Estimating the position of a moving object based on test disturbance of camera position

The problem of estimating the coordinates of a moving object based on visual data arises in numerous applications, starting from robotic and ending with the consumer market of portable devices. Traditional algorithms for solving this problem require either additional devices or significant constraints on the possible motion of the object. In this work, we present a new approach to tracking the object that lets us estimate its position under sufficiently general conditions. The method is based on randomizing the camera location independently of the object's motion; since the test disturbance we choose is independent, it lets us construct a feasible iterative pseudogradient estimation algorithm.

Presented by the member of Editorial Board: O. A. Stepanov