We describe a method to solve the stereo correspondence using controlled eye (or camera) movements. These eye movements essentially supply additional image frames which can be used to constrain the stereo matching. Because the eye movements are small, traditional methods of stereo with multiple frames will not work. We develop an alternative approach using a systematic analysis to define a probability distribution for the errors. Our matching strategy then matches the most probable points first, thereby reducing the ambiguity for the remaining matches. We demonstrate this algorithm with several examples.

The dissertation followed 3 research goals: to compare the availability of controlled physical activities in children with mental, hearing, visual disability in selected regions of the EU countries (South Bohemia-Czech Republic, Plovdiv-Bulgaria, Primorska-Slovenia, West Midlands-UK), then in experimental investigation in South Bohemia to monitor indicators of physical health in samples of children with named disabilities, and in same children to monitorindicators of psychosocial health.Analytical research investigations related to availability of controlled movement activities included children aged 8-15 years with researched disabilities, registered in the school systems of analysed regions of EU countries (N=12073 children, 6355 males, 5718 females). In followed experimental investigation in South Bohemia 180 children participated (90 males, 90 females) aged 8 - 15years, weredividedin samplesaccordingresearched disabilities.Evaluation of the data and their statistic interpretation verified the hypotheses. Research results have shown that children with observed types of disabilities can achieve positive effects in anthropometric indicators of training under the influence of controlled physical activities. Research results present also benefits for the social rehabilitation of children with disability in the problematic of reducing fearful behaviour symptoms and in increasing of independent behaviour.