作者: Larry S. Shapiro , Andrew Zisserman , Michael Brady
DOI: 10.1007/BF01539553
关键词:
摘要: Algorithms to perform point-based motion estimation under orthographic and scaled projection abound in the literature. A key limitation of many existing algorithms is that they operate on minimum amount data required, often requiring selection a suitable minimal set from available serve as “local coordinate frame”. Such approaches are extremely sensitive errors noise set, forfeit advantages using full set. Furthermore, attention seldom paid statistical performance algorithms.