Gray Level Thresholding in Badly Illuminated Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiple Camera Based Human Motion Estimation
ACCV '98 Proceedings of the Third Asian Conference on Computer Vision-Volume II
Tracking human motion in an indoor environment
ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol. 1)-Volume 1 - Volume 1
Hand image segmentation using sequential-image-based hierarchical adaptation
ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 1 - Volume 1
Tracking Human Motion Using Multiple Cameras
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
A Camera-Based System for Tracking People in Real Time
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
Automatic target segmentation by locally adaptive image thresholding
IEEE Transactions on Image Processing
A video surveillance system under varying environmental conditions
SPPRA'06 Proceedings of the 24th IASTED international conference on Signal processing, pattern recognition, and applications
Visual tracking of independently moving body and arms
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Hi-index | 0.00 |
We propose a novel method of extracting a moving object region from each frame in a series of images regardless of complex, changing background using statistical knowledge about the target. In vision systems for 'real worlds' like a human motion tracker, a priori knowledge about the target and environment is often limited (e.g., only the approximate size of the target is known) and is insufficient for extracting the target motion directly. In our approach, information about both target object and environment is extracted with a small amount of given knowledge about the target object. Pixel value (color, intensity, etc.) distributions for both the target object and background region are adaptively estimated from the input image sequence based on the knowledge. Then, the probability of each pixel being associated with the target object is calculated. The target motion can be extracted from the calculated stochastic image. We confirmed the stability of this approach through experiments.