Sorry, you need to enable JavaScript to visit this website.

We introduce the notion of semantic background subtraction, a novel framework for motion detection in video sequences. The key innovation consists to leverage object-level semantics to address the variety of challenging scenarios for background subtraction. Our framework combines the information of a semantic segmentation algorithm, expressed by a probability for each pixel, with the output of any background subtraction algorithm to reduce false positive detections produced by illumination changes, dynamic backgrounds, strong shadows, and ghosts.

We investigate video classification via a 3D deep convolutional neural network (CNN) that directly ingests compressed bitstream information. This idea is based on the observation that video macroblock (MB) motion vectors (that are very compact and directly available from the compressed bitstream) are inherently capturing local spatiotemporal changes in each video scene.

This project aims to propose a fast and automatic inpainting technique for high-definition videos which works under many challenging conditions such as a moving camera, a dynamic background or a long occlusion. Our algorithm does not limit to objects removal type but extends to simultaneous background and foreground reconstruction even when the moving objects are occluded for a long period. Built upon Newson et al [1] which optimizes a global patch-based function, our method holds a significant improvement by the introduction of the optical flow term.

This demonstration aims to show some resulting videos for our method presented in ICIP. It is a fast and automatic inpainting technique for high-definition videos which works under many challenging conditions such as a moving camera, a dynamic background or a long-lasting occlusion. By incorporating optical flow in a global patch-based algorithm, our method provide improvements compared to the state-of-the-art, especially in motion preservation.

This demonstration aims to show some resulting videos for our method presented in ICIP. It is a fast and automatic inpainting technique for high-definition videos which works under many challenging conditions such as a moving camera, a dynamic background or a long-lasting occlusion. By incorporating optical flow in a global patch-based algorithm, our method provide improvements compared to the state-of-the-art, especially in motion preservation.

This demonstration aims to show some resulting videos for our method presented in ICIP. It is a fast and automatic inpainting technique for high-definition videos which works under many challenging conditions such as a moving camera, a dynamic background or a long-lasting occlusion. By incorporating optical flow in a global patch-based algorithm, our method provide improvements compared to the state-of-the-art, especially in motion preservation.