Page 1 |
Save page Remove page | Previous | 1 of 215 | Next |
|
small (250x250 max)
medium (500x500 max)
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
Subset
|
PART BASED OBJECT DETECTION, SEGMENTATION, AND TRACKING
BY BOOSTING SIMPLE SHAPE FEATURE BASED WEAK CLASSIFIERS
by
Bo Wu
A Dissertation Presented to the
FACULTY OF THE GRADUATE SCHOOL
UNIVERSITY OF SOUTHERN CALIFORNIA
In Partial Fulfillment of the
Requirements for the Degree
DOCTOR OF PHILOSOPHY
(COMPUTER SCIENCE)
August 2008
Copyright 2008 Bo Wu
Object Description
| Title | Part based object detection, segmentation, and tracking by boosting simple shape feature based weak classifiers |
| Author | Wu, Bo |
| Author email | bowu@usc.edu |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Computer Science |
| School | Viterbi School of Engineering |
| Date defended/completed | 2008-04-11 |
| Date submitted | 2008 |
| Restricted until | Unrestricted |
| Date published | 2008-06-25 |
| Advisor (committee chair) | Nevatia, Ram |
| Advisor (committee member) |
Medioni, Gerard Tjan, Bosco |
| Abstract | Detection, segmentation, and tracking of objects of a known class is a fundamental problem in computer vision. For this task, we need to first detect the objects of interest and segment them from the background, and then track them across different frames while maintaining the correct identities. The two principle sources of difficulty in performing this task are: a) change in appearance of the objects with viewpoint, illumination, and possible articulation, and b) partial occlusion of objects of interest by other objects. The objective of this work is to develop a system to automatically detect, segment, and track multiple, possibly partially occluded objects of a known class from a single camera. We take pedestrians, which are important for many real-life applications, as the main class of interest to demonstrate our approach. However, some components of the method are also applied to the class of cars to show the generality of our approach.; We represent an object as a hierarchy of parts. The use of a part based model enables us to detect and track objects when some parts are not visible. We have developed a new type of shape oriented features, called edgelet, to capture the silhouette based patterns. We have integrated the edgelet features with some other existing shape features, and learned tree structured classifiers for object parts. Part detection responses are combined jointly so that the spatial relations, including possible occlusions, between multiple objects are analyzed. For specific applications, an unsupervised, online learning algorithm is used to improve the performance of the detectors by adapting them to the particular environment. Object segmentor, whose output is pixel-level figure-ground segmentation, is learned based on local shape features. The object detection and segmentation results provide the observations for tracking. Trajectory initialization and termination are both automatic and rely on the detection results. Two complementary techniques, data association and mean-shift, are used to track an object.; An automatic object detection and tracking system has been implemented and evaluated on a number of images and videos. The experimental results show that our method achieves state-of-the-art performance. |
| Keyword | object detection and tracking; AdaBoost |
| Language | English |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Type | texts |
| Legacy record ID | usctheses-m1290 |
| Contributing entity | University of Southern California |
| Rights | Wu, Bo |
| Repository name | Libraries, University of Southern California |
| Repository address | Los Angeles, California |
| Repository email | http://www.usc.edu/isd/libraries/services/ask_a_librarian/email/ |
| Filename | etd-Wu-20080625 |
| Archival file | uscthesesreloadpub_Volume44/etd-Wu-20080625.pdf |
Description
| Title | Page 1 |
| Contributing entity | University of Southern California |
| Full text | PART BASED OBJECT DETECTION, SEGMENTATION, AND TRACKING BY BOOSTING SIMPLE SHAPE FEATURE BASED WEAK CLASSIFIERS by Bo Wu A Dissertation Presented to the FACULTY OF THE GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (COMPUTER SCIENCE) August 2008 Copyright 2008 Bo Wu |
