In MPEG-4, global motion estimation (GME) and global motion compensation can improve the visual quality of local motion estimation/compensation. However, the computational complexity of GME is very high. Even the existing fast algorithm, FFRGMET, in the MPEG-4 OM3 software is not fast enough. In this paper, we propose a fast GME algorithm called APSGME. It uses motion vectors from the PMVFAST l...

Fundamental to advance video processing such as object tracking, gait recognition and video indexing is the issue of robust background and foreground segmentation. Several methods have been explored regarding this application, but they are either time or memory consuming or not so efficient in segmentation. This paper proposes an accurate and fast foreground detection technique for object track...

This paper revisits the graph-cuts based approach for solving the multi-view stereo problem, and proposes a novel foreground / background energy which is shown to be unbiased and robust against noisy depth maps. Unlike most existing works which focus on deriving a robust photo-consistency energy, this paper targets at deriving a robust and unbiased foreground / background energy. By introducing...

This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a foreground element from a background image by estimating an opacity for each pixel of the foreground element. Our approach models both the foreground and background color distributions with spatiallyvarying sets of Gaussians, and assumes a fractional blending of the foreground and background colors t...

The occultation of background stars by foreground Solar system objects, such as planets and asteroids, has been widely used as an observational probe to study physical properties associated with the foreground sample. Similarly, the gravitational microlensing of background stellar sources by foreground mass concentrations has also been widely used to understand the foreground mass distribution....

In uncontrolled video surveillance environments, performing efficient foreground segmentation is very challenging. In order to improve robustness and accuracy of object detection, we take advantage of spectral information of both visible and thermal videos. This paper presents a novel joint background model combining visible and thermal videos for foreground object detection in complex scenario...

Low-cost systems that can obtain a high-quality foreground segmentation almost independently of the existing illumination conditions for indoor environments are very desirable, especially for security and surveillance applications. In this paper, a novel foreground segmentation algorithm that uses only a Kinect depth sensor is proposed to satisfy the aforementioned system characteristics. This ...

Foreground detection is a key procedure in video analysis such as object detection and tracking. Several foreground detection techniques and edge detectors have been developed until now but the problem is, usually it is difficult to obtain an optimal foreground due to weather, light, shadow and clutter interference. Background subtract is a common method in foreground detection. In background s...

Change detection is the most important task for video surveillance analytics such as foreground and anomaly detection. Current foreground detectors learn models from annotated images since the goal is to generate a robust foreground model able to detect changes in all possible scenarios. Unfortunately, manual labelling is very expensive. Most advanced supervised learning techniques based on gen...

Video matting attempts to extract foreground images from an image sequence, as well as the alpha-mattes that describe their transparency. This papers presents an automated video matting framework using motion-based segmentation and bayesian matting. We build upon existing techniques for layer segmentation based on optical flow to generate a coarse trimap, by identifying image pixels as belongin...