Improvements in accuracy of single camera terrain classification

Syed Muhammad Abbas, Abubakr Muhammad, Syed Atif Mehdi, Karsten Berns
2013 2013 16th International Conference on Advanced Robotics (ICAR)  
Autonomous terrain classification is an important requirement for robotic applications for the outdoor and more so for off-road systems. Different technique have been developed in recent years mainly relying on either color features or on texture-based features for classification. We present an approach which combines the two approaches and delivers an overall increase in performance and accuracy. We describe the computational framework, training dataset, off-line learning and real-time
more » ... cation results of our system. We report overall average classification accuracies in excess of 98% in a fair experimental setup along with confusion matrices. Our method gives a noticeable improvement in accuracy for classifying similar terrain classes over the current state of the art that uses only texture for classification with acceptable overhead for real-time applications.
doi:10.1109/icar.2013.6766493 dblp:conf/icar/AbbasMMB13 fatcat:xg5r5y7nknbypohswbyqczvpcq