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 de ne 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 e ciently. The paper compares di erent wavelet transformations used for feature extraction.

• Type: Conference
• Year: 1997
• Where: ICIP
• Authors: Heinrich Niemann, Josef Pösl
• Keywords: Global Pose Search, Hierarchical Pose Estimation, ICIP 1997, Image Processing, Paper Compares Di