We propose a new method, video repairing, to robustly infer missing static background and moving foreground due to severe damage or occlusion from a video. To recover background pixels, we extend the image repairing method, where layer segmentation and homography blending are used to preserve temporal coherence and avoid flickering. By exploiting the constraint imposed by periodic motion and a subclass of camera and object motions, we adopt a two-phase approach to repair moving foreground pixels: In the sampling phase, motion data are sampled and regularized by 3D tensor voting to maintain temporal coherence and motion periodicity. In the alignment phase, missing moving foreground pixels are inferred by spatial and temporal alignment of the sampled motion data at multiple scales. We experimented our system with some difficult examples, where the camera can be stationary or in motion.
Video repairing: inference of foreground and background under severe occlusion
2004-01-01
1044463 byte
Conference paper
Electronic Resource
English
Video Repairing: Inference of Foreground and Background under Severe Occlusion
British Library Conference Proceedings | 2004
|Smooth Foreground-Background Segmentation for Video Processing
British Library Conference Proceedings | 2006
|Two video analysis applications using foreground/background segmentation
British Library Conference Proceedings | 2003
|Video-Based Background/Foreground Estimation for Vehicle Detection
Springer Verlag | 2021
|