearance changes of the target object, illumination changes, rotations, non-rigid deformations, partial or full occlusions, background clutter, fast motion, and so fo...

Full description

Published in: IEEE Access
ISSN: 2169-3536
Published: 2017
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa34537
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Visual tracking is a challenging issue in surveillance, human-computer interaction and intelligent robotics, among others. Managing appearance changes of the target object, illumination changes, rotations, non-rigid deformations, partial or full occlusions, background clutter, fast motion, and so forth is generally difficult. Among the numerous existing trackers, the correlationfilter- based tracker can achieve appealing performance with a fast speed for fast Fourier transform (FFT). Motivated by this property, the spatio-temporal context (STC) learning algorithm was proposed with consideration of the information from the context around the target, and this algorithm achieved good results. However, STC only utilizes the overall intensity information. In this paper, we propose a multi-channel features spatio-temporal context (MFSTC) learning algorithm with an improved scaleadaptive scheme. Our algorithm integrates powerful features, including Histogram of Oriented Gradients (HoG) and color naming, using kernel methods on the basis of the STC algorithm to further enhance the overall tracking performance. Extensive experimental results obtained from various benchmark datasets demonstrate that the proposed tracker is promising for various challenging scenarios and maintains real-time performance at an average speed of 78 fps. According to the test results, our algorithm outperforms the STC algorithm and achieves performance that is competitive with the state-of-the-art algorithms.
College: Faculty of Science and Engineering
Start Page: 12856
End Page: 12864