Pfinder: Real-Time Tracking of the Human Body
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
W4: Who? When? Where? What? A Real Time System for Detecting and Tracking People
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Detecting Moving Shadows: Algorithms and Evaluation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image segmentation in video sequences: a probabilistic approach
UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence
Basic Video-Surveillance with Low Computational and Power Requirements Using Long-Exposure Frames
ACIVS '08 Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems
IEICE - Transactions on Information and Systems
Efficient wavelet based detection of moving objects
DSP'09 Proceedings of the 16th international conference on Digital Signal Processing
Optimal wavelet differencing method for robust motion detection
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
ISIDIS: an intelligent videosurveillance system
Proceedings of the International Working Conference on Advanced Visual Interfaces
Abrupt motion tracking using a visual saliency embedded particle filter
Pattern Recognition
Hi-index | 0.00 |
In this paper we propose a robust approach to detect moving objects for video surveillance applications. We demonstrate that a jointly use of frame by frame difference with a background subtraction algorithm allows us to have a strong and fast pixel foreground classification without the need of previous background learning. The Joint Difference algorithm uses frame difference information to correct pixels classification made by a background subtraction algorithm while selectively updating the background model according to such classification. In this way we should perform motion segmentation also in presence of environmental changes such as illumination variations or "waking persons". The algorithm is capable of 15 fps tracking of moving people on 640-480 unsampled color images; results on both VSSN06 and Wallflower [8] benchmark videos are presented.