As we move towards improving the skill of computers to play games like chess against\nhumans, the ability to accurately perceive real-world game boards and game states remains a\nchallenge in many cases, hindering the development of game-playing robots. In this paper, we\npresent a computer vision algorithm developed as part of a chess robot project that detects the\nchess board, squares, and piece positions in relatively unconstrained environments. Dynamically\nresponding to lighting changes in the environment, accounting for perspective distortion, and using\naccurate detection methodologies results in a simple but robust algorithm that succeeds 100% of\nthe time in standard environments, and 80% of the time in extreme environments with external\nlighting. The key contributions of this paper are a dynamic approach to the Hough line transform,\nand a hybrid edge and morphology-based approach for object/occupancy detection, that enable the\ndevelopment of a robot chess player that relies solely on the camera for sensory input.
Loading....