Foundations and Trends® in Signal Processing > Vol 3 > Issue 1–2

Statistical Methods and Models for Video-Based Tracking, Modeling, and Recognition

By Rama Chellappa, Department of Electrical and Computer Engineering, Center for Automation Research, UMIACS, at University of Maryland, rama@cfar.umd.edu | Aswin C. Sankaranarayanan, Department of Electrical and Computer Engineering, Rice University, saswin@rice.edu | Ashok Veeraraghavan, Mistubishi Electric Research Laboratory, veerarag@merl.com | Pavan Turaga, Department of Electrical and Computer Engineering, Center for Automation Research, UMIACS, at University of Maryland, pturaga@cfar.umd.edu

 
Suggested Citation
Rama Chellappa, Aswin C. Sankaranarayanan, Ashok Veeraraghavan and Pavan Turaga (2010), "Statistical Methods and Models for Video-Based Tracking, Modeling, and Recognition", Foundations and Trends® in Signal Processing: Vol. 3: No. 1–2, pp 1-151. http://dx.doi.org/10.1561/2000000007

Publication Date: 01 Feb 2010
© 2010 R. Chellappa, A. C. Sankaranarayanan, A. Veeraraghavan and P. Turaga
 
Subjects
Image and video processing
 
Keywords
Electrical and electronic engineeringVideo and image processing and coding
 

Free Preview:

Download extract

Share

Download article
In this article:
1 Introduction 
2 Geometric Models for Imaging 
3 Statistical Estimation Techniques 
4 Detection, Tracking, and Recognition in Video 
5 Statistical Analysis of Structure and Motion Algorithms 
6 Shape, Identity, and Activity Recognition 
7 Future Trends 
Acknowledgments 
References 

Abstract

Computer vision systems attempt to understand a scene and its components from mostly visual information. The geometry exhibited by the real world, the influence of material properties on scattering of incident light, and the process of imaging introduce constraints and properties that are key to interpreting scenes and recognizing objects, their structure and kinematics. In the presence of noisy observations and other uncertainties, computer vision algorithms make use of statistical methods for robust inference. In this monograph, we highlight the role of geometric constraints in statistical estimation methods, and how the interplay between geometry and statistics leads to the choice and design of algorithms for video-based tracking, modeling and recognition of objects. In particular, we illustrate the role of imaging, illumination, and motion constraints in classical vision problems such as tracking, structure from motion, metrology, activity analysis and recognition, and present appropriate statistical methods used in each of these problems.

DOI:10.1561/2000000007
ISBN: 978-1-60198-314-5
160 pp. $99.00
Buy book (pb)
 
ISBN: 978-1-60198-315-2
160 pp. $150.00
Buy E-book (.pdf)
Table of contents:
1: Introduction
2: Geometric Models for Imaging
3: Statistical Estimation Techniques
4: Detection, Tracking, and Recognition in Video
5: Statistical Analysis of Structure and Motion Algorithms
6: Shape, Identity and Activity Recognition
7: Future Trends
Acknowledgements
References

Statistical Methods and Models for Video-based Tracking, Modeling, and Recognition

Computer vision systems attempt to understand a scene and its components from mostly visual information. The geometry exhibited by the real world, the influence of material properties on scattering of incident light, and the process of imaging introduce constraints and properties that are key to solving some of these tasks. In the presence of noisy observations and other uncertainties, the algorithms make use of statistical methods for robust inference. Statistical Methods and Models for Video-based Tracking, Modeling, and Recognition highlights the role of geometric constraints in statistical estimation methods, and how the interplay of geometry and statistics leads to the choice and design of algorithms. In particular, it illustrates the role of imaging, illumination, and motion constraints in classical vision problems such as tracking, structure from motion, metrology, activity analysis and recognition, and appropriate statistical methods used in each of these problems

 
SIG-007