基于Faster R-CNN的野外环境中蝗虫快速识别

doi:10.3969/j.issn.1673-503X.2020.06.017

Abstract

Abstract:

Locust is the stubborn pest insects which can damage crops and ecosystems.Traditional methods for monitoring locust have many disadvantages.To effectively apply massive field image data to achieve real-time monitoring of locusts, a locust automatic identification model based on a deep learning network was established in this study.Firstly, 280 locust RGB images photographed by the mobile phone camera in a complex field environment from the grasslands of Xilinhot, Inner Mongolia were obtained.Then the Faster R-CNN network structure which performs better in recognition was used.The accuracy of this model is 0.756.The model performs well on locust detection and outperforms the previous methods in the identify results and practicality.The model can accurately identify the locust from the complex environment on fields, which provide auxiliary information for the control of locusts.It is a basis for establishing a real-time monitoring system for monitoring locusts.At the same time, the network structure can also be applied to other pests and diseases' monitor.In addition, the model broadens the application field of deep learning algorithms.

Key words: Locust, Deep learning, Identification, Faster R-CNN

CLC Number:

TP391.41/S433.2

Ying-jie WU,Shi-bo FANG,Chudzik Piotr,Pearson Simon,Al-Diri1 Bashir,Xu-yu FENG,Yun-peng LI. Rapid identification of locust on fields based on Faster R-CNN[J]. Journal of Meteorology and Environment, 2020, 36(6): 137-143.

Figures/Tables 8

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Table 1

Fig.7

References 30

1	Estruch J J , Carozzi N B , Desai N , et al. Transgenic plants:an emerging approach to pest control[J]. Nature Biotechnology, 1997, 15 (2): 137- 141.
2	Latchininsky A V . Locusts and remote sensing:a review[J]. Journal of Applied Remote Sensing, 2013, 7 (1): 075099. doi: 10.1117/1.JRS.7.075099
3	Zhang L , Hunter D M . Management of locusts and grasshoppers in China[J]. Journal of Orthoptera Research, 2017, 26 (2): 155- 159. doi: 10.3897/jor.26.20119
4	石瑞香, 刘闯, 李典谟, 等. 蝗虫生境监测方法研究进展[J]. 生态学报, 2003, 23 (11): 2475- 2483. doi: 10.3321/j.issn:1000-0933.2003.11.032
5	Sivanpillai R , Latchininsky A V , Driese K L , et al. Mapping locust habitats in River Ili Delta, Kazakhstan, using Landsat imagery[J]. Agriculture, Ecosystems & Environment, 2006, 117 (2/3): 128- 134.
6	Sivanpillai R , Latchininsky A V . Mapping locust habitats in the Amudarya River Delta, Uzbekistan with multi-temporal MODIS imagery[J]. Environmental Management, 2007, 39 (6): 876- 886. doi: 10.1007/s00267-006-0193-y
7	Latchininsky A V, Sivanpillai R.Locust habitat monitoring and risk assessment using remote sensing and GIS technologies[M]//Ciancia A, Mukerji K.Integrated management of arthropod pests and insect borne diseases.Dordrecht, Netherlands: Springer, 2010: 163-188.
8	Latchininsky A, Piou C, Franc A, et al.8-Applications of remote sensing to locust management[M]//Baghdadi N, Zribi M.Land surface remote sensing.Oxford, UK: Elsevier, 2016: 263-293.
9	房世波, 韩威, 裴志方. 沙漠蝗群对印巴边境植被的影响及其未来可能发展趋势[J]. 遥感学报, 2020, 24 (3): 326- 332.
10	孙苏琪, 王式功, 罗彬, 等. 应用机器学习算法的成都市冬季空气污染预报研究[J]. 气象与环境学报, 2020, 36 (2): 98- 104. doi: 10.3969/j.issn.1673-503X.2020.02.013
11	李晓岚, 刘旸, 栾健, 等. 基于BP人工神经网络法沈阳市PM_2.5质量浓度集成预报试验[J]. 气象与环境学报, 2018, 34 (2): 100- 106. doi: 10.3969/j.issn.1673-503X.2018.02.013
12	Girshick R, Donahue J, Darrell T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE.2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus, OH, USA: IEEE, 2014: 580-587.
13	Ren S , He K , Girshick R , et al. Faster R-CNN:Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
14	He K , Zhang X Y , Ren S Q , et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37 (9): 1904- 1916. doi: 10.1109/TPAMI.2015.2389824
15	Redmon J, Divvala S, Girshick R, et al.You only look once: Unified, real-time object detection[C]//IEEE.2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas, NV, USA: IEEE, 2016: 779-788.
16	瞿建华, 鄢俊洁, 薛娟, 等. 基于深度学习的FY3D/MERSI和EOS/MODIS云检测模型研究[J]. 气象与环境学报, 2019, 35 (3): 87- 93.
17	Swersky K, Snoek J, Adams R P.Multi-task bayesian optimization[C]//Neural Infommation Processing Systems.Advances in Neural Information Processing Systems 26.Red Hook, NY: Curran Associates, Inc., 2013: 2004-2012.
18	Lee C Y, Xie S N, Gallagher P, et al.Deeply-supervised nets[C]//Proceedings of Machine Learning Research.Proceedings of the Eighteenth Internatinal Conference on Artificial Intelligence and statistics.San Diego, California, USA: PMLR, 2015: 562-570.
19	Russakovsky O , Deng J , Su H , et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115 (3): 211- 252. doi: 10.1007/s11263-015-0816-y
20	Szegedy C, Liu W, Jia Y Q, et al.Going deeper with convolutions[C]//IEEE.2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston, MA, USA: IEEE, 2015: 1-9.
21	Jiang H, Learned-Miller E.Face detection with the Faster R-CNN[C]//IEEE.2017 IEEE International Conference on Automatic Face and Gesture Recognition and Workshops.Washington, DC, USA: IEEE, 2017: 650-657.
22	Xu Y Z , Yu G Z , Wang Y P , et al. Car detection from low-altitude UAV imagery with the Faster R-CNN[J]. Journal of Advanced Transportation, 2017, 2823617.
23	Li J X , Zhang D X , Zhang J J , et al. Facial expression recognition with Faster R-CNN[J]. Procedia Computer Science, 2017, (107): 135- 140.
24	Sun X D , Wu P C , Hoi S C H . Face detection using deep learning:An improved faster RCNN approach[J]. Neurocomputing, 2018, (299): 42- 50.
25	Xiong X, Wang Y, Zhang X.Color Image Segmentation using Pulse-Coupled Neural Network for Locusts Detection[C]//Crone S F, Lessmann S, Stahlbock R.Proceedings of the 2006 International Conference on Data Mining, DMIN 2006.Las Vegas, Nevada, USA: CSREA Press, 2006.
26	Liu Z Y , Gao J F , Yang G G , et al. Localization and classification of paddy field pests using a saliency map and deep convolutional neural network[J]. Scientific Reports, 2016, 6 (2): 20410.
27	Liu L , Wang R J , Xie C J , et al. PestNet:An end-to-end deep learning approach for large-scale multi-class pest detection and classification[J]. IEEE Access, 2019, 7 (4): 45301- 45312.
28	Xia D N , Chen P , Wang B , et al. Insect detection and classification based on an improved convolutional neural network[J]. Sensors, 2018, 18 (12): 4169. doi: 10.3390/s18124169
29	Ding W G , Taylor G . Automatic moth detection from trap images for pest management[J]. Computers and Electronics in Agriculture, 2016, 123 (4): 17- 28.
30	Simonyan K, Zisserman A.Very deep convolutional networks for large-scale image recognition[C]//Bengio Y, LeCun Y.3rd International Conference on Learning Representations, ICLR 2015.San Diego, CA, USA: ICLR, 2015.

识别指标	循环1	循环2	循环3	循环4	循环5	循环6	循环7	循环8	循环9	平均
精确度	0.696	0.778	0.913	0.955	0.586	0.719	0.750	0.684	0.720	0.756
准确度	0.500	0.477	0.618	0.677	0.548	0.605	0.656	0.433	0.439	0.551
平均识别精度	0.479	0.455	0.629	0.616	0.462	0.611	0.617	0.426	0.409	0.522

[1]	Yi-yong CAI, Guo-fei WEI, Hao-fei DANG, Qing LIN. Identification and spatial verification of the forecasting bias of the main rain belts based on precipitation objectives [J]. Journal of Meteorology and Environment, 2020, 36(1): 36-42.
[2]	YANG Lei, HE Hong-bing, YANG Bo, MENG Xin. Identification of hydrometeors based on S-band dual-polarimetric radar measurement [J]. Journal of Meteorology and Environment, 2019, 35(4): 127-132.
[3]	QU Jian-hua, YAN Jun-jie, XUE Juan, GUO Xue-xing. Research on the cloud detection model of FY3D/MERSI and EOS/MODIS based on deep learning [J]. Journal of Meteorology and Environment, 2019, 35(3): 87-93.
[4]	LE Zhang-yan,BAI Yue-ming, LIU Ling,WANG Pei-juan,GAO Su-hua. The effect of temperature on hatching of Asiatic migratory locust in the grassland of northeast China [J]. Journal of Meteorology and Environment, 2013, 29(5): 144-147.
[5]	WANG Cheng-wei,XU Hai-ming,REN Li,CHEN Li. The objective identification method of northeast cold vortex [J]. Journal of Meteorology and Environment, 2012, 28(2): 1-4.

Rapid identification of locust on fields based on Faster R-CNN

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 30

Related Articles 5

Metrics

Comments

Recommended 10