Infrared and Laser Engineering, Volume. 51, Issue 8, 20210702(2022)
Object point cloud classification and segmentation based on semantic information compensating global features
[1] Osada R, Funkhouser T, Chazelle B, et al. Shape distributions[J]. ACM Transactions on Graphics (TOG), 21, 807-832(2002).
[2] [2] Sun J, Ovsjanikov M, Guibas L. A concise provably infmative multiscale signature based on heat diffusion[C]Computer graphics fum. Oxfd, UK: Blackwell Publishing Ltd, 2009, 28(5): 13831392.
[3] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep conv neural networks[J]. Communications of the ACM, 60, 84-90(2017).
[4] Pan X Z, Zhang S Q, Guo W P. Application of multi-mode deep convolutional neural network to video expression recognition[J]. Optics and Precision Engineering, 27, 230-237(2019).
[5] [5] Qi C R, Su H, Mo K, et al. Point: Deep learning on point sets f 3D classification segmentation[C]Proceedings of the IEEE Conference on Computer Vision Pattern Recognition (CVPR), 2017: 7785.
[6] [6] Qi C R, Li Y, Hao S, et al. Point++: Deep hierarchical feature learning on point sets in a metric space[C]Advances in Neural Infmation Processing Systems, 2017, 30: 50995108.
[7] [7] Li Y, Bu R, Sun M, et al. Pointcnn: Convolution on Xtransfmed points[C]Advances in Neural Infmation Process ing Systems, 2018, 31: 820830.
[8] Wang Y, Sun Y, Liu Z, et al. Dynamic graph CNN for learning on point clouds[J]. ACM Transactions on Graphics (TOG), 38, 1-12(2019).
[9] [9] Jaderberg M, Simonyan K, Zisserman A. Spatial transfmer wks[C]Advances in Neural Infmation Processing Systems, 2015, 28: 20172025.
[10] [10] Hastie T, Tibshirani R. Discriminant adaptive nearest neighb classification regression[C]Advances in Neural Infmation Processing Systems, 1996, 9: 409415.
[11] [11] Jégou H, Douze M, Sch C, et al. Aggregating local des into a compact image representation[C]2010 IEEE Computer Society Conference on Computer Vision Pattern Recognition. IEEE, 2010: 33043311.
[12] Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions[J]. arXiv preprint arXiv, 1511.07122(2015).
[13] [13] Wu Z, Song S, Khosla A, et al. 3 D Shapes: A deep representation f volumetric shapes[C]Proceedings of the IEEE Conference on Computer Vision Pattern Recognition (CVPR), 2015: 19121920.
[14] Yi L, Guibas L, Hertzmann A, et al. Learning hierarchical shape segmentation and labeling from online repositories[J]. ACM Transactions on Graphics, 36, 1-12(2017).
[15] Zhang D, He F, Tu Z, et al. Pointwise geometric and semantic learning network on 3 D point clouds[J]. Integrated Computer-Aided Engineering, 27, 57-75(2020).
[16] [16] Duan Y, Zheng Y, Lu J, et al. Structural relational reasoning of point clouds[C]Proceedings of the IEEECVF Conference on Computer Vision Pattern Recognition, 2019: 949958.
[17] [17] Li D, Shen X, Yu Y, et al. GGM: Graph geometric moments convolution neural wk f point cloud shape classification[C]IEEE Access, 2020, 8: 124989124998.
[18] [18] Zhai Z, Zhang X, Yao L. Multiscale dynamic graph convolution wk f point clouds classification[C]IEEE Access, 2020, 8: 6559165598.
[19] Lyu Y, Huang X, Zhang Z. EllipsoidNet: Ellipsoid representation for point cloud classification and segmentation[J]. arXiv preprint arXiv, 2103.02517(2021).
Get Citation
Copy Citation Text
Sen Lin, Zhenyu Zhao, Xiaokui Ren, Zhiyong Tao. Object point cloud classification and segmentation based on semantic information compensating global features[J]. Infrared and Laser Engineering, 2022, 51(8): 20210702
Category: Image processing
Received: Jan. 20, 2022
Accepted: --
Published Online: Jan. 9, 2023
The Author Email: Zhenyu Zhao (610685324@qq.com)