|Generate QR code
Open Access
Subscription Access
Research on Grassland Rodent Infestation Monitoring Methods Based on Dense Residual Networks and Unmanned Aerial Vehicle Remote Sensing
Abstract
Grassland rodent infestations are important factors that limit the healthy development of grassland ecosystems. Understanding the spatial distributions of rodent populations in relation to vegetation and soil is a prerequisite for implementing ecological prevention and control measures to alleviate rodent infestations. A low-altitude unmanned aerial vehicle hyperspectral image data acquisition system has been developed for monitoring grassland rodent infestations. The three-dimensional dense convolutional network (3D-DenseNet) model is improved by using a residual structure and asymmetric convolution, and a 3D deep dense residual network (3D-DDRNet) model is proposed and used to classify the features of grassland rodent monitoring information. The results show that the overall classification accuracy of the 3D-DDRNet model is 96.68%, and the model size is 6.12 MB. The overall accuracy is improved by 1.46%, and the model size is reduced by 15.5% compared with that achieved before the improvement. This study can be used as a benchmark for the extraction and inversion of rodent information acquired from grassland remote sensing images, and it provides a theoretical basis for grassland rodent pest control.
Keywords
remote sensing with unmanned aerial vehicles,
3D dense convolutional network,
grassland rodent infestation,
grassland degradation
Supporting agencies: The research leading to these results received funding from the National Natural Science Foundation of China under grant agreement No. 31660137.
About the Authors
T. Zhang
Inner Mongolia Agricultural University
China
China
Mechanical and Electrical Engineering College,
Hohhot
J. Du
Inner Mongolia Agricultural University
China
China
Mechanical and Electrical Engineering College,
Hohhot
X. Zhu
Inner Mongolia Agricultural University
China
China
Mechanical and Electrical Engineering College,
Hohhot
X. Gao
Inner Mongolia Agricultural University
China
China
Mechanical and Electrical Engineering College,
Hohhot
References
1. T. Akiyama, K. Kawamura, Grassl. Sci., 53, No. 1, 1 (2007).
2. X. Lyu, X. Li, J. Gong, H. Wang, D. Dang, H. Dou, S. Li, S. Liu, Sustainability (Basel, Switzerland), 12, No. 9, 3682 (2020).
3. X. Lyu, X. Li, D. Dang, H. Dou, X. Xuan, S. Liu, M. Li, J. Gong, Ecol. Indic., 114, 106310 (2020).
4. W. Q. Zhong, Q. Q. Zhou, C. L. Sun, Acta Theriolog. Sinica, 5, No. 4, 241 (1985).
5. D. Sun, J. H. Zheng, T. Ma, J. J. Chen, X. Li, Int. Arch. Photogram., Remote Sens. Spatial Information Sci., XLII-3, 1575 (2018).
6. L. Kang, X. Han, Z. Zhang, O. J. Sun, Phil. Trans. R. Soc. B, 362, No. 1482, 997 (2007).
7. J. Jacob, C. Imholt, C. Caminero-Saldaña, G. Couval, P. Giraudoux, S. Herrero-Cófreces, G. Horváth, J. J. Luque-Larena, E. Tkadlec, E. Wymenga, J. Pest Sci., 93, No. 2, 703 (2020).
8. Y. Wang, Z. Ren, P. Ma, Z. Wang, D. Niu, H. Fu, J. J. Elser, Sci. Total Environ., 722, 137910 (2020).
9. D. Mao, Z. Wang, B. Wu, Y. Zeng, L. Luo, B. Zhang, Land Degrad. Dev., 29, No. 11, 3841 (2018).
10. H. Yang, J. Du, Optik, 247, 167877 (2021).
11. D. Holiaka, H. Kato, V. Yoschenko, Y. Onda, Y. Igarashi, K. Nanba, P. Diachuk, M. Holiaka, R. Zadorozhniuk, V. Kashparov, I. Chyzhevskyi, J. Environ. Manage., 295, 113319 (2021).
12. L. N. Habibi, T. Watanabe, T. Matsui, T. S. T. Tanaka, Remote Sens. (Basel, Switzerland), 13, No. 13, 2548 (2021).
13. A. Gebrehiwot, L. Hashemi-Beni, G. Thompson, P. Kordjamshidi, T. E. Langan, Sensors (Basel, Switzerland), 19, No. 7, 1486 (2019).
14. J. Wan, D. Jian, D. Yu, J. Phys. Conf. Ser., 1952, No. 2, 22061 (2021).
15. Y. Chen, Z. Lin, X. Zhao, G. Wang, Y. Gu, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 7, No. 6, 2094 (2014).
16. J. S. Barrera, A. Echavarría, C. Madrigal, J. Herrera-Ramirez, J. Phys. Conf. Ser., 1547, No. 1, 12014 (2020).
17. W. Qi, X. Zhang, IOP Conf. Ser. Earth Environ. Sci., 502, No. 1, 12015 (2020).
18. Z. Xue, X. Yu, B. Liu, X. Tan, X. Wei, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 14, 3566 (2021).
19. Z. Zhong, J. Li, L. Ma, H. Jiang, H. Zhao, IEEE Int. Geoscience and Remote Sensing Symposium (IGARSS), 1824 (2017).
20. C. Zhang, G. Li, S. Du, W. Tan, F. Gao, J. Appl. Remote Sens., 13, No. 1, 1 (2019).
21. X. X. Xie, X. W. Nan, Y. X. Li, F. Li, B. H. Liu, S. Q. Wu, H. X. Wang, Chin. J. Vector Biology and Control, 31, No. 5, 602 (2020).
22. W. Pi, J. Du, H. Liu, X. Zhu, J. Appl. Spectrosc., 87, No. 2, 309 (2020).
23. G. Huang, Z. Liu, L. V. D. Maaten, K. Q. Weinberger, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2261 (2017).
24. X. Ding, Y. Guo, G. Ding, J. Han, IEEE/CVF Int. Conf. Computer Vision (ICCV), 1911 (2019).
25. K. He, X. Zhang, S. Ren, J. Sun, IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 770 (2016).
26. S. F. Sawyer, J. Man. Manip. Ther., 17, No. 2, 27E (2009).
27. J. Yue, W. Zhao, S. Mao, H. Liu, Remote Sens. Lett., 6, No. 6, 468 (2015).
28. W. Pi, J. Du, Y. Bi, X. Gao, X. Zhu, Ecol. Inform., 62, 101278 (2021).
Review
For citations:
Zhang T., Du J., Zhu X., Gao X. Research on Grassland Rodent Infestation Monitoring Methods Based on Dense Residual Networks and Unmanned Aerial Vehicle Remote Sensing. Zhurnal Prikladnoii Spektroskopii. 2022;89(6):905.
Views: 108
Email this article 