Designing evaluation methodologies: The case of motion detection
N. Lazarevic-McManus, J. Renno, Dimitrios Makris, G. A. Jones · 2006
Motion detection is a fundamental processing step in the majority of visual surveillance algorithms. While an increasing number of authors are beginning to perform quantitative comparison of their algorithms, most do not address the complexity and range of the issues which underpin the design of good evaluation methodology. In this paper we explore the problems associated with optimising the operating point of detection algorithms and objective performance evaluation. A motivated and comprehensive comparative evaluation methodology is described and used to compare two motion detection algorithms reported in the literature. 1.