CLASSIFICATION OF TREE SPECIES AT THE LEAF LEVEL BASED ON HYPERSPECTRAL IMAGING TECHNOLOGY
Abstract
This study utilized hyperspectral imaging technology to identify eight tree species at the leaf level. The successive projections algorithm (SPA), information gain (IG), and Gini index (Gini) were used to select the feature bands. Furthermore, the binary particle swarm optimization (BPSO) algorithm was used to optimize the feature bands selected by SPA, IG, and Gini. The particle swarm optimization-extreme learning machine (PSO-ELM), linear Bayes normal classifier (LBNC), and k-nearest neighbor (KNN) recognition models for tree species were established based on all bands, feature bands, and optimized feature bands, respectively. The experimental results show that the recognition rates of the PSO-ELM, LBNC, and KNN models based on all bands were 98.45, 99.10, and 83.67%, respectively. The SPA, IG, and Gini can all effectively select spectral bands on tree species discrimination and greatly reduce the dimension of spectral data, in which the recognition effects of the models based on the feature bands selected by Gini were the best, and the recognition rates of the PSO-ELM, LBNC, and KNN models reached 97.55, 96.53, and 80.5%, respectively. Additionally, BPSO-SPA, BPSO-IG, and BPSO-Gini can all further reduce the dimension of spectral data on the basis of ensuring the recognition accuracy of models, in which the models established based on the optimized feature bands selected by BPSO-Gini achieved the best recognition effect and the recognition rates of the PSO-ELM, LBNC, and KNN models reached 96.53, 96.68, and 81.05%, respectively. In general, the recognition performance of the PSO-ELM model was better than those of the LBNC and KNN models.
Keywords
tree species identification,
leaf level,
hyperspectral imaging technology,
dimensionality reduction,
feature band optimization
Supporting agencies: This work was supported by the National Natural Science Foundation of China (Grant No 31570713) and the Beijing Municipal Construction Project Special Fund.
About the Authors
R. Yang
School of Technology, Beijing Forestry University
China
China
Key Laboratory of State Forestry Administration on Forestry Equipment and Automation
Beijing 100083J. Kan
School of Technology, Beijing Forestry University
China
China
Key Laboratory of State Forestry Administration on Forestry Equipment and Automation
Beijing 100083References
1. X. S. Liu, X. L. Zhang, Forest Res. Manage, 1 , 61–64 (2004).
2. O. Nevalainen, E. Honkavaara, S. Tuominen, N. Viljanen, T. Hakala, X. Yu, Remote Sens., 9 , 185 (2017).
3. L. C. Plourde, S. V. Ollinger, M. L. Smith, M. E. Martin, Photogram. Eng. Remote Sens., 73 , No. 7, 829–840 (2007).
4. B. X. Ma, Y. B. Ying, X. Q. Rao, J. S. Gui, Spectrosc. Spectr. Anal., 29 , No. 6, 1611–1615 (2009).
5. J. B. Feret, G. P. Asner, IEEE Transact. Geosci. Remote Sens., 51 , No. 1, 73–84 (2012).
6. R. George, H. Padalia, S. P. S. Kushwaha, Int. J. Appl. Earth Observ. Geoinform., 28 , No. 1, 140–149 (2014).
7. M. Jia, Y. Zhang, Z. Wang, K. Song, C. Ren, Int. J. Appl. Earth Observ. Geoinform., 33 , No. 1, 226–231 (2014).
8. H. P. La, D. E. Yang, A. Chang, C. Kim, KSCE J. Civil Engin., 19 , No. 4, 1078–1087 (2015).
9. Z. Zhang, A. Kazakova, L. Moskal, D. Styers, Forests, 7 , No. 6, 122 (2016).
10. J. Cao, W. Leng, K. Liu, L. Liu, Z. He, Y. Zhu, Remote Sens., 10 , No. 1, 89 (2018).
11. A. Ghosh, F. E. Fassnacht, P. K. Joshi, B. Koch, Int. J. Appl. Earth Observ. Geoinform., 26 , No. 2, 49–63 (2014).
12. R. D. Jackson, P. M. Teillet, P. N. Slater, G. Fedosejevs, M. F. Jasinski, J. K. Aase, Remote Sens. Environ., 32 , No. 2, 189–202 (1990).
13. X. Li, A. H. Strahler, IEEE Transact. Geosci. Remote Sens., 30 , No. 2, 276–292 (1992).
14. P. Pellikka, D. J. King, S. G. Leblanc, Remote Sens. Rev., 19 , No. 1-4, 259–291 (2000).
15. S. Tuominen, R. Nasi, E. Honkavaara, A. Balazs, T. Hakala, N. Viljanen, I. Polonen, H. Saari, H. Ojanen, Remote Sens., 10 , No. 5, 714 (2018).
16. M. A. Cochrane, Int. J. Remote Sens., 21 , No. 10, 2075–2087 (2000).
17. Z. H. Wang, L. X. Ding, Spectrosc. Spectr. Analys., 30 , No. 7, 1825–1829 (2010).
18. H. J. Lin, H. F. Zhang, Y. Q. Gao, X. Li, F. Yang, Y. F. Zhou, Spectrosc. Spectr. Anal., 34 , No. 12, 3358–3362 (2014).
19. X. R. Geng, K. Sun, L. Y. Ji, Y. C. Zhao, IEEE Trans. Geosci. Remote Sens., 52 , No. 11, 7111–7119 (2014).
20. Y. Liu, H. Xie, L. G. Wang, K. Z. Tan, Appl. Opt., 55 , No. 3, 462–472 (2016).
21. G. K. Zhu, Y. C. Huang, S. Y. Li, J. Tang, D. Liang, IEEE Geosci. Remote Sens. Lett., 14 , No. 12, 2320–2324 (2017).
22. S. Jia, G. H. Tang, J. S. Zhu, Q. Q. Li, IEEE Trans. Geosci. Remote Sens., 54 , No. 1, 88–102 (2016).
23. M. Huang, J. Tang, B. Yang, Q. Zhu, Comput. Electron. Agric., 122 , 139–145 (2016).
24. M. C. U. Araujo, T. C. B. Saldanha, R. K. H. Galvao, T. Yoneyama, H. C. Chame, V. Visani, Chemometrics Intell. Lab. Syst., 57 , No. 2, 65–73 (2001).
25. Q. Dai, Cheng, J. H. Sun, X. A. Zeng, J. Food Eng., 136 , 64–72 (2014).
26. Y. He, C. Zhang, F. Liu, W. W. Kong, P. Cui, W. J. Zhou, Appl. Eng. Agric., 31 , No. 1, 23–30 (2015).
27. Z. Y. Huang, J. Shandong Agric. Univ. (Nat. Sci. Ed.), 44 (2), 252–256 (2013).
28. W. Q. Shang, H. K. Huang, Y. L. Liu, Y. M. Lin, Y. L. Qu, H. B. Dong, J. Comput. Res. Dev., 43 (10), 1688–1694 (2006).
29. G. B. Huang, Q. Y. Zhu, C. K. Siew, Neurocomputing, 70 , No. 1/2/3, 489–501 (2006).
30. J. Wang, L. Zhang, J. J. Cao, D. Han, Int. J. Mach. Learn. Cyber., 9 , No. 1, 21–35 (2018).
31. A. Kadir, Proc. 3rd Int. Symp. “Leaf Identification Using Polar Fourier Transform and Linear Bayes Normal Classifier”, 40–49 ( 2015 ).
32. T. Cover, P. Hart, IEEE Trans. Inform. Theory, 13 , No. 1, 21–27 (1967).
33. W. Sun, C. F. Wang, C. C. Zhang, J. Clean Prod., 162 , 1095–1101 (2017).
34. J. Kennedy, R. Eberhart, IEEE Int. Conf. Neural Networks, 4 , 1942–1948 (1995).
35. J. Kennedy, R. C. Eberhart, IEEE Int. Conf. Systems, Man, Cybern. Comput. Cybern. Simul., 5 , 4104–4108 (1997).
36. X. T. Zhao, S. J. Zhang, J. L. Liu, H. X. Sun, Food Sci. Technol., 33 , No. 10, 281–287 (2017).
Review
For citations:
Yang R., Kan J. CLASSIFICATION OF TREE SPECIES AT THE LEAF LEVEL BASED ON HYPERSPECTRAL IMAGING TECHNOLOGY. Zhurnal Prikladnoii Spektroskopii. 2020;87(1):175(1)-175(10).
Views: 289
Email this article 