“…In the earlier works of motion-stereo integration, no matter it is the mere juxtaposition of the results from independent processing of the motion and stereo information (Ayache and Faugeras, 1989;Grosso et al, 1989;Kriegman et al, 1989), where the final estimates of structure were based on some combination of the outputs of these separate processes (coupled loosely together sensus (Clark and Yuille, 1994)), or the tightly coupled approach where the processing of one type of visual information may depend on the presence of another (Balasubramanyam and Snyder, 1991;Li and Duncan, 1993;Shi et al, 1994;Waxman and Duncan, 1993;Zhang and Negahdaripour, 2008), the all but universal assumption is that the overlap in the visual field is used for computing binocular disparity. This assumption remains true in the later approaches with the advent of more sophisticated techniques such as PDE (Strecha and Gool, 2002), variational approach (Huguet and Devernay, 2007;Pons et al, 2007;Williams et al, 2005)and factorization (Ho and Chung, 2000).…”