南京邮电大学学报（自然科学版）2017，Vol.37Issue(5)：13-18,6.DOI:10.14132/j.cnki.1673-5439.2017.05.003
稀疏字典驱动高阶依赖的RGB-D室内场景语义分割
Semantic segmentation of RGB-D indoor scenes using sparse dictionary-driven high-order dependencies
摘要
Abstract
A sparse dictionary-driven high-order dependent RGB-D (color-depth) image semantic segmentation method is proposed to annotate the given indoor scene using high-order conditional random field.Firstly,the global probability of boundary-ultrametric contour map is exploited using depth-fused multi-scale combinatorial grouping for hierarchical over-segmentation of the given RGB-D scene.Secondly,the regional visual feature of each super pixel is extracted to build super pixel label pool to train support vector machine classifier.Then,the unary potential energy of each super pixel and the pairwise potential energy between the adjacent super pixels are calculated,while accumulating the statistical histograms of the sparse code of keypoint features in each super pixel for each class as high-order potential energy.Finally,the semantic segmentation is implemented by exploiting the conditional random field model inference with the top-down discriminative category cost.Compared with other state-of-the-art methods,the presented method can obtain semantic label map with stronger visual expression and higher accuracy.关键词
语义分割/条件随机场模型/稀疏字典学习/结构化支持向量机Key words
semantic segmentation/conditional random field models/sparse dictionary learning/structural support vector machine分类
信息技术与安全科学引用本文复制引用
刘天亮,徐高帮,戴修斌,曹旦旦,罗杰波..稀疏字典驱动高阶依赖的RGB-D室内场景语义分割[J].南京邮电大学学报（自然科学版）,2017,37(5):13-18,6.基金项目
国家自然科学基金(61001152,31200747,61071091,61071166,61172118)、江苏省自然科学基金(BK2012437)、国家留学基金和南京邮电大学校级科研基金(NY214037)资助项目 （61001152,31200747,61071091,61071166,61172118）
