Multi-Image Matching for a General Motion Stereo Camera Model

Motion stereo is to extract the 3-0 information of an object from images of a moving camera, using geometric relationships between corresponding points. This paper presents an accurate and robust motion stereo algorithm employing multiple images, taken under a general motion. The object functions for individual stereo pairs are represented, with respect to the distance, then these object functions are integrated, considering the position of cameras and the shape of the object functions. By integrating the general motion stereo images, we not only reduce the ambiguities in correspondence, but also improve the precision of reconstruction. Also by introducing an adaptive window technique, we can alleviate the effect of projective distortion in matching features and improve accuracy greatly. Experimental results on the synthetic and real data set are presented to demonstrate the performance of the proposed algorithm.

• Type: Conference
• Year: 1998
• Where: ICIP
• Authors: Ja Seong Ku, Kyoung Mu Lee, Sang Uk Lee
• Keywords: ICIP 1998, Image Processing, Motion Stereo Algorithm, Motion Stereo Images, Object Functions