DESERTIFICATION GLASSLAND CLASSIFICATION AND THREE-DIMENSIONAL CONVOLUTION NEURAL NETWORK MODEL FOR IDENTIFYING DESERT GRASSLAND LANDFORMS WITH UNMANNED AERIAL VEHICLE HYPERSPECTRAL REMOTE SENSING IMAGES
Abstract
Based on deep learning, a desertification grassland classification (DGC) and three-dimensional convolution neural network (3D-CNN) model is established. The F-norm2 paradigm is used to reduce the data; the data volume was effectively reduced while ensuring the integrity of the spatial information. Through structure and parameter optimization, the accuracy of the model is further improved by 9.8%, with an overall recognition accuracy of the optimized model greater than 96.16%. Accordingly, high-precision classification of desert grassland features is achieved, informing continued grassland remote sensing research.
Keywords
unmanned aerial vehicle,
hyperspectral image,
grassland desertification,
ground object identification,
3D convolutional neural networks
Supporting agencies: This study was financially supported by the National Natural Science Foundation of China (No. 31660137).
About the Authors
W. Pi
Inner Mongolia Agricultural University, Mechanical and Electrical Engineering College
China
Hohhot
China
Hohhot
J. Du
Inner Mongolia Agricultural University, Mechanical and Electrical Engineering College
China
Hohhot
China
Hohhot
H. Liu
Inner Mongolia Agricultural University, Mechanical and Electrical Engineering College
China
Hohhot
China
Hohhot
X. Zhu
Inner Mongolia Agricultural University, Mechanical and Electrical Engineering College
China
Hohhot
China
Hohhot
References
1. Q. G. Zhao, G. Q. Huang, Y. Q. Ma, Acta Ecol. Sin., 36, N 19, 6328–6335 (2016).
2. Q. M. Pan, J. G. Xue, T. Jin, Chin. Sci. Bull., 63, N 17, 1642–1650 (2018).
3. Y. F. Bai, Q. M. Pan, Q. Xing, Chin. Sci. Bull., 61, N 2, 201–212 (2016).
4. Y. Yan, Y. F. Chen, G. C. Zhao, Geol. Exploration., 55, N 2, 630–640 (2019).
5. D. Han, H. Z. Wang, B. Y. Zheng, F. Wang, Acta Ecol. Sin., 38, N 18, 6655–6663 (2018).
6. Z. H. Gao, B. P. Sun, G. D. Ding, J. Desert Res., 84, N 1, 19–24 (2017).
7. X.-Q. Wei, X.-F. Gu, Q.-Y. Meng, T. Yu, K. Jia, Y.-L. Zhan, Ch.-M. Wang, J. Appl. Spectrosc., N 5, 829–836 (2017).
8. D. Tuia, C. Persello, L. Bruzzone, IEEE Geosci. Rem. Sens. Magn., 4, 41–57 (2016).
9. R. R. Wan, P. Wang, X. L. Wang, J. Appl. Rem. Sens., 12, N 4, 046029 (2018).
10. Q. L. Niu, H. K. Feng, G. J. Yang, Trans. Chin. Soc. Agric. Eng., 34, N 5, 73–82 (2018).
11. C. Gevaert, J. Suomalainen, J. Tang, IEEE J. Sel. Top. Appl. Earth Obs., 8, 3140–3146 (2015).
12. G. E. Hinton, N. Srivastava, A. Krizhevsky, Neural Comput., 18, N 3, 1527–1554 (2006).
13. L. M. Dang, S. Hassan, Expert Syst. Appl., 9, N 1, 156–168 (2019).
14. H. Chen, Y. Sun, X. L. Li, Neurocomputing, 9, N 356, 83–96 (2019).
15. A. Krizhevsky, I. Sutskever, G. E. Hinton, Commun. ACM, 60, N 6, 84–90 (2017).
16. Q. Zou, L. H. Ni, T. Zhang, IEEE Geosci. Rem. Sens. Lett., 12, N 11, 2321–2325 (2015).
17. X. R. Ma, H. Y. Wang, J. Geng, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 3282–3285 (2016).
18. Y. Li, H. K. Zhang, X. Z. Xue, Wiley Interdisciplinary Reviews-Data Mining and Knowledge Discovery, 8, N 6 (2018).
19. L. Samaniego, A. Bardossy, K. Schulz, IEEE Trans. Geosci. Rem. Sens., 46, N 7, 2112–2125 (2008).
20. J. Li, J. M. Bioucas-Dias, A. Plaza, IEEE Trans. Geosci. Rem. Sens., 48, N 11, 4085–4098 (2010).
21. Y. Li, H. K. Zhang, Q. Shen, Rem. Sens., 9, N 1, 67 (2017).
22. J. Yue, S. J. Mao, M. Li, Rem. Sens. Lett., 7, N 9, 875–884 (2016).
23. Y. Chen, X. Zhao, X. Jia, IEEE J. Sel. Top. Appl. Earth Observ. Rem. Sens., 8, N 6, 2381–2392 (2015).
24. Y. S. Chen, Z. H. Lin, X. Zhao, IEEE J. Sel. Top. Appl. Earth Observ. Rem. Sens., 7, N 6, 2094–2107 (2014).
25. X. F. Liu, Q. Q. Sun, Y. Meng, Rem. Sens., 10, N 9, 1425 (2018).
26. Y. X. Jin, F, Liu, J. Zhang, Chin. J. Plant Ecol., 42, N 3, 361–371 (2018).
27. Z. B. Xie, P. Wu, G. D. Han, J. Agric. Mech. Res., 35, N 2, 189–191, 196 (2013).
28. S. W. Ji, W. Xu, M. Yang, IEEE Trans. Pattern Anal. Mach. Intel., 35, 221–231 (2013).
29. W. Zhao, H. Zhang, Proc. 2012 Int. Conf. Computer Science and Electronics Engineering (ICCSEE 2012), 23–25 March 2012, 88–391 (2012).
Review
For citations:
Pi W., Du J., Liu H., Zhu X. DESERTIFICATION GLASSLAND CLASSIFICATION AND THREE-DIMENSIONAL CONVOLUTION NEURAL NETWORK MODEL FOR IDENTIFYING DESERT GRASSLAND LANDFORMS WITH UNMANNED AERIAL VEHICLE HYPERSPECTRAL REMOTE SENSING IMAGES. Zhurnal Prikladnoii Spektroskopii. 2020;87(2):296-305.
Views: 326
Email this article 