CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 1998 vol.20 Issue No.09 - September
Revised Definition of Optical Flow: Integration of Radiometric and Geometric Cues for Dynamic Scene Analysis
Issue No.09 - September (1998 vol.20)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.713362
<p><b>Abstract</b>—Optical flow has been commonly defined as the apparent motion of image brightness patterns in an image sequence. In this paper, we propose a revised definition to overcome shortcomings in interpreting optical flow merely as a geometric transformation field. The new definition is a complete representation of geometric and radiometric variations in dynamic imagery. We argue that this is more consistent with the common interpretation of optical flow induced by various scene events. This leads to a general framework for the investigation of problems in dynamic scene analysis, based on the integration and unified treatment of both geometric and radiometric cues in time-varying imagery. We discuss selected models, including the generalized dynamic image model in [<ref rid="bibi096121" type="bib">21</ref>], for the estimation of optical flow. We show how various 3D scene information are encoded in, and thus may be extracted from, the geometric and radiometric components of optical flow. We provide selected examples based on experiments with real images.</p>
Motion vision, optical flow, time-varying image analysis, dynamic visual cues, integration of radiometric and geometric cues.
Shahriar Negahdaripour, "Revised Definition of Optical Flow: Integration of Radiometric and Geometric Cues for Dynamic Scene Analysis", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.20, no. 9, pp. 961-979, September 1998, doi:10.1109/34.713362