Interactive Multi-label Segmentation of RGB-D Images

Interactive Multi-label Segmentation of RGB-D Images
复制标题

DOI:
10.1007/978-3-319-18461-6_24
复制
发表时间:
2015-05
期刊:
--
影响因子:
--
通讯作者:
Julia Diebold;Nikolaus Demmel;C. Hazirbas;Michael Möller;D. Cremers
Julia Diebold;Nikolaus Demmel;C. Hazirbas;Michael Möller;D. Cremers
中科院分区:
其他
文献类型:
--
作者:
Julia Diebold;Nikolaus Demmel;C. Hazirbas;Michael Möller;D. Cremers

文献摘要

被引文献

相似文献

我们提出了一种新的交互式多标签RGB-D图像分割方法,通过扩展[14]中的空间变化的颜色分布来另外以两种不同的方式利用深度信息。一方面,我们把深度图像看作是一个附加的数据通道。另一方面,我们将平面上的空间变化的颜色分布的思想扩展到3D中的体积变化的颜色分布。此外,我们通过局部自适应每个像素周围附近涂鸦的影响来提高数据保真度。我们的方法是在并行硬件上实现的,并在一个新的交互式RGB-D图像分割基准上进行了评估,该基准具有像素精度的地面真实。我们表明,深度信息会导致更精确的分割结果。同时,与不使用深度线索相比,需要更少的用户涂鸦来获得相同的分割精度。
We propose a novel interactive multi-label RGB-D image segmentation method by extending spatially varying color distributions [14] to additionally utilize depth information in two different ways. On the one hand, we consider the depth image as an additional data channel. On the other hand, we extend the idea of spatially varying color distributions in a plane to volumetrically varying color distributions in 3D. Furthermore, we improve the data fidelity term by locally adapting the influence of nearby scribbles around each pixel. Our approach is implemented for parallel hardware and evaluated on a novel interactive RGB-D image segmentation benchmark with pixel-accurate ground truth. We show that depth information leads to considerably more precise segmentation results. At the same time significantly less user scribbles are required for obtaining the same segmentation accuracy as without using depth clues.