Eckes Christian, Triesch Jochen, von der Malsburg Christoph
Fraunhofer Institute for Media Communications IMK, D-53754 Sankt Augustin, Germany.
Neural Comput. 2006 Jun;18(6):1441-71. doi: 10.1162/neco.2006.18.6.1441.
We present a system for the automatic interpretation of cluttered scenes containing multiple partly occluded objects in front of unknown, complex backgrounds. The system is based on an extended elastic graph matching algorithm that allows the explicit modeling of partial occlusions. Our approach extends an earlier system in two ways. First, we use elastic graph matching in stereo image pairs to increase matching robustness and disambiguate occlusion relations. Second, we use richer feature descriptions in the object models by integrating shape and texture with color features. We demonstrate that the combination of both extensions substantially increases recognition performance. The system learns about new objects in a simple one-shot learning approach. Despite the lack of statistical information in the object models and the lack of an explicit background model, our system performs surprisingly well for this very difficult task. Our results underscore the advantages of view-based feature constellation representations for difficult object recognition problems.
我们提出了一种用于自动解释杂乱场景的系统，该场景包含位于未知复杂背景前的多个部分遮挡的物体。该系统基于扩展的弹性图匹配算法，该算法允许对部分遮挡进行显式建模。我们的方法在两个方面扩展了早期的系统。首先，我们在立体图像对中使用弹性图匹配，以提高匹配的鲁棒性并消除遮挡关系的歧义。其次，我们通过将形状、纹理与颜色特征相结合，在对象模型中使用更丰富的特征描述。我们证明这两种扩展的结合显著提高了识别性能。该系统通过一种简单的一次性学习方法来学习新物体。尽管对象模型中缺乏统计信息且没有明确的背景模型，但我们的系统在这项非常困难的任务中表现出惊人的良好性能。我们的结果强调了基于视图的特征星座表示对于困难对象识别问题的优势。
