Depth Supporting Semantic Segmentation via Deep Neural Markov Random Field

摘要：

　　Semantic segmentation is of great importance to various vision applications.Depth information plays an important role in human visual system to help people obtain meaningful segmentation results,but it is not well considered by most existing segmentation methods.In this paper,we address the problem of semantic segmentation by incorporating depth information via deep neural Markov Random Field.In our method,the color image and its corresponding depth map are first fed to a convolutional neural network.Then,a deconvolution approach is performed on the network output to obtain the pixelwise prediction in terms of the probability of labels assigned to pixels.Finally,the dense prediction is used to design unary term and pairwise term,which are determined by pixels coordinate,color and depth.Experiments are conducted on several public datasets to illustrate the effectiveness of the proposed method.On the PASCAL VOC 2011 test dataset,experimental results show that our method can get accurate results when compared with the ground truth.On the PASCAL VOC 2012 dataset and NYUDv2 dataset,the proposed method can obtain competitive results.

关键词： Semantic segmentation Depth CNNs MRF

作者: Wen Su Zengfu Wang

作者单位: Institute of Intelligent Machines,Hefei Institutes of Physical Sciences,Chinese Academy of Sciences,Hefei,Anhui,China;University of Science and Technology of China,Hefei,Anhui,China;National Engineering Laboratory for Speech and Language Information Processing,Hefei,Anhui,China

会议类型: 国际会议

会议名称: 第七届全国模式识别学术会议(The 7th Chinese Conference on Pattern Recognition,CCPR2016)

会议地点: 成都

会议语种:英文

页码: 278-289

在线出版日期: 2016-11-03（万方平台首次上网日期，不代表论文的发表时间）