Stationary background generation: an alternative to the difference of two images
Pattern Recognition
Pfinder: Real-Time Tracking of the Human Body
IEEE Transactions on Pattern Analysis and Machine Intelligence
Background Initialization in Cluttered Sequences
CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Pattern Recognition, Third Edition
Pattern Recognition, Third Edition
A novel robust statistical method for background initialization and visual surveillance
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Journal on Image and Video Processing - Special issue on advanced video-based surveillance
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
Hi-index | 0.00 |
Many computer vision algorithms such as object tracking and event detection assume that a background model of the scene under analysis is known. However, in many practical circumstances it is unavailable and must be estimated from cluttered image sequences. We propose a sequential technique for background estimation in such conditions, with low computational and memory requirements. The first stage is somewhat similar to that of the recently proposed agglomerative clustering background estimation method, where image sequences are analysed on a patch by patch basis. For each patch location a representative set is maintained which contains distinct patches obtained along its temporal line. The novelties lie in iteratively filling in background areas by selecting the most appropriate candidate patches according to the combined frequency responses of extended versions of the candidate patch and its neighbourhood. It is assumed that the most appropriate patch results in the smoothest response, indirectly enforcing the spatial continuity of structures within a scene. Experiments on real-life surveillance videos demonstrate the efficacy of the proposed method.