Kim Seong-Heum, Tai Yu-Wing, Park Jaesik, Kweon In So
IEEE Trans Image Process. 2016 Aug;25(8):3639-3654. doi: 10.1109/TIP.2016.2555698. Epub 2016 Apr 21.
This paper presents an automatic method to extract a multi-view object in a natural environment. We assume that the target object is bounded by the convex volume of interest defined by the overlapping space of camera viewing frustums. There are two key contributions of our approach. First, we present an automatic method to identify a target object across different images for multi-view binary co-segmentation. The extracted target object shares the same geometric representation in space with a distinctive color and texture model from the background. Second, we present an algorithm to detect color ambiguous regions along the object boundary for matting refinement. Our matting region detection algorithm is based on information theory, which measures the Kullback-Leibler (KL) divergence of local color distribution of different pixel-bands. The local pixel-band with the largest entropy is selected for matte refinement, subject to the multi-view consistent constraint. Our results are highquality alpha mattes consistent across all different viewpoints. We demonstrate the effectiveness of the proposed method using various examples.
本文提出了一种在自然环境中提取多视图对象的自动方法。我们假设目标对象由相机视锥重叠空间定义的凸感兴趣体积所界定。我们的方法有两个关键贡献。首先，我们提出了一种自动方法，用于跨不同图像识别目标对象以进行多视图二元协同分割。提取的目标对象在空间中具有相同的几何表示，并具有与背景不同的颜色和纹理模型。其次，我们提出了一种算法，用于检测沿对象边界的颜色模糊区域以进行抠图细化。我们的抠图区域检测算法基于信息论，它测量不同像素带的局部颜色分布的库尔贝克-莱布勒（KL）散度。选择具有最大熵的局部像素带进行抠图细化，并受多视图一致性约束。我们的结果是在所有不同视点上都一致的高质量alpha抠图。我们使用各种示例证明了所提出方法的有效性。
