Three-dimensional object recognition
ACM Computing Surveys (CSUR) - Annals of discrete mathematics, 24
IEEE Transactions on Pattern Analysis and Machine Intelligence
Curvature-based representation of objects from range data
Image and Vision Computing
Determining Attitude of Object From Needle Map Using Extended Gaussian Image
Determining Attitude of Object From Needle Map Using Extended Gaussian Image
Hi-index | 0.00 |
Object manipulation by a robot requires some degree of sensing, and of all possible forms of sensory perception, visual sensing is one of the most attractive because of its non-contact nature, high speed and accuracy. Visual data can be obtained in two or three-dimensional (depth map) form from commercially available sensors. Interpreting visual data has been one of the major themes of computer vision researchers in the past decade.In this paper, we present efficient techniques for object representation and recognition from dense range (depth) maps. The objects and models are represented by regions that are a collection of surface patches homogeneous in curvature-based surface properties. The recognition scheme is based on matching object surface descriptions with model surface descriptions. The recognition task includes both locating the overall object and identifying each of its features. Location is achieved by finding a geometrical “registration” function that correctly superimposes an arbitrary instance of the known model and the model. A localization technique is presented which requires that correspondence be established exactly, between one point on the object surface and one on the model surface. Once the single point correspondence is specified, closed form solutions are given for determining the attitude of the unknown view of the object in 3 space with respect to the model.