摘要
3D目标的标识别已逐渐成为计算机视觉领域的热点问题。在研究了传统的基于几何不变量和基于3D/2D约束关系两种识别方法的基础上,提出了1类新的空间几何结构模型,并计算出了这类模型3D仿射不变量和其对应的2D仿射不变量之间的约束关系。利用这种关系,可以在目标的姿态和摄像机的参数均未知的情况下,有效利用单幅图像来识别3D目标。
3D object recognition has became the problem which attract much more attention. In this paper,after studied the traditional based on the geometric invariant and based on the 3D/2D constraints to recognition the 3D object, A new space geometric model was proposed , and the relations between the 3Daffine invariants and 2Daffine invariants was presented. Employing the relation the object can be recognized from single view without the attitude of object and the parameter of the camera.
出处
《火力与指挥控制》
CSCD
北大核心
2007年第7期126-128,131,共4页
Fire Control & Command Control
