Building Facades Extraction from On-vehicle Camera Images in a Graph-cut-Based Optimization ramework
In this paper, a method to extract building wall textures from an on-vehicle camera images is proposed as an aid to construct the 3D maps. The building wall textures are required to attach to 3D polygons which are obtained through 3D measurements in urban space. We assume that the on-vehicle camera is under linear uniform motion and building walls are planar regions perpendicular to the optical axis. Under the assumption, the same building wall region has the same depth, or disparities, over the region among successive images. Since disparities derived from foreground objects are different from the disparities derived from the building wall, we can use the disparity differences as a clue to effectively distinguish the building walls from the foreground objects. We formulate the extraction of building wall textures incorporating these consideration as an optimization problem which can be solved by graph-cut algorithm. To show the effectiveness of the proposed method, it is applied to some sequential scenes.
building facades stereo images graph-cut optimization 3D map
Hideaki Kawano Hideaki Orii Yoshiya Fukuda Hiroshi Maeda
Kyushu Institute of Technology, 1-1 Seunsui-cho, Tobata-ku, Kitakyushu 804-8550 Japan
国际会议
湘潭
英文
641-648
2011-07-19（万方平台首次上网日期，不代表论文的发表时间）