Depth Map Reconstruction Method in Control Problems for Robots and Mechatronic Systems
Aleksandr Zelensky, Nikolay Gapon, Marina M. Zhdanova, Viacheslav Voronin, Yurii V. Ilyukhin · Mekhatronika Avtomatizatsiya Upravlenie · 2022
In modern robotic and mechatronic systems, technologies are in demand that makes it possible to build an optimaltrajectory of movement of their actuators. Such technologies are formed by combining navigation methods and building a3-D map of the surrounding space based on vision systems and are successfully used in robotics and mechatronics. Butthere is a problem, consisting of a decrease in the accuracy of planning the trajectory of movement, caused by incorrectsections on the map (depth map) due to incorrect determination of the distance to objects. Such defects appear as a resultof poor lighting, specular or fine-grained surfaces of objects. This leads to the impossibility of obtaining reliable informationabout the depth. As a result, the effect of increasing the boundaries of objects (obstacles) appears, and the overlapping ofobjects makes it impossible to distinguish one object from another. This problem can be solved using image reconstructionmethods. The article presents an approach based on a modified algorithm for searching for similar blocks using the conceptof quaternions and anisotropic gradient. The analysis of the research results shows that the proposed method allows you tocorrectly restore the boundaries of objects on the depth map image when reconstructing 3-D scenes, which contributes to anincrease in the accuracy of planning the trajectory of motion of the actuators robotic and mechatronic systems.