An Integrated Image Filter for Enhancing Change Detection Results

Abstract

Change detection is a fundamental task in computer vision. Despite the fact that significant advances have been made, most of the change detection methods fail to work well in challenging scenes due to ubiquitous noise and interferences. Nowadays, post-processing methods aiming to enhance the binary change detection results still fall short of the requirements on universality for distinctive scenes, applicability for different types of detection methods, accuracy, and real-time performance. Inspired by the nature of image filtering, which separates noise from pixel observations and recovers the real structure of patches, we consider utilizing image filters to enhance the detection masks. In this paper, we present an integrated filter that comprises a weighted guided image filter and a weighted spatiotemporal tree filter. The spatiotemporal tree filter leverages the global spatiotemporal information of adjacent video frames, and meanwhile, the guided filter carries out local window filtering of pixels. The main contributions are as follows. First, the proposed filter can make full use of the information of the same object in consecutive frames to improve its current detection mask by computations on a spatiotemporal minimum spanning tree. Second, the integrated filter possesses both advantages of local filtering and global filtering; it not only has good edge-preserving property but also can handle heavily textured and colorful foreground regions. Third, unlike some popular enhancement methods [Markov random field (MRF) and conditional random field (CRF)] that require either a priori background probabilities or a posteriori foreground probabilities to improve the coarse detection masks, our method is a versatile enhancement filter that can be applied after many different types of change detection methods and is particularly suitable for video sequences. The experiments demonstrate that our method is suitable to be applied after a wide range of change detection methods, and it also works effectively on various scenes. In comparison, it evidently outperforms seven popular enhancement approaches.

Keywords

• Change detection
• binary mask enhancement
• integrated filtering
• spatiotemporal tree filter
• guided image filter