基于ARG模型识别局部被遮挡物体

在计算机视觉中，局部被遮挡物体的识别有着重要的意义。本文提出了一种基于ARG（关系属性图）模型识别局部被遮挡物体的新算法。由于关系属性图对图像遮挡、噪音或者二维几何引起的变形都是稳定的，所以用ARG模型能够识别那些由于局部被遮挡或其它原因引起的丢失特征的物体。该算法如下：首先，根据模型和图像特征之间的局部和整体的对应性约束，在图像中选出有限数量的侯选子图。其次，基于在关系向量空间中的误差分析，使用投票方案对丢失的特征进行迭代检测，丢失的特征全部被检测出后即可进行匹配。最后用实例进行了验证，结果表明该算法是有效的。

Recognition of partially occluded objects based on ARG model

The recognition of partially occluded objects is significant in computer vision. In this paper, a new algorithm of recognition of partially occluded objects based on ARG model is proposed. The ARG is robust to shape variations due to noise and occlusions and 2 - D geometric transformation as well, so the objects with lost features caused by partially occluded or other reasons can be recognized by using the ARG model. The algorithm consists of two- phases. First, a finite number of candidate subgraphs are selected in an image, by using the logical constraint embedding local and structure consistency as well as the correspondence measure between model and image features. Second, the feature loss detection is done iteratively by the error detection and voting scheme through the error analysis in the relation vector space. Partial matching is performed after all lost features are detected. Finally, the effectiveness of the algorithm is demonstrated by the experiment.