Temporal irradiance variations are useful for finding dense stereo correspondences. These variations can be created artificially using structured light. They also occur naturally underwater. We introduce a variational optimization formulation for finding a dense stereo correspondence field. It is based on multi-frame optical flow, adapted to stereo. The formulation uses a sequence of stereo frames, and yields dense and robust results. The inherent aperture problem of optical flow is resolved using a temporal sequence of stereo frame-pairs. The results are achieved even without considering epi-polar geometry. The method has the ability to handle dynamic stereo underwater, in harsh conditions of flickering illumination. The method is demonstrated experimentally both outdoors and indoors.

Video motion detection (VMD) is a critical task demanded for surveillance and monitoring applications for both static and moving camera setup. A new VMD algorithm is proposed: the probabilistic time integrated RANSAC (PTIR) which robustly detects and tracks objects in the difficult long range scenario. The problem of detecting long range moving objects in a wide field of view from a moving camera is difficult especially in poor visibility, cluttered and noisy environments. The suggested method also copes with cases where no time correspondence information is available. The experimental results demonstrate the performance and robustness of the proposed method.