|
This paper describes an approach to 3-D surface reconstruction that integrates the information provided by two different sources: stereo vision and local shading analysis. In our scheme a sparse depth map, obtained by a binocular stereo technique, provides an estimate of surface shape that can be refined by local shading information (an orientation map), extracted from one of the stereo pair of intensity images. The proposed local shading analysis is simplified. In fact, illumination direction and line of sight are coincident. This seems to provide better results on surface orientation estimates than do more general methods. The integration process consists of two phases: First, the scene is segmented in connected regions by means of a raw needle map. Second, the surface interpolation is obtained using information extracted from the segmentation process and the sparse depth map. The result of the integrated approach is a good quality, dense depth map. The functionality of the approach has been tested on synthetic data and real data.
|
