Extraction of local features from image sequences using spatio-temporal independent component analysis

Independent component analysis (ICA) has been used to extract salient features from natural video images. The purpose of this paper is to study how the ICA can be applied to extracting features from a sequence of images of an object taken at different time, from different view angles, or with different spatial structures. Local features are considered as basic building blocks of images. To extract localized features in image sequences, spatio-temporal ICA, which maximizes the degree of independence over space and time, is a suitable method for analyzing such image sequences and extracting local features.