Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic extraction of roads from aerial images based on scale space and snakes
Machine Vision and Applications
Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
ICAPR '09 Proceedings of the 2009 Seventh International Conference on Advances in Pattern Recognition
General road detection from a single image
IEEE Transactions on Image Processing
Color-based road detection in urban traffic scenes
IEEE Transactions on Intelligent Transportation Systems
| Hi-index | 0.00 |
The problem of road segment extraction from high resolution satellite or aerial images has been considered in this paper. Efficient extraction of road segments is a difficult task due to the problems regarding image acquisition, local road width and orientation etc. A novel method of road region extraction using local spectral and geometrical properties has been proposed here. The image is first segmented using mean-shift based approach. Edge preserving smoothing is performed beforehand to preserve the sharpness of the object boundaries. Then a rejection stage using chord distribution technique is considered to remove dominant non-road regions. It is followed by a cost optimization step based on a region following grid graph to efficiently extract the road segments. A further orientation based region linking is performed to overcome problems due to occlusion. Experiments on several high resolution satellite images have established the capability of the proposed method.