Efficiently selecting regions for scene understanding
Efficiently selecting regions for scene understanding
复制标题
DOI：
10.1109/cvpr.2010.5540072
复制
发表时间：
2010-06
期刊：
影响因子：
--
通讯作者：
M. P. Kumar;D. Koller
中科院分区：
文献类型：
--
作者：
M. P. Kumar;D. Koller
场景理解和相关任务的最新进展凸显了使用区域来推理高级场景结构的重要性。通常，预先选择区域，然后在它们上定义能量函数。这两个步骤的过程存在以下缺陷：（i）区域可能与场景实体的边界不匹配，从而引入错误； (ii) 由于这些区域是在不了解能量函数的情况下获得的，因此它们可能不适合当前的任务。我们通过设计一种有效的方法来解决这些问题，以获得能量函数本身的最佳区域集。我们算法的每次迭代都通过对偶分解求解精确的线性规划松弛来从大字典中选择区域。区域字典是通过合并和交叉从多个自下而上的过度分割获得的片段来构造的。为了证明我们的算法的有用性，我们考虑了场景分割的任务，并展示了相对于最先进的方法的显着改进。
Recent advances in scene understanding and related tasks have highlighted the importance of using regions to reason about high-level scene structure. Typically, the regions are selected beforehand and then an energy function is defined over them. This two step process suffers from the following deficiencies: (i) the regions may not match the boundaries of the scene entities, thereby introducing errors; and (ii) as the regions are obtained without any knowledge of the energy function, they may not be suitable for the task at hand. We address these problems by designing an efficient approach for obtaining the best set of regions in terms of the energy function itself. Each iteration of our algorithm selects regions from a large dictionary by solving an accurate linear programming relaxation via dual decomposition. The dictionary of regions is constructed by merging and intersecting segments obtained from multiple bottom-up over-segmentations. To demonstrate the usefulness of our algorithm, we consider the task of scene segmentation and show significant improvements over state of the art methods.