Land cover mapping at very high resolution with rotation equivariant CNNs: Towards small yet accurate models

ISPRS Journal of Photogrammetry and Remote Sensing

Volumn 145, Issue , 2018, Pages 96-107

  Marcos, Diego ^a,b   Volpi, Michele ^a   Kellenberger, Benjamin ^b   Tuia, Devis ^a,b  

^a UNIVERSITY OF ZURICH   (Switzerland)

^b WAGENINGEN UNIVERSITY   (Netherlands)

Author keywords

Deep learning; Rotation invariance; Semantic labeling; Sub decimeter resolution

Indexed keywords

CONVOLUTION; DEEP LEARNING; ENCODING (SYMBOLS); IMAGE SEGMENTATION; NETWORK ARCHITECTURE; NEURAL NETWORKS; REMOTE SENSING; SEMANTICS;

ABSOLUTE ORIENTATION; CONVOLUTIONAL NEURAL NETWORK; ORIENTATION ENCODING; REMOTE SENSING IMAGES; ROTATION INVARIANCE; SEMANTIC LABELING; STATE-OF-THE-ART PERFORMANCE; VERY HIGH RESOLUTION;

ROTATION;

ACCURACY ASSESSMENT; ARTIFICIAL NEURAL NETWORK; LAND COVER; MAPPING METHOD; NUMERICAL MODEL; ORIENTATION; REMOTE SENSING; RESOLUTION; SATELLITE IMAGERY; VECTOR;

EID: 85042151311     PISSN: 09242716     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.isprsjprs.2018.01.021     Document Type: Article

References (37)

1. Audebert, N., Le Saux, B., Lefèvre, S., 2016. Semantic segmentation of earth observation data using multimodal and multi-scale deep networks. In: Proc. Asian Conference on Computer Vision.
2. Audebert, N., Le Saux, B., Lefèvrey, S., Fusion of heterogeneous data in convolutional networks for urban semantic labeling. Urban Remote Sensing Event (JURSE), 2017 Joint, 2017, IEEE, 1–4.
3. Campos-Taberner, M., Romero-Soriano, A., Gatta, C., Camps-Valls, G., Lagrange, A., Saux, B.L., Beaupère, A., Boulch, A., Chan-Hon-Tong, A., Herbin, S., Randrianarivo, H., Ferecatu, M., Shimoni, M., Moser, G., Tuia, D., Processing of extremely high resolution LiDAR and RGB data: outcome of the 2015 IEEE GRSS data fusion contest. Part A: 2D contest. IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens. 9 (2016), 5547–5559.
4. Castelluccio, M.P.G., Sansone, C., Verdoliva, L., 2015. Land Use Classification in Remote Sensing Images by Convolutional Neural Networks, 1–11. Available from: .
5. Cheng, G., Zhou, P., Han, J., Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE Trans. Geosci. Rem. Sens. 54 (2016), 7405–7415.
6. Cohen, T.S., Welling, M., 2016. Group Equivariant Convolutional Networks. Available from: < arXiv:1602.07576>.
7. Dalla Mura, M., Atli Benediktsson, J., Waske, B., Bruzzone, L., Morphological attribute profiles for the analysis of very high resolution images. IEEE Trans. Geosci. Rem. Sens. 48 (2010), 3747–3762.
8. Fauvel, M., Tarabalka, Y., Benediktsson, J., Chanussot, J., Tilton, J., Advances in spectral-spatial classification of hyperspectral images. Proc. IEEE 101 (2013), 652–675, 10.1109/JPROC.2012.2197589.
9. Gerke, M., 2015. Use of the Stair Vision Library within the ISPRS 2D Semantic Labeling Benchmark (Vaihingen). Technical Report. ITC, Univ. of Twente.
10. Glocer, K., Eads, D., Theiler, J., 2005. Online feature selection for pixel classification. In: Int. Conf. Machine Learning, Bonn, Germany.
11. Goodfellow, I., Bengio, Y., Courville, A., 2016. Deep Learning. URL: < http://goodfeli.github.io/dlbook/> (Book in preparation for MIT Press).
12. Gueguen, L., Hamid, R., 2015. Large-scale damage detection using satellite imagery. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1321–1328.
13. Hariharan, B., Arbelaez, P., Girshick, R., Malik, J., 2015. Hypercolumns for object segmentation and fine-grained localization. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
14. Harvey, N.R., Theiler, J., Brumby, S.P., Perkins, S., Szymanski, J.J., Bloch, J.J., Porter, R.B., Galassi, M., Young, A.C., Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction. IEEE Trans. Geosci. Rem. Sens. 40 (2002), 393–404.
15. Jaderberg, M., Simonyan, K., Zisserman, A., et al., 2015. Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017–2025.
16. Lagrange, A., Le Saux, B., Beaupere, A., Boulch, A., Chan-Hon-Tong, A., Herbin, S., Randrianarivo, H., Ferecatu, M., 2015. Benchmarking classification of earth-observation data: From learning explicit features to convolutional networks. In: Proc. IGARSS, Milan, Italy, pp. 4173–4176.
17. Laptev, D., Savinov, N., Buhmann, J.M., Pollefeys, M., 2016. TI-pooling: transformation-invariant pooling for feature learning in convolutional neural networks. Available from: < arXiv:1604.06318>.
18. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., Gradient-based learning applied to document recognition. Proc. IEEE. 86:11 (1998), 2278–2324, 10.1109/5.726791.
19. Leen, T.K., From data distributions to regularization in invariant learning. Neural Comp. 7 (1995), 974–981.
20. Lei, Z., Fang, T., Huo, H., Li, D., Rotation-invariant object detection of remotely sensed images based on texton forest and hough voting. IEEE Trans. Geosci. Rem. Sens. 50 (2012), 1206–1217.
21. Lenc, K., Vedaldi, A., 2015. Understanding image representations by measuring their equivariance and equivalence. In: Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 991–999.
22. Liu, Y., Piramanayagam, S., Monteiro, S.T., Saber, E., Dense semantic labeling of very-high-resolution aerial imagery and lidar with fully-convolutional neural networks and higher-order CRFs. IEEE/CVF CVPRW Earthvision, 2017, IEEE, 1561–1570.
23. Long, J., Shelhamer, E., Darrell, T., 2015. Fully convolutional networks for semantic segmentation. In: IEEE/CVF International Conference on Computer Vision and Pattern Recognition.
24. Maggiori, E., Tarabalka, Y., Charpiat, G., Alliez, P., 2016. High-resolution aerial image labeling with convolutional neural networks. Available from: < arXiv:1611.01962>.
25. Maggiori, E., Tarabalka, Y., Charpiat, G., Alliez, P., Convolutional neural networks for large-scale remote-sensing image classification. IEEE Trans. Geosci. Rem. Sens. 55 (2017), 645–657.
26. Malek, S., Bazi, Y., Alajlan, N., AlHichri, H., Melgani, F., Efficient framework for palm tree detection in UAV images. IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens. 7 (2014), 4692–4703.
27. Marcos, D., Volpi, M., Komodakis, N., Tuia, D., 2016. Rotation equivariant vector field networks. Available from: < arXiv:1612.09346>.
28. Marmanis, D., Wegner, J.D., Galliani, S., Schindler, K., Datcu, M., Stilla, U., Semantic segmentation of aerial images with an ensemble of CNSS. ISPRS Ann. Photogram. Rem. Sens. Spatial Inform. Sci. 3 (2016), 473–480.
29. Moser, G., Serpico, S.B., Benediktsson, J.A., Land-cover mapping by Markov modeling of spatial-contextual information. Proc. IEEE 101 (2013), 631–651.
30. Penatti, O., Nogueira, K., dos Santos, J.A., 2015. Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? In: IEEE/CVF Computer Vision and Pattern Recognition Workshops, Earthvision.
31. Regniers, O., Bombrun, L., Lafon, V., Germain, C., Supervised classification of very high resolution optical images using wavelet-based textural features. IEEE Trans. Geosci. Rem. Sens. 54 (2016), 3722–3735.
32. Sherrah, J., 2016. Fully convolutional networks for dense semantic labelling of high-resolution aerial imagery. Available from: < arXiv:1606.02585>.
33. Tuia, D., Courty, N., Flamary, R., Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions. ISPRS J. Int. Soc. Photo. Rem. Sens. 105 (2015), 272–285.
34. Volpi, M., Ferrari, V., 2015. Semantic segmentation of urban scenes by learning local class interactions. In: IEEE/CVF CVPRW Earthvision.
35. Volpi, M., Tuia, D., Dense semantic labeling of subdecimeter resolution images with convolutional neural networks. IEEE Trans. Geosci. Rem. Sens. 55 (2017), 881–893.
36. Worrall, D.E., Garbin, S.J., Turmukhambetov, D., Brostow, G.J., 2016. Harmonic Networks: Deep Translation and Rotation Equivariance. Available from: < arXiv:1612.04642>.
37. Zhou, Y., Ye, Q., Qiu, Q., Jiao, J., 2017. Oriented Response Networks. Available from: < arXiv:1701.01833>.