基于形态及受约束结构的三维物体建模方法

3D Object Modeling Based on Aspect and Constrained Structure

文中提出一种基于物体形态及受约束结构的三维物体建模方法,该方法利用具有透视不变性的三维结构来表达物体的各个形态。利用该表达方法可以使机器视觉系统在用单幅灰度图像识别物体时,在模型索引阶段避开求解物体位姿、摄像机参数、特征对应等复杂问题,从而实现先索引后匹配的识别策略,提高识别物体的实时性。文中首先论述了透视不变性和具有透视不变性的受约束结构的基本概念;其次,给出了用受约束结构进行三维物体建模的一般方法和应用实例;最后,指出了这种方法的不足和进一步的研究方向。

In this paper a modeling method based on aspect of 3D object and constrained structure is presented. The method makes use of constrained 3D structures with the property of perspective invariance to represent aspects of 3D object. By using this representation, the machine vision system could avoid the computing of object pose, camera calibration and feature correspondence in the indexing phase of recognizing 3D object from a single view, therefore, the strategy of indexing before matching can be realized and high realtime recognition efficiency can be obtained. At first, the basic concepts of perspective invariance and constrained structure are discussed. Then, a general way using such constrained structures to represent 3D object is given, and an application of it is also presented. Finally, the weakness of this modeling method as well as the future research is pointed out.