MULTIPLE MOVING OBJECT ESTIMATION IN IMAGE SEQUENCES OF A NATURAL SCENE

Texture- and shape-preserving, velocity-selective moving object estima tion in time-sequential imageries are investigated. A 3-D spatiotempor al filter is usually effective for velocity-selective processing of no nmaneuvering moving objects. However, its performance is limited by th e inherent aliasing problem due to discrete space and time sampling of continuous signals of moving objects with various motion vectors. To complement the imaging effects due to spectral aliasing apparent in th e spectral domain processing, the time-recursive temporal low-pass fil ter, which is based on the Kalman theory, is incorporated in parallel to the proposed 3-D spatiotemporal filter banks. This temporal low-pas s filter is effective in adaptively separating relatively stationary b ackgrounds from all other moving objects. In other words, the false mo ving objects due to the imaging effect can be successfully suppressed using the binary masks of all moving objects that are obtained through the simple type of time-recursive temporal low-pass filtering. From t he simulation using several real IR Image sequences, not only for the multiple moving objects with various shapes and speeds but also for th e noisy image sequences, the highly accurate texture- and shape-preser ving, velocity-selective moving object estimation results are observed with a graceful degradation in accordance to the increased amount of noise. (C) 1997 Society of Photo-Optical Instrumentation Engineers.