Skip to main content

Visual Object Tracking from Correlation Filter to Deep Learning

  • Book
  • © 2021

Overview

  • Presents context aware, scale pyramid, and multi-scale superpixels to optimize correlation filter based trackers
  • Designs memory term, content perception and channel attention for correlation filter with deep feature based trackers
  • Proposes attention shake, frequency-aware, and epsilon-greedy to improve deep learning based trackers

This is a preview of subscription content, log in via an institution to check access.

Access this book

eBook USD 119.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 159.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book USD 159.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

Licence this eBook for your library

Institutional subscriptions

Table of contents (6 chapters)

Keywords

About this book

The book focuses on visual object tracking systems and approaches based on correlation filter and deep learning. Both foundations and implementations have been addressed. The algorithm, system design and performance evaluation have been explored for three kinds of tracking methods including correlation filter based methods, correlation filter with deep feature based methods, and deep learning based methods. Firstly, context aware and multi-scale strategy are presented in correlation filter based trackers; then, long-short term correlation filter, context aware correlation filter and auxiliary relocation in SiamFC framework are proposed for combining correlation filter and deep learning in visual object tracking; finally, improvements in deep learning based trackers including Siamese network, GAN and reinforcement learning are designed. The goal of this book is to bring, in a timely fashion, the latest advances and developments in visual object tracking, especially correlation filter and deep learning based methods, which is particularly suited for readers who are interested in the research and technology innovation in visual object tracking and related fields.

Authors and Affiliations

  • School of Software Engineering, Beijing Jiaotong University, Beijing, China

    Weiwei Xing, Shunli Zhang, Yuxiang Yang, Bowen Song

  • Institute of Information Science, Beijing Jiaotong University, Beijing, China

    Weibin Liu

  • College of Electronic Information Engineering, Hebei University, Baoding, China

    Jun Wang

  • Department of Information and Communication, Army Academy of Armored Forces Academy, Beijing, China

    Lihui Wang

About the authors

Weiwei Xing received the B.S. degree in computer science and technology and the Ph.D. degree in Signal and Information Processing from Beijing Jiaotong University, Beijing, China, in 2001 and 2006, respectively. She was also a visiting researcher at Department of Computer Science in University of Pennsylvania, PA, USA from Feb.2011 to Feb. 2012. She is currently a Professor at School of Software Engineering, Beijing Jiaotong University. Her research interests include video information processing, computer vison, machine learning, big data analysis and software engineering.




Weibin Liu received the Ph.D. degree in Signal and Information Processing from Institute of Information Science at Beijing Jiaotong University, China, in 2001. During 2001-2005, he was a researcher in Information Technology Division at Fujitsu Research and Development Center Co., LTD. Since 2005, he has been with the Institute of Information Science at Beijing Jiaotong University, where currently he is a professor in Digital Media Research Group. He was also a visiting researcher in Center for Human Modeling and Simulation at University of Pennsylvania, PA, USA during 2009-2010. His research interests include computer vision, computer graphics, image processing, virtual human and virtual environment, and pattern recognition. 


Jun Wang received the M.S. degree in Pattern Recognition and Intelligent Systems from Hebei University, China, in 2015. He received the Ph.D degree in Signal and Information Processing from Institute of Information Science at Beijing Jiaotong University, China. He was also a visiting researcher in Visual Object Tracking at University of Central Florida, USA during 2018-2019. Currently, he is an associate professor at College of Electronic Information Engineering, Hebei University. His research interests include image processing, computer vision, visual object tracking and pattern recognition.


Shunli Zhang received the B.S. and M.S. degrees in electronics and information engineering from Shandong University, Jinan, China, in 2008 and 2011, respectively, and the Ph.D. degree in signal and information processing from Tsinghua University in 2016. He was a visiting scholar in Carnegie Mellon University, Pittsburgh, from 2018 to 2019. He is currently an associate professor in School of Software Engineering, BeijingJiaotong University. His research interests include pattern recognition, computer vision, and image processing.


Lihui Wang received the Ph.D. degree in Signal and Information Processing from Beijing Jiaotong University, Beijing, China, in 2011. She is currently a lecturer of the Department of Information and Communication, Army Academy of Armored Forces Academy. Her main research interests include computer application, big data analysis, and three-dimensional reconstruction.


Yuxiang Yang received theB.S. degree in computer science and technology from the Northeastern University of China, Liaoning, China, in 2014. He is currently a Ph.D. Candidate at School of Software Engineering, Beijing Jiaotong University. His research interests include deep learning, reinforcement learning, and object tracking.


Bowen Song received the B.S. degree in computer science and technology from the School of Computer Science and Technology, Heilongjiang University, China, in 2018. She is currently pursuing the master’s degree at School of Software Engineering, Beijing Jiaotong University. Her research interests include visual object tracking, and deep learning.


Bibliographic Information

  • Book Title: Visual Object Tracking from Correlation Filter to Deep Learning

  • Authors: Weiwei Xing, Weibin Liu, Jun Wang, Shunli Zhang, Lihui Wang, Yuxiang Yang, Bowen Song

  • DOI: https://doi.org/10.1007/978-981-16-6242-3

  • Publisher: Springer Singapore

  • eBook Packages: Computer Science, Computer Science (R0)

  • Copyright Information: The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021

  • Hardcover ISBN: 978-981-16-6241-6Published: 19 November 2021

  • Softcover ISBN: 978-981-16-6244-7Published: 20 November 2022

  • eBook ISBN: 978-981-16-6242-3Published: 18 November 2021

  • Edition Number: 1

  • Number of Pages: XIV, 193

  • Number of Illustrations: 41 b/w illustrations, 84 illustrations in colour

  • Topics: Image Processing and Computer Vision, Computer Imaging, Vision, Pattern Recognition and Graphics, Artificial Intelligence

Publish with us