A lexical analogy to feature matching and pose estimation
John Albert Horst · 2002
We relate the problem of finding a correspondence between sensed and model features to that of finding a match between a random set of letters and words in a dictionary.The process is equivalent to hashing and the lexical perspective illumi nates items such as design tradeoffs, computational complexity, and hashing function definition.A method for two-dimensional pose estimation based on this concept has been implemented.The method is local feature based and is robust to image warping, oc- clusion, illumination anomalies, and sensed feature generation er- rors.The method will work with certain modifications for three- dimensional data.The domain is restricted to translation and rota- tion invariant applications, since many pose estimation problems do not require scale and skew invariance.This non-affine con- straint can reduce computational and storage complexity vis a vis a fully affine transformation invariant technique.