Experiments in Interpretation-Guided Segmentation
Experiments in Interpretation-Guided Segmentation
复制标题
DOI：
10.1016/0004-3702(77)90031-5
复制
发表时间：
1977-06
期刊：
影响因子：
--
通讯作者：
J. Tenenbaum;H. Barrow
中科院分区：
文献类型：
--
作者：
J. Tenenbaum;H. Barrow
本文提出了一种将场景分析的分割和解释相结合的新方法。来自各种来源的知识被用来对区域的解释进行推断，并根据它们可能的解释合并区域。利用华尔兹滤波算法的推广实现了区域解释的推导。通过消除与相邻区域的任何可能解释不一致的可能区域解释来进行演绎。不同的知识来源被统一地表示为对区域可能解释的约束。因此，多个知识来源可以以一种直接的方式组合在一起，这样知识的增量添加（或等同的，人类指导）将影响性能的增量改进。实验结果报告了三个场景域，景观，机械设备和房间，分别使用人类合作者，几何模型和一组关系约束作为知识来源。这些实验表明，当与解释相结合时，分割得到了很大的改善。此外，与非引导分割相比，集成方法只产生很小的计算开销。该方法可应用于制图、影像解译、车辆导航、医学和电影分析等领域。
This paper presents a new approach for integrating the segmentation and interpretation phases of scene analysis. Knowledge from a variety of sources is used to make inferences about the interpretations of regions, and regions are merged in accordance with their possible interpretations.The deduction of region interpretations is performed using a generalization of Waltz's filtering algorithm. Deduction proceeds by eliminating possible region interpretations that are not consistent with any possible interpretation of an adjacent region. Different sources of knowledge are expressed uniformly as constraints on the possible interpretations of regions. Multiple sources of knowledge can thus be combined in a straightforward way such that incremental additions of knowledge (or equivalently, human guidance) will effect incremental improvements in performance.Experimental results are reported in three scene domains, landscapes, mechanical equipment, and rooms, using, respectively, a human collaborator, a geometric model and a set of relational constraints as sources of knowledge. These experiments demonstrate that segmentation is much improved when integrated with interpretation. Moreover, the integrated approach incurs only a small computational overhead over unguided segmentation.Applications of the approach in cartography, photointerpretation, vehicle guidance, medicine, and motion picture analysis are suggested.