Simple Image Processing Algorithms for Robot Navigation in Unknown Environment

Abstract

This article deals with simple image processing algorithms which are used for navigation of the robot in unknown environment. In the beginning of the article image processing procedures used in these algorithms are defined. The transformation of coordinate system of camera to robot’s coordinate system is introduced. The main body of the article consists of the definition of L-K optical flow method used in proposed visual odometry system. Article also contains the parameter settings of the used methods. Emphasis in these algorithms has been placed on simplicity and speed, so that they can be carried out in real-time. Algorithms have been verified on several scenarios.

Landmark Finding Algorithms for Indoor Autonomous Mobile Robot Localization

“…Information about the key point's (landmark's) distance is allocated at xfinal, yfinal co ordinates of the depth image pixel. The x final , y final co ordinates are necessary to calculate (5) and (6) for correct pixel identification in the depth picture: (5) y final = R y * y landmark (6) where:…”

“…If these significant marks (characteristics) match in pairing, vectors are created between these significant marks. After that vectors characterise the position change of the mobile robot among two images (frames) that were captured by the visual system (Duchoň et al, 2014). This methodology is also called as optical flow localization (Figure 1).…”

“…This will provide by certain value characterizing the eventually maximum distance between the pair and the corresponding significant marks. The implementation and the application of this filter can help to remove cases when probably there has been captured a motion of a dynamic objects (Duchoň et al, 2014). [191]…”