HSV and RGB color histograms comparing for objects tracking among non overlapping FOVs, using CBTF

Object tracking over wide-areas, such as an airport, the downtown of a large city or any large public area, is done by multiple cameras. Especially in realistic application, those cameras have non overlapping Field of Views (FOVs). Multiple camera tracking is very important to establish correspondence among detected objects across different cameras. In this paper we investigate color histogram techniques to evaluate inter-camera tracking algorithm based on object appearances. We compute HSV and RGB color histograms in order to evaluate their performance in establishing correspondence between object appearances in different FOVs before and after Cumulative Brightness Transfer Function (CBTF).