Robust regression and outlier detection
Robust regression and outlier detection
Pfinder: Real-Time Tracking of the Human Body
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
W4: Real-Time Surveillance of People and Their Activities
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Hierarchical Approach to Robust Background Subtraction using Color and Gradient Information
MOTION '02 Proceedings of the Workshop on Motion and Video Computing
Tomato sorting using independent component analysis on spectral images
Real-Time Imaging - Special issue on spectral imaging
A Texture-Based Method for Modeling the Background and Detecting Moving Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient adaptive density estimation per image pixel for the task of background subtraction
Pattern Recognition Letters
Consensus sets for affine transformation uncertainty polytopes
Computers and Graphics
Motion-based background subtraction using adaptive kernel density estimation
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Image segmentation in video sequences: a probabilistic approach
UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence
Statistical modeling of complex backgrounds for foreground object detection
IEEE Transactions on Image Processing
Hi-index | 0.00 |
Background modeling is fundamentally important in the computer vision tasks such as image understanding, object tracking and video surveillance. It is especially difficult in the complex natural scenes, mainly due to two matters: 1) gross errors resulted by random outliers that can not be described in a uniform distribution; 2) structural confusion cluttered by sample sets' polymorphism, which is originated by multiple structures. For dealing with these problems, a novel robust background modeling algorithm is presented. The model is established by an improved Multi-RANSAC approach for dynamic background pixels and by one-tail trimmed sample mean estimator for static pixels. A three-component-set is derived for the model so that it can be updated quickly in a unified framework for both types. It stands right even when there are more than 70 percent outliers and is fit for complex natural scenes. Quantitative evaluation and comparisons with traditional methods show that the proposed method has much improved results.