Three-dimentional reconstruction of semantic scene based on RGB-D map

被引：0

作者：

Lin J.-H. ^{[1
]}

Wang Y.-J. ^{[2
]}

机构：

[1] School of Application Technology, Changchun University of Technology, Changchun

[2] Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun

来源：

Guangxue Jingmi Gongcheng/Optics and Precision Engineering | 2018年 / 26卷 / 05期

关键词：

Convolution neural network; Machine vision; RGB-D map; Scene restoration; Semantic classification;

D O I：

10.3788/OPE.20182605.1231

中图分类号：

学科分类号：

摘要：

Reconstruction of 3D object is an important part in machine vision system, and the semantic understanding of 3D object is a core function for the machine vision system. In this paper, 3D restoration was combined with the semantic understanding of 3D object, a 3D semantic scene recovery network was proposed. The semantic classification and scene restoration of 3D scene were achieved only by using a single RGB-D map as input. Firstly, an end-to-end 3D convolution neural network was established. The input of the network was a depth map. The 3D context module was used for learning the region within the camera view, then the 3D voxels with semantic labels were generated. Secondly, a synthetic data set with dense volume labels was established to train the depth learning network. Finally, the experimental results showed that the recovery performance w improved by 2.0% compared with the state-of-art. It can be seen that the 3D learning network plays well in 3D scene restoration, it owns high accuracy in semantic annotation of object in the scene. © 2018, Science Press. All right reserved.

引用

页码：1231 / 1241

页数：10

共 26 条

[1]

Gupta S., Arbelaez P., Malik J., Perceptual organization and recognition of indoor scenes from RGB-D images, Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 564-571, (2013)

[2]

Ren X.F., Bo L.F., Fox D., RGB-(D) scene labeling: features and algorithms, Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2759-2766, (2012)

[3]

Silberman N., Hoiem D., Kohli P., Et al., Indoor segmentation and support inference from RGBD images, Proceedings of the 12th European Conference on Computer Vision, pp. 746-760, (2012)

[4]

Lai K., Bo L.F., Fox D., Unsupervised feature learning for 3D scene labeling, Proceedings of 2014 IEEE International Conference on Robotics and Automation, pp. 3050-3057, (2014)

[5]

Rock J., Gupta T., Thorsen J., Et al., Completing 3D object shape from one depth image, Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2484-2493, (2015)

[6]

Monszpart A., Mellado N., Brostow G.J., Et al., RAPter: rebuilding man-made scenes with regular arrangements of planes, ACM Transactions on Graphics, 34, 4, (2015)

[7]

Firman M., Aodha O.M., Julier S., Et al., Structured prediction of unobserved voxels from a single depth image, Proceedings of 2016 IEEE Computer Vision and Pattern Recognition, pp. 5431-5440, (2016)

[8]

Gupta S., Arbelaez P., Girshick R., Et al., Aligning 3D models to RGB-D images of cluttered scenes, Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 4731-4740, (2015)

[9]

Song S.R., Xiao J.X., Sliding shapes for 3D object detection in depth images, Proceedings of the 13th European Conference on Computer Vision, pp. 634-651, (2014)

[10]

Geiger A., Wang C.H., Joint 3D object and layout inference from A single RGB-D image, Pattern Recognition, pp. 183-195, (2015)

← 1 2 3 →