Early Model of Vision-Based Obstacle Mapping Utilizing Grid-Edge-Depth Map

Abstract

This paper described a new method of obstacle mapping in an indoor environment utilizing a Grid-edge-depth map. The Grid-edge-depth map contained the information of distance and relative position of the object in the front of the robot. This mapping method utilized this information to mark off the visible obstacle/s in a particular virtual map. The 2D map created as a representative of the environment using a 300 by 500 pixels image. Every pixel represents a one by one cm of the environment and the obstacle's size. The obstacle's size was 30 by 30 pixels when it mapped by the system. It was a fixed size in the mapping process since the system cannot calculate the dimension of the detected obstacle. If the obstacle detected, the system checked its distance in GED-map. Then the system calculated the obstacle’s position against the goal, and finally map it in the 2D map. In this case, the proposed method in building a 2D map of the obstacle in the indoor environment combined with the rules to decide the direction of the mobile robot. The rules used to avoid the collision to the obstacle. The evaluation of the method showed that the system could map the detected obstacles, the initial position, and the goal’s relatif distance and position. The robot also reaches the goal position while avoiding the collision to the obstacle.

A Novel Algorithm of Distance Calculation Based-on Grid-Edge-Depth-Map and Gyroscope for Visually-Impaired

“…The right image is a comparator image in building a disparity map, so this right image is used in this process. This edge-detection process is resulting a binary image [15]. The white color of the edge detected obstacle value would be one, and the others will be zero (the color is black) [6].…”

“…Preliminary testing of the device's computational process has been done by setting a fixed camera angle to determine the accurate distance to objects or objects visible to the camera. The test results show that as long as the camera angle does not change, the accuracy of the computational results of actual distance measurements will remain above 90 percent [15,16]. The computational processes on the actual distance of objects in front of the user must be carried out based on the acquisition results of stereo cameras with relatively variable angles [11].…”