Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
What Energy Functions Can Be Minimizedvia Graph Cuts?
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian Modeling of Dynamic Scenes for Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Dynamic Conditional Random Field Model for Foreground and Shadow Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Framework for Feature Selection for Background Subtraction
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
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 and Vision Computing
Hi-index | 0.01 |
Kernel-based density estimation have been successful for background subtraction in complex environments where background statistics at the pixel level cannot be described parametrically. These methods, however, typically requires a training sequence free or mostly free of foreground activity in order to get a good initial estimate of the background distribution. We present an approach for non-parametric statistical modeling of both foreground and background in complex and busy environments without any restrictions or constraints on the scene foreground activity at initialization. Our unsupervised approach uses the difference in relative frequency and probability mass between background and foreground modes to generate foreground and background likelihood functions as well as estimates of foreground and background priors. For each frame, the output is a non-binary mask of foreground probabilities which can be easily combined with spatial and temporal constraints in an intelligent decision process. Results show that our approach performs well in a variety of complex scenarios where foreground probabilities can be as high as 80%.