Road Scene Understanding from a Single Image

Road scene segmentation is important in computer vision for different applications such as autonomous driving and pedestrian detection. Recovering the 3D structure of road scenes provides relevant contextual information to improve their understanding. In this paper, we use a convolutional neural network based algorithm to learn features from noisy labels to recover the 3D scene layout of a road image. The novelty of the algorithm relies on generating training labels by applying an algorithm trained on a general image dataset to classify on–board images. Further, we propose a novel texture descriptor based on a learned color plane fusion to obtain maximal uniformity in road areas. Finally, acquired (off–line) and current (on–line) information are combined to detect road areas in single images. From quantitative and qualitative experiments, conducted on publicly available datasets, it is concluded that convolutional neural networks are suitable for learning 3D scene layout from...

• Type: Conference
• Year: 2012
• Where: ECCV
• Authors: Jose M. Alvarez, Theo Gevers, Yann LeCun, Antonio M. Lopez
• Keywords: Convolutional Neural Networks, Domain Adaptation, Road Detection, Road Scene Segmentation, Texture