Nondeterministic Criteria to Discard Redundant Information in Real Time Autonomous Navigation Systems based on Monocular Vision

Navigation of a mobile robot is based on its interaction with the environment through information acquired by sensors. Particularly for mobile robot navigation in unknown environment, the type and number of sensors determines the data volume necessary to process and compose the image from the environment. Nevertheless, the excess of information imposes a great computational cost in data processing. Based on the fact that real-time navigation systems could have their performance compromised by the need of processing all this redundant information, in previous work we presented an automatic image discarding method. Our experiments showed that about 90% of the images can be discarded without loss of information. In this work we developed further this discarding process, proposing a nondeterministic discarding criteria, based on information generated by the TH Finder (threshold and horizon finder) method. The TH Finder is a machine vision segmentation algorithm capable of identifying the navigation area from an image captured by a single camera. Our algorithm is not based on previous knowledge of the environment neither from the image acquisition system and does not depend on information from signs or marks on the road, what makes it robust and well suitable also for nonstructured roads. As a dynamic threshold search method, it is not affected by illumination changes and does not need any contrast adjustments. Experiments showed that the nondeterministic discarding criteria assumed different values according to the amount of obstacles or details in images, thus adjusting the discarding rate of redundant information to each individual situation.