[Information Technology] [2004.06] Omni-directional image processing for human detection and tracking

This article Czech Republic Brno University of Technology (Author:. Ing Igor Potúček) doctoral thesis, a total of 101.

This paper studies the establishment and method of a omni-directional human activity detection and tracking system. There are more and more researches on omni-directional systems because of its advantages such as low cost, good portability, and easy installation.

Its main advantage is that it can capture a large part of the 360-degree spatial angle. However, on the other hand, there are many problems that must be resolved. The images of omnidirectional systems have different characteristics from standard fluoroscopic images because they have lower effective resolution and unfavorable image distortion. If the resulting image is to be presented to people or further processed, it must be transformed and appropriately corrected.

This article proposes the technology of converting images into perspective or panoramic images and geometric correction. The mobile catadioptric system is usually prone to vibration, which results in distortion of the transformed panoramic image. Therefore, a new omnidirectional system image stabilization method is proposed.

Face and hand detection play an important role in applications such as video surveillance, human-machine interfaces, and face recognition. Wide viewing angles are the key to achieving such tasks. Therefore, a comprehensive system is very suitable for these applications. For various video sequences captured by the omnidirectional system, two different tracking methods are compared to illustrate the advantages and disadvantages of the omnidirectional system and the proposed method. The qualitative and quantitative algorithms of different video sources are described and compared, and evaluation schemes are proposed.

This work investigates the setup and the set of methods of omni-directional system for human activity detection and tracking. Research in the area of the omni-directional systems is growing, the reason are many advantages such as low cost, portability and easy installation.

The main advantage is capturing a large portion of a space angle, which is 360 degrees. On the other hand, a lot of problems exist and they must be solved. Images from omni-directional systems have different properties than standard perspective images as they have lower effective resolution and suffer adverse image distortion. If the resulting image is to be presented to a human or is further processed, transformation and suitable kind of corrections must be done. Techniques for image transformation into a perspective or panoramic view and geometrical corrections are suggested in this paper. The mobile catadioptric system is usually prone to vibrations, which cause the distortion in the transformed panoramic image. Therefore the novel approach for stabilization of the image from omni-directional system was proposed.

Human face and hands detection plays an important role in applications such as video surveillance, human computer interface, face recognition, etc. The wide view angle is important for this kind of tasks and therefore the omni-directional system is suitable for these purposes. Two different tracking methods are compared on the various kinds of video sequences captured by omni-directional system in order to demonstrate the benefits and/or drawbacks of the omni-directional system and proposed methods. The evaluation scheme was developed for qualitative and quantitative algorithm description and comparison on different video sources.

1.   引言
   

2. Omnidirectional system and image processing
3. The proposed method for the omnidirectional vision system
4. goal achieved
5. Experimental result
6. Application of the proposed method
7. Conclusion
   Appendix A Definition of Terms
   Appendix B Real-time Application of Omnidirectional System

For more exciting articles, please pay attention to the public account: