Lokesh Peddireddi
Object Tracking and Velocity
Determination using TMS320C6416T DSK
Internship Project Report
Studium Information Technology
Alpen-Adria-Universität Klagenfurt
Fakultät für Technische Wissenschaften
Begutachter: Univ.Prof. Dr. techn. Bernhard Rinner
Betreuer: Univ.Ass. Dipl.Ing. Wolfgang Schriebl
Institute of Networked and Embedded Systems
Pervasive Computing
Klagenfurt, im April 2008
Abstract
This project deals with the tracking and following of single object in a sequence of frames
and the velocity of the object is determined. Algorithms are developed for improving
the image quality, segmentation, feature extraction and for deterring the velocity. The
developed algorithms are implemented and evaluated on TMS320C6416T DSP Starter
Kit (DSK). Segmentation is performed to detect the object after reducing the noise from
that scene. The object is tracked by plotting a rectangular bounding box around it in
each frame. The velocity of the object is determined by calculating the distance that the
object moved in a sequence of frames with respect to the frame rate that the video is
recorded. The algorithms developed can also be used for other applications (real time,
object classication, etc.).
i
Acknowledgments
I would like to thank my project advisor Mr. Wolfgang Schriebl, Pervasive Computing
Group, for constantly supporting me throughout the project and guiding me in a proper
way.
I am grateful to Prof. Dr. techn. Bernhard Rinner, Pervasive Computing Group,
Alpen-Adria University, for giving me a very good opportunity to carry out my internship
work in this group and for providing me sucient resources to accomplish this project.
ii
Contents
1 Introduction 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Goal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.3 Outline of the Project . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
2 Single Object Tracking 2
2.1 Pre-processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
2.1.1 Mean Filter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
2.1.2 Gaussian Smoothing . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2.1.3 Median Filter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2.2 Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2.2.1 Histogram Based Segmentation . . . . . . . . . . . . . . . . . . . . . 3
2.2.2 Single Gaussian Background Method . . . . . . . . . . . . . . . . . . 4
2.2.3 Frame Dierence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.3 Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.3.1 Edges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.3.2 Bounding Box with Colour Feature . . . . . . . . . . . . . . . . . . . 5
2.4 Object Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.4.1 Optical Flow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.4.2 Block Matching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.5 Tracking . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.5.1 Velocity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
3 Algorithms 7
3.1 Noise removal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.2 Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.3 Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.4 Distance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.5 Velocity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
4 Implementation and Evaluation 10
4.1 Hardware Specication . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
4.2 Conversion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
4.2.1 Video to images . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
4.2.2 Image to hexadecimal format . . . . . . . . . . . . . . . . . . . . . . 12
4.3 Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
iii
4.4 Noise Removal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
4.5 Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
4.6 Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
4.7 Distance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
4.8 Velocity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
5 Results 17
6 Conclusion 19
Bibliography 20
iv
- 1
- 2
前往页