The Sample Tree: A Sequential Hypothesis Testing Approach to 3D Object Recognition

A method is presented for e cient and reliable object recognition within noisy, cluttered, and occluded range images. The method is based on a strategy which hypothesizes the intersection of the object with some selected image point, and searches for additional surface data at locations relative to that point. At each increment, the image is queried for the existence of surface data at a speci c spatial location, and the set of possible object poses is further restricted. Eventually, either the object is identi ed and localized, or the initial hypothesis is refuted. The strategy is implemented in the discrete domain as a binary decision tree classi er. The tree leaf nodes represent individual voxel templates of the model. The internal tree nodes represent the union of the templates of their descendant leaf nodes. The union of all leaf node templates is the complete template set of the model over its discrete pose space. Each internal node also references a single voxel which is the mo...

• Type: Conference
• Year: 1998
• Where: CVPR
• Authors: Michael A. Greenspan
• Keywords: Child Node Templates, Computer Vision, CVPR 1998, Descendant Leaf Nodes, Individual Voxel Templates, Internal Tree Nodes, Tree Leaf Nodes