Highway 3D model from image and lidar data

We present a new method of highway 3-D model construction developed based on feature extraction in highway images and LIDAR data. We describe the processing road coordinate data that connect the image frames to the coordinates of the elevation data. Image processing methods are used to extract sky, road, and ground regions as well as significant objects (such as signs and building fronts) in the roadside for the 3D model. LIDAR data are interpolated and processed to extract the road lanes as well as other features such as trees, ditches, and elevated objects to form the 3D model. 3D geometry reasoning is used to match the image features to the 3D model. Results from successive frames are integrated to improve the final model.

[1]  Lu Wang,et al.  3D building reconstruction from LiDAR data , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[2]  Lu Wang,et al.  Graph theoretic segmentation of airborne lidar data , 2008, SPIE Defense + Commercial Sensing.

[3]  Suya You,et al.  Urban Site Modeling from LiDAR , 2003, ICCSA.

[4]  Alexei A. Efros,et al.  Geometric context from a single image , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[5]  Aloysius Wehr,et al.  Airborne laser scanning—an introduction and overview , 1999 .

[6]  D Veneziano.  ACCURACY EVALUATION OF LIDAR-DERIVED TERRAIN DATA FOR HIGHWAY LOCATION , 2002 .

[7]  Alexei A. Efros,et al.  Blocks World Revisited: Image Understanding Using Qualitative Geometry and Mechanics , 2010, ECCV.

[8]  Claus Brenner,et al.  Extraction of buildings and trees in urban environments , 1999 .