vSlam experiments in a custom simulated environment

Abstract

In order to perform vSLAM experiments, a camera capturing information along a certain path is necessary. What if the resources to execute this are not available or a proof of concept is needed before a real application? This paper describes a simple method of combining MATLAB and Blender to perform vSLAM experiments in a custom created environment. A virtual robot and camera are created to navigate through the simulated space to capture textured images and objects that are used for the image processing. The images or video created by Blender can be easily processed by MATLAB as shown in this work. In addition, a simple application is demonstrated in the experiments section.

An Original Application of Image Recognition Based Location in Complex Indoor Environments

“…The robotics community has focused on visual odometry approaches [20] and simultaneous and location mapping (SLAM) [21,22], while other groups related to geomatics and graphics are investigating semantic features [23] or structure from motion.…”