Real-time corridor recognition adaptable for shadow and illuminance variation

In the fields of ITS and Robotics, recognition of a working environment using a vision system is critical for an autonomous vehicle such as a car controlled automatically and a mobile robot to guide it along corridor and to confirm its possible intelligence. Therefore it is necessary to equip a recognition system with some sensor, such as a CCD camera, which is generally thought to be useful for all kinds of vehicles, and can get environmental information at once. However, it is thought to be hard to use the CCD camera for visual feedback that requires to acquire the information in real-time, and moreover to be robust against lighting condition variations and existence of noises objects including a shadow. This research presents a corridor recognition method using unprocessed gray-scale image, termed here as a raw-image, and a genetic algorithm (GA), without any image information conversion, so as to perform the recognition process in real-time. Furthermore, to achieve robustness concerning lighting condition variations, we propose a model-matching method using a representative object model designated here as surface-strips model. The robustness of the method against noises in the environment, including lighting conditions variations and shadows, and the effectiveness of the method for real-time recognition have been verified using real corridor images.