The deep learning development for real-time ball and goal detection of barelang-FC

Abstract

Studies of object detection have recently attracted increased interest. One of the applications of object detection is robotics. This paper present the real-time object detection integrated to humanoid robot soccer. In order to enhance the vision to detect ball and goal, the You Only Look Once (YOLO) methods is used as deep-learning object detection method. The real-time experiments have been carried out in LINUX OS by using NVIDIA JETSON TX1 controller board. The experimental results show that the proposed method capable to detect and distinguish objects in the different lighting condition, with interference from other objects, also from the different angle of capturing an image.