Scene Restoration and Semantic Classification Network Using Depth Map and Discrete Pooling Technology

doi:10.16383/j.aas.2018.c170439

CIOMP OpenIR

	Scene Restoration and Semantic Classification Network Using Depth Map and Discrete Pooling Technology
	J.-H.Lin; Y.Yao; Y.Wang
	2019
发表期刊	Zidonghua Xuebao/Acta Automatica Sinica
ISSN	02544156
卷号	45 期号:11 页码:2178-2186
摘要	In the machine vision perception system, it is very important to robustly reconstruct the 3D scene and recognize target semantics. At present, commonly used methods generally deal with these two functions separately. In this paper, we propose a scene restoration and semantic classification network using the depth map. Based on the RGB-D information in the depth map, reconstruction of a 3D target scene is completed along with classification. Firstly, a deep convolutional neural network model from the CPU end to the GPU end is constructed, which takes depth samples as input from sensor and deeply learns contextual target scene information in the camera projection area. The output of the network comes from the improved truncated signed distance function (TSDF) coding voxel-level semantic annotation. Secondly, in order to enhance the deep learning ability of the convolutional neural network, a three-dimensional target scene dataset with semantic annotation is constructed to enhance the robustness of the proposed network. Experimental results show that compared with the current advanced network model, the reconstruction scale of this network model expands by 2.1%. The proposed convolutional network has good reconstruction effect on the missing scene and the accuracy of semantic classification is also guaranteed. Copyright 2019 Acta Automatica Sinica. All rights reserved.
关键词	Deep neural networks,Classification (of information),Computer vision,Convolution,Deep learning,Image reconstruction,Neural networks,Semantic Web,Semantics
DOI	10.16383/j.aas.2018.c170439
URL	查看原文
收录类别	EI
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/63218
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	J.-H.Lin,Y.Yao,Y.Wang. Scene Restoration and Semantic Classification Network Using Depth Map and Discrete Pooling Technology[J]. Zidonghua Xuebao/Acta Automatica Sinica,2019,45(11):2178-2186.
APA	J.-H.Lin,Y.Yao,&Y.Wang.(2019).Scene Restoration and Semantic Classification Network Using Depth Map and Discrete Pooling Technology.Zidonghua Xuebao/Acta Automatica Sinica,45(11),2178-2186.
MLA	J.-H.Lin,et al."Scene Restoration and Semantic Classification Network Using Depth Map and Discrete Pooling Technology".Zidonghua Xuebao/Acta Automatica Sinica 45.11(2019):2178-2186.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Scene Restoration an（971KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载