SVM-based obstacles recognition for road vehicle applications
Miguel Ángel Sotelo, Jesús Nuevo, David Fernández Llorca, I. Parra, Luis Miguel Bergasa, Manuel Ocaña, R. Flores · 2005
This paper describes an obstacle Recognition System based on SVM and vision. The basic components of the detected objects are first located in the image and then combined with a SVM-based classifier. A distributed learning approach is proposed in order to better deal with objects variability, illumination conditions, partial occlusions and rotations. A large database containing thousands of object examples extracted from real road images has been created for learning purposes. We present and discuss the results achieved up to date. 1