随着深度传感器的发展,深度图的获取变得非常廉价和方便,在近几年的计算机视觉领域得到了广泛的应用,结合深度图的场景理解也越发受到关注。然而,现有的RGB-D场景理解算法大多是基于模型训练的参数化方法,本文针对RGB-D场景下的场景理解问题,提出一种高效的基于标签传递机制的非参数化场景理解算法。本文首先提出了一种基于马尔科夫随机场框架的标签传递算法,算法主要分为标签源构建,超像素双向匹配和标签传递三个步骤。构建了基于协同表示分类(Collaborative Representation based Classification, CRC)的马尔科夫随机场(Markov Random Field, MRF),利用Graph Cuts进行快速求解,从而获得场景图像每个像素的语义标签。该算法在NYU-Depth-V1数据集上进行了实验,实验结果表明,与现有算法相比,该算法在像素准确率和类别准确率上都有更好的表现。本文随后提出了一种基于语义图模型的集体场景理解算法,通过将测试图像聚类得到相似图像簇,然后对相似图像簇分别构建k-最近邻语义图、L1范数语义图和CRC语义图,将语义相关性在语义图中传递,对标注结果进行平滑。实验...
【英文摘要】
With the development of depth or range sensors, the depth map has been publicly available and widely used in the field of computer vision in recent years, and RGB-D scene parsing also has received the widespread attention. However, the existing RGB-D scene parsing algorithms are mostly parametric models based on training method. In this paper, an effective nonparametric method based upon the label trans-ferring scheme is proposed for RGB-D scene parsing.This thesis first proposes a label transfer algorithm ...
| 
点击下列相关研究机构和相关文献作者，可以直接查到这些机构和作者被《中国知识资源总库》收录的其它文献，使您全面了解该机构和该作者的研究动态和历史。
