Pfinder: Real-Time Tracking of the Human Body
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
A Framework for High-Level Feedback to Adaptive, Per-Pixel, Mixture-of-Gaussian Background Models
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
A Hierarchical Approach to Robust Background Subtraction using Color and Gradient Information
MOTION '02 Proceedings of the Workshop on Motion and Video Computing
Efficient Design of Advanced Correlation Filters for Robust Distortion-Tolerant Face Recognition
AVSS '03 Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance
Segmenting Foreground Objects from a Dynamic Textured Background via a Robust Kalman Filter
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Image segmentation in video sequences: a probabilistic approach
UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence
Real-time object tracking with relevance feedback
Proceedings of the 6th ACM international conference on Image and video retrieval
Object matching in disjoint cameras using a color transfer approach
Machine Vision and Applications
Minimizing Video Data Using Looping Background Detection Technique
PCM '09 Proceedings of the 10th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Background subtraction for automated multisensor surveillance: a comprehensive review
EURASIP Journal on Advances in Signal Processing - Special issue on advanced image processing for defense and security applications
Hi-index | 0.00 |
Accurate background modeling is fundamentally important to motion-based segmentation, object tracking, and video surveillance. Models must discriminate between coherent foreground motion and periodic, random, or small pixel variations typically found in complex outdoor scenes. We introduce an adaptive match filter framework that is capable of modeling the locally changing spatial image structure. The correlation values of these filters are combined to robustly discriminate foreground regions from regions that conform to the background model. Each filter is constrained to produce a predefined correlation value with the previously seen background blocks for a particular offset and resolution while minimizing the average energy of the correlation plane. The power spectrum of each sample is weighed by the local temporal gradient to take into account regions that exhibit significant change. The system is demonstrated on challenging outdoor environments including object motion near swaying trees and objects on moving water. Results compare favorably to traditional parametric pixel-based methods that produce a significant number of false-positives under similar conditions.