Self Localization with Edge Detection in 3D Space

摘要

The paper describes our contribution in the field of visual localization as a desirable feature of an autonomous mobile robot in an unknown environment. Reviewing current approaches, our paper provides an improved algorithm to track 3D straight edges, facilitated by the use of Kinect (a camera developed by Microsoft corporation) to provide RGB color image as well as the depth map through IR sensor on it. Correspondence between edges in two consecutive frames is established through edge templates. Following this is the determination of rotation and translation of edges from one frame to the matched corresponding edge in other frames using a set of edge descriptors (six parameters of a straight edge in 3D) to update subsequent camera positions. Finally, we compare the result with measurements made from an independent source, the Personal Space Tracker (PST-110) manufactured by Personal Space Technologies. 