Tracking of motion objects in the surveillance videos is useful for themonitoring and analysis. The performance of the surveillance system willdeteriorate when shadows are detected as moving objects. Therefore, shadowdetection and elimination usually benefits the next stages. To overcome thisissue, a method for detection and elimination of shadows is proposed. Thispaper presents a method for segmenting moving objects in video sequences basedon determining the Euclidian distance between two pixels consideringneighborhood values in temporal domain. Further, a method that segments castand self shadows in video sequences by computing the Eigen values for theneighborhood of each pixel is proposed. The dual-map for cast and self shadowpixels is represented based on the interval of Eigen values. The proposedmethods are tested on the benchmark IEEE CHANGE DETECTION 2014 dataset.
展开▼
