Pfinder: Real-Time Tracking of the Human Body
IEEE Transactions on Pattern Analysis and Machine Intelligence
A view of the EM algorithm that justifies incremental, sparse, and other variants
Proceedings of the NATO Advanced Study Institute on Learning in graphical models
Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient greedy learning of Gaussian mixture models
Neural Computation
Non-parametric Model for Background Subtraction
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
"GrabCut": interactive foreground extraction using iterated graph cuts
ACM SIGGRAPH 2004 Papers
Bayesian Modeling of Dynamic Scenes for Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
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
Bilayer Segmentation of Live Video
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
A Practical Approach to Morse-Smale Complex Computation: Scalability and Generality
IEEE Transactions on Visualization and Computer Graphics
Image segmentation in video sequences: a probabilistic approach
UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence
Initializing the EM algorithm in Gaussian mixture models with an unknown number of components
Computational Statistics & Data Analysis
Integrating intensity and texture differences for robust change detection
IEEE Transactions on Image Processing
Hi-index | 0.00 |
Background subtraction techniques require high segmentation quality and low computational cost. Achieving high accuracy is difficult under abrupt illumination changes. We develop a new background subtraction method in an expectation maximization (EM) framework. We describe foreground colors and illumination ratios using a few Gaussian mixture models. EM convergence is dependent on its initialization. We propose a novel initialization method that considers reflectance and illumination implicitly. Scene points occluded by a foreground object tend to have prominent illumination ratios since both the reflectance and illumination are different. We introduce a topological approach based on Morse theory to pre-classify pixels into foreground and background. Moreover, we only decompose the probability distributions in the initial step in our EM. Later iterations do not consider the probability distribution decomposition anymore. The experimental results demonstrate that our EM formulation provides high accuracy under abrupt variations in illumination. Additionally, in comparison with one of the state-of-the-art methods based on EM, our approach converges in fewer iterations, yielding computational savings.