Improvements and Experiments of a Compact Statistical Background Model
This work addresses background modeling for video-based applications, but it is incremental as it builds on existing statistical approaches with minor improvements.
The paper tackled the problem of change detection in video by proposing a compact statistical background model that uses spatial correlation and a single Gaussian for intensity deviations, with results showing it is comparable to recent methods on the changedetection.net dataset.
Change detection plays an important role in most video-based applications. The first stage is to build appropriate background model, which is now becoming increasingly complex as more sophisticated statistical approaches are introduced to cover challenging situations and provide reliable detection. This paper reports a simple and intuitive statistical model based on deeper learning spatial correlation among pixels: For each observed pixel, we select a group of supporting pixels with high correlation, and then use a single Gaussian to model the intensity deviations between the observed pixel and the supporting ones. In addition, a multi-channel model updating is integrated on-line and a temporal intensity constraint for each pixel is defined. Although this method is mainly designed for coping with sudden illumination changes, experimental results using all the video sequences provided on changedetection.net validate it is comparable with other recent methods under various situations.