격자 부호화를 사용한 3차원 물체 인식 = 3-Dimensional Object Recognition Using the Grid Coding

다국어 초록 (Multilingual Abstract)

In general, model-based object recognition methods used adhoc techniques to decide whether or not an object model a given scene.
However, to get the reasonable features between the model and data, the number of views needed may be large and the selection of view points may be critical In order to solve these problems, we propose a grid coding technique to extract the surfaces with a different orientation. Here, the objects are recognized using matched features such as the interior angle the elements for deciding the shape of surfaces.
The observed objects are assumed to rest on a plane(base plane) in a scene which is "encoded" with light cast through a grid plane. Two orthogonal grid pattern are used, where each pattern is obtained with a set of equally spaced stripe marked on a glass. The scene is observed through a camera and the object surface orientation is determined using the projected pattern on the surface.
Finally, the paper contains the simulation results of this prototype system for verfing simple blocks world.