3-D object pose estimation by shading and edge data fusion-simulating virtual manipulation on mental images

Human beings seem to recognize objects based on a kind of model-matching, i.e., a virtual manipulation on mental images. This paper presents a 3-D object pose estimation method simulating the human recognition scheme. Computer synthesizes not only an edge image but also a shading image from an object model. Then, it matches the two kinds of synthesized images with the inputted images individually by using a non-linear least-squares method, and estimates the pose parameter values. Finally, it chooses the better of the individually estimated poses. Thus, the fusion of the shading and the edge information is achieved. Since the two pieces of information complement each other, this method has the advantage of much higher robustness and accuracy of pose estimation than ordinary model-matching techniques which rely only on geometrical features such as vertices or edges