3D Scene Priors for Road Detection

Vision-based road detection is important in different areas of computer vision such as autonomous driving, car collision warning and pedestrian crossing detection. However, current vision-based road detection methods are usually based on low-level features and they assume structured roads, road homogeneity, and uniform lighting conditions. Therefore, in this paper, contextual 3D information is used in addition to low-level cues. Low-level photometric invariant cues are derived from the appearance of roads. Contextual cues used include horizon lines, vanishing points, 3D scene layout and 3D road stages. Moreover, temporal road cues are included. All these cues are sensitive to different imaging conditions and hence are considered as weak cues. Therefore, they are combined to improve the overall performance of the algorithm. To this end, the low-level, contextual and temporal cues are combined in a Bayesian framework to classify road sequences. Large scale experiments on ...

• Type: Conference
• Year: 2010
• Where: CVPR
• Authors: Jose M. Alvarez, Theo Gevers, Antonio M. Lopez
• Keywords: Autonomous Driving, Combining Classifiers, Context, Contextual Information, CVPR 2010, Diversificacion, Priors, Road Cue, Road Detection, Road Segmentation, Scene Analysis