Geometrical learning from multiple stereo views through monocular based feature grouping

A geometrical learning system is described which constructs automatically the geometric model of indoor environments from multiple stereo views. The produced model includes not only 3-D segments initially provided by a stereo vision system, but also 3-D feature groups. Feature grouping helps to predict the position of a given view with respect to the current model and allows one to correct noisy features by the geometric constraints of feature groups. This 3-D feature grouping is based on a monocular process working on the 2-D segments associated with one source image of a stereo view. Experimental results are presented