Smart cameras [1] are used in automatic surveillance systems and for inspection and control of production lines. Vision sensors are also mounted in autonomous vehicles or used in military systems.In case of video sequence analysis, extracting the movement parameters of individual objects present on the scene is often desired. Because objects consists of pixels, it is possible to extract their movement based on resultant value of corresponding pixels displacement. Therefore the object movement can be obtained by computing the optical flow, which is a vector field describing the relative displacement of pixels between two consecutive frames from a video sequence.Information about optical flow, is valuable in many different applications. It allows to extract the object movement direction and its speed [2].

It can also be used for classification of pixels according to their motion flow (for example in [3] rigid bodies such as cars were differentiated from people based on this premise). Moving object mask [4,5] can be obtained by thresholding the optical flow magnitude. Other possible applications are: structure from motion [6], tracking [7], human behaviour analysis [8], etc. It is worth to notice, that optical flow is essential in many embedded systems: UAV (unmanned aerial vehicle), autonomous robots, driver assistance systems etc. In such applications high computation performance, low power consumption, compact size and low weight are required.The issue of accurate optical flow computation is a separate and very comprehensive research problem.

Improvements or new algorithms were described in many publications. The summary of this efforts is presented in [9]. It is also possible to see and compare results of different methods on the web page hosted by the Middlebury University [10]. There is also a frequently updated ranking of recently proposed approaches on that site.Optical flow computation algorithms can be divided into two groups. The first one consists of methods which determine the optical flow field for every pixel of the image (dense flow). Algorithms computing the flow only for selected pixels (sparse flow) belong to the second group. This classification was proposed, because some points are easier to track than others. For example, a pixel which has a unique colour is simpler to localize than a pixel which is surrounded by other pixels of the same or similar colour.

Method Anacetrapib used for picking proper points can be very different. From choosing pixels located at a rectangular grid virtually imposed on image to corner or feature detection (e.g., Scale Invariant Feature Transform) methods. It is not possible to determine optical flow for all pixels. For example, when a pixel disappears between two frames due to occlusion. This is why dense optical flow methods use more clues to compute the flow than only pixel intensity (e.