Improving the speed of ball detection process and obstacle detection process in ERSOW robot using omnidirectional vision based on ROS

This paper presents a novel approach for improving the computation speed of ball detection and obstacle processes in our robot. The conditions robot still have slow processing speed, this condition makes not real-time robot's movement is hampered. To build good world model, things to note are information detection. focus research increase process around process, it necessary optimize use OpenCV library on operating system (ROS) divide into several small so that work can be optimally divided threads been created. Then, minimize too many frames. will sent base station also avoidance purposes.