Wavelet features for statistical object localization without segmentation

This paper describes a new technique for statistical 3-D object localization. Local feature vectors are extracted for all image positions, in contrast to segmentation in classical schemes. We define a density function for those features and describe a hierarchical pose estimation scheme for the localization of a single object in a scene with arbitrary background. We show how the global pose search on the starting level of the hierarchy can be computed efficiently. The paper compares different wavelet transformations used for feature extraction.