| Author: | Wong, Ka-fai |
| Title: | Motion-based head detection for lift control system |
| Degree: | M.Sc. |
| Year: | 2000 |
| Subject: | Image processing Optical pattern recognition Pattern recognition systems Hong Kong Polytechnic University -- Dissertations |
| Department: | Multi-disciplinary Studies Department of Electronic and Information Engineering |
| Pages: | ii, 100 leaves : ill. ; 30 cm |
| Language: | English |
| Abstract: | In this project, a motion-based head detection system is developed to segment and count moving human heads from complex background. The constraint line clustering and the block based motion compensation approach with Higher Order Statistics (HOS) are implemented to produce velocity field clusters. The constraint line clustering approach provides a robust method for scalar motion field generation. The block based motion compensation approach with HOS generates motion field vectors of an image sequence, which aims to produce compact segments of objects for further recognition. Higher order statistics algorithm instead of a typical mean square error minimization algorithm is implemented to eliminate Gaussian noise. The performance of the detector is evaluated on a number of image frames with different illumination conditions and injection of noise. In addition, a color feature-based approach is developed to extract heads from segmented objects. The possible applications in industry are also discussed in this dissertation. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b15276193.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.11 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/3319