Abstract
Multispectral points, as a new data source containing both spectrum and spatial geometry, opens the door to three-dimensional (3D) land cover classification at a finer scale. In this paper, we model the multispectral points as a graph and propose a multi-attribute smooth graph convolutional network (MaSGCN) for multispectral points classification. We construct the spatial graph, spectral graph, and geometric-spectral graph respectively to mine patterns in spectral, spatial, and geometric-spectral domains. Then, the multispectral points graph is generated by combining the spatial, spectral, and geometric-spectral graphs. Moreover, dimensionality features and spectrums are introduced to screen the appropriate connection points for constructing the spatial graph. For remote sensing scene classification tasks, it is usually desirable to make the classification map relatively smooth and avoid salt and pepper noise. A heat operator is then introduced to enhance the low-frequency filters and enforce the smoothness in the graph signal. Considering that different land covers have different scale characteristics, we use multiple scales instead of the single scale when leveraging heat operator on graph convolution. The experimental results on two real multispectral points data sets demonstrate the superiority of the proposed MaSGCN to several state-of-the-art methods.
Similar content being viewed by others
References
Joshi N, Baumann M, Ehammer A, et al. A review of the application of optical and radar remote sensing data fusion to land use mapping and monitoring. Remote Sens, 2016, 8: 70
Chen W, Li X, He H, et al. A review of fine-scale land use and land cover classification in open-pit mining areas by remote sensing techniques. Remote Sens, 2018, 10: 15
Fisher J, Acosta E A, Dennedy-Frank P J, et al. Impact of satellite imagery spatial resolution on land use classification accuracy and modeled water quality. Remote Sens Ecol Conservation, 2018, 4: 137–149
Wang Q, Gu Y, Tuia D. Discriminative multiple kernel learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens, 2016, 54: 3912–3927
Gu Y, Wang Q, Xie B. Multiple kernel sparse representation for airborne LiDAR data classification. IEEE Trans Geosci Remote Sens, 2017, 55: 1085–1105
Stal C, Briese C, De Maeyer P, et al. Classification of airborne laser scanning point clouds based on binomial logistic regression analysis. Int J Remote Sens, 2014, 35: 3219–3236
Zhang Z, Zhang L, Tong X, et al. A multilevel point-cluster-based discriminative feature for ALS point cloud classification. IEEE Trans Geosci Remote Sens, 2016, 54: 3309–3321
Hong D, Gao L, Yokoya N, et al. More diverse means better: Multimodal deep learning meets remote-sensing imagery classification. IEEE Trans Geosci Remote Sens, 2021, 59: 4340–4354
Zhang L, Zhang L, Du B. Deep learning for remote sensing data: A technical tutorial on the state of the art. IEEE Geosci Remote Sens Mag, 2016, 4: 22–40
Hong D, Yokoya N, Xia G S, et al. X-ModalNet: A semi-supervised deep cross-modal network for classification of remote sensing data. ISPRS J Photogrammetry Remote Sens, 2020, 167: 12–23
Rasti B, Hong D, Hang R, et al. Feature extraction for hyperspectral imagery: The evolution from shallow to deep: Overview and toolbox. IEEE Geosci Remote Sens Mag, 2020, 8: 60–88
Zhang L, Zhang L, Du B, et al. Hyperspectral image unsupervised classification by robust manifold matrix factorization. Inf Sci, 2019, 485: 154–169
Fernandez-Diaz J, Carter W, Glennie C, et al. Capability assessment and performance metrics for the titan multispectral mapping lidar. Remote Sens, 2016, 8: 936
Bakuła K, Kupidura P, Jełowicki Ł. Testing of land cover classification from multispectral airborne laser scanning data. Int Arch Photogramm Remote Sens Spatial Inf Sci, 2016, XLI-B7: 161–169
Wang C K, Tseng Y H, Chu H J. Airborne dual-wavelength LiDAR data for classifying land cover. Remote Sens, 2014, 6: 700–715
Teo T A, Wu H M. Analysis of land cover classification using multi-wavelength LiDAR system. Appl Sci, 2017, 7: 663
Matikainen L, Karila K, Hyyppä J, et al. Object-based analysis of multispectral airborne laser scanner data for land cover classification and map updating. ISPRS J Photogrammetry Remote Sens, 2017, 128: 298–313
Leigh H W, Magruder L A. Using dual-wavelength, full-waveform airborne lidar for surface classification and vegetation characterization. J Appl Remote Sens, 2016, 10: 045001
Zou X, Zhao G, Li J, et al. 3D land cover classification based on multispectral lidar point clouds. Int Arch Photogramm Remote Sens Spatial Inf Sci, 2016, XLI-B1: 741–747
Yu Y, Guan H, Li D, et al. A hybrid capsule network for land cover classification using multispectral LiDAR data. IEEE Geosci Remote Sens Lett, 2020, 17: 1263–1267
Wichmann V, Bremer M, Lindenberger J, et al. Evaluating the potential of multispectral airborne lidar for topographic mapping and land cover classification. ISPRS Ann Photogramm Remote Sens Spatial Inf Sci, 2015, II-3/W5: 113–119
Teledyne O. Titan world’s first multispectral LiDAR. Available: http://www.teledyneoptech.com/en/products/airborne-survey/titan/
Sun J, Shi S, Biwu C, et al. Combined application of 3D spectral features from multispectral LiDAR for classification. In: IEEE International Geoscience and Remote Sensing Symposium. Fort Worth, 2017. 5264–5267
Ekhtari N, Glennie C, Fernandez-Diaz J C. Classification of multispectral lidar point clouds. In: IEEE International Geoscience and Remote Sensing Symposium. Fort Worth, 2017. 2756–2759
Ekhtari N, Glennie C, Fernandez-Diaz J C. Classification of airborne multispectral Lidar point clouds for land cover mapping. IEEE J Sel Top Appl Earth Observations Remote Sens, 2018, 11: 2068–2078
Miller C I, Thomas J J, Kim A M, et al. Application of image classification techniques to multispectral lidar point cloud data. In: Proceedings of Laser Radar Technol Appl XXI. Baltimore, 98320X. 2016
Morsy S, Shaker A, El-Rabbany A. Multispectral LiDAR data for land cover classification of urban areas. Sensors, 2017, 17: 958
He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computervision and Pattern Recognition. Las Vegas, 2016. 770–778
Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell, 2017, 39: 1137–1149
Feng Q, Zhu D, Yang J, et al. Multisource hyperspectral and LiDAR data fusion for urban land-use mapping based on a modified two-branch convolutional neural network. Int J Geo-Inf, 2019, 8: 28
Micheli A. Neural network for graphs: A contextual constructive approach. IEEE Trans Neural Netw, 2009, 20: 498–511
Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering. In: 30th Conference on Neural Information Processing Systems. Barcelona, 2016. 3844–3852
Monti F, Boscaini D, Masci J, et al. Geometric deep learning on graphs and manifolds using mixture model CNNs. In: IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, 2017. 5425–5434
Yan S, Xiong Y, Lin D. Spatial temporal graph convolutional networks for skeleton-based action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018. 1–28
Bruna J, Zaremba W, Szlam A, et al. Spectral networks and locally connected networks on graphs. In: 2nd International Conference on Learning Representations. Banff, 2014
Atwood J, Towsley D. Diffusion-convolutional neural networks. In: 30th Conference on Neural Information Processing Systems. Barcelona, 2016. 1993–2001
Niepert M, Ahmed M, Kutzkov K. Learning convolutional neural networks for graphs. In: Proceedings of the 33rd International Conference on Machine Learning. New York, 2016. 2014–2023
Henaff M, Bruna J, Lecun Y. Deep convolutional networks on graph-structured data. Computer Science, 2015
Li Y, Zemel R, Brockschmidt M, et al. Gated graph sequence neural networks. In: 4th International Conference on Learning Representations. San Juan, 2016
Kipf T, Welling M. Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations. Toulon, 2017
Chung F. Spectral Graph Theory. Rhode Island: American Mathematical Society, 1997
Hammond D K, Vandergheynst P, Gribonval R. Wavelets on graphs via spectral graph theory. Appl Comput Harmonic Anal, 2011, 30: 129–150
Xu K, Li C, Tian Y, et al. Representation learning on graphs with jumping knowledge networks. In: ICML. Stockholm, 2018. 5449–5458
Wan S, Gong C, Zhong P, et al. Multiscale dynamic graph convolutional network for hyperspectral image classification. IEEE Trans Geosci Remote Sens, 2020, 58: 3162–3177
Hong D, Gao L, Yao J, et al. Graph convolutional networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens, 2021, 59: 5966–5978
Mou L, Lu X, Li X, et al. Nonlocal graph convolutional networks for hyperspectral image classification. IEEE Trans Geosci Remote Sens, 2020, 58: 8246–8257
Zhang Y, Rabbat M. A graph-CNN for 3D point cloud classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing. Calgary, Alberta, 2018
Te G, Hu W, Guo Z, et al. RGCNN: Regularized graph CNN for point cloud segmentation. arXiv preprint: 1806.02952, 2018
Shuman D I, Narang S K, Frossard P, et al. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Process Mag, 2013, 30: 83–98
Wang Q, Gu Y. A discriminative tensor representation model for feature extraction and classification of multispectral LiDAR data. IEEE Trans Geosci Remote Sens, 2020, 58: 1568–1586
Lin Y, Wang C, Zhai D, et al. Toward better boundary preserved supervoxel segmentation for 3D point clouds. ISPRS J Photogrammetry Remote Sens, 2018, 143: 39–47
Demantke J, Mallet C, David N, et al. Dimensionality based scale selection in 3D LiDAR point clouds. Int Arch Photogramm Remote Sens Spat Inf Sci, 2011, 38: 97–102
Coifman R R, Lafon S. Diffusion maps. Appl Comput Harmonic Anal, 2006, 21: 5–30
Qin A, Shang Z, Tian J, et al. Spectral-spatial graph convolutional networks for semisupervised hyperspectral image classification. IEEE Geosci Remote Sens Lett, 2019, 16: 241–245
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the Key Research and Development Project of Ministry of Science and Technology (Grant No. 2017YFC1405100), and in part by the National Natural Science Foundation of Key International Cooperation (Grant No. 61720106002).
Rights and permissions
About this article
Cite this article
Wang, Q., Gu, Y., Yang, M. et al. Multi-attribute smooth graph convolutional network for multispectral points classification. Sci. China Technol. Sci. 64, 2509–2522 (2021). https://doi.org/10.1007/s11431-020-1871-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11431-020-1871-8