|
Identifier |
uch.csd.tcl//2003panagiotakis |
Title |
Παρακολούθηση ανθρώπου σε ακολουθία ψηφιακών εικόνων |
Alternative Title |
Human Tracking in video sequences |
Author
|
Παναγιωτάκης, Κωνσταντίνος
|
Author
|
Τζιρίτας, Γιώργος
|
Abstract |
The analysis of image sequences containing moving non-rigid objects, such as people, has been the subject of considerable research in the field of computer vision, pattern recognition, and neural networks. The human tracking is a difficult problem because of unpredictable and complicated human motion and it is one of the most interesting problems in this field of science. We developed a prototype method to solve the 2D human tracking problem using the 18 major joint human points. The human body is divided geometrically into 6 main parts and we track each part separately. We used a 2D model, a prediction method, geometry constraints of human body and color information. The algorithm demands the position of human in the first image of sequence. Our basic purpose is to develop a low computation cost algorithm that can be used independently of camera motion. The outputs of the algorithm are the position of 18 basic human points and a 2D human segmentation in every image of video sequence. Also our method recognizes if any human part is visible or not. The precision of the results is satisfactory. However, there are cases where the tracking algorithm fails because of low quality sequences or low background contrast. These cases can be recognized by high matching errors.
|
Language |
Greek |
Issue date |
2003-03-27 |
Collection
|
School/Department--School of Sciences and Engineering--Department of Computer Science--Technical reports
|
|
Type of Work--Technical reports
|
Permanent Link |
https://elocus.lib.uoc.gr//dlib/4/0/e/metadata-dlib-2003panagiotakis_1.tkl
|
Views |
3703 |