Motion Tracking and Stereo Vision are complicated,

\r\nalbeit well-understood problems in computer vision. Existing

\r\nsoftwares that combine the two approaches to perform stereo motion

\r\ntracking typically employ complicated and computationally expensive

\r\nprocedures. The purpose of this study is to create a simple and

\r\neffective solution capable of combining the two approaches. The

\r\nstudy aims to explore a strategy to combine the two techniques

\r\nof two-dimensional motion tracking using Kalman Filter; and depth

\r\ndetection of object using Stereo Vision. In conventional approaches

\r\nobjects in the scene of interest are observed using a single camera.

\r\nHowever for Stereo Motion Tracking; the scene of interest is

\r\nobserved using video feeds from two calibrated cameras. Using two

\r\nsimultaneous measurements from the two cameras a calculation for

\r\nthe depth of the object from the plane containing the cameras is made.

\r\nThe approach attempts to capture the entire three-dimensional spatial

\r\ninformation of each object at the scene and represent it through a

\r\nsoftware estimator object. In discrete intervals, the estimator tracks

\r\nobject motion in the plane parallel to plane containing cameras and

\r\nupdates the perpendicular distance value of the object from the plane

\r\ncontaining the cameras as depth. The ability to efficiently track

\r\nthe motion of objects in three-dimensional space using a simplified

\r\napproach could prove to be an indispensable tool in a variety of

\r\nsurveillance scenarios. The approach may find application from high

\r\nsecurity surveillance scenes such as premises of bank vaults, prisons

\r\nor other detention facilities; to low cost applications in supermarkets

\r\nand car parking lots.<\/p>\r\n","references":null,"publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 98, 2015"}