Assessing Macro Disease Index of Wheat Stripe Rust Based on Segformer with Complex Background in the Field
Abstract
:1. Introduction
2. Materials and Methods
2.1. Data Sources
2.2. Data Preprocessing
2.3. Semantic Segmentation Model
2.4. Model Training
2.5. Model Evaluation
2.6. Calculation Method of Macro Disease Index (MDI)
3. Results and Analysis
3.1. Results with Different Models
3.2. The Influence of Different Loss Functions and Minority Class Weighting
3.3. Model Results with Different Data Sets
3.4. Comparison of Macro Disease Index Results
4. Discussion
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Chen, X. Pathogens which threaten food security: Puccinia striiformis, the wheat stripe rust pathogen. Food Secur. 2020, 12, 239–251. [Google Scholar] [CrossRef]
- Zeng, S.-M.; Luo, Y. Long-distance spread and interregional epidemics of wheat stripe rust in China. Plant Dis. 2006, 90, 980–988. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Wan, A.M.; Zhao, Z.H.; Chen, X.M.; He, Z.H.; Jin, S.L.; Jia, Q.Z.; Yao, G.; Yang, J.X.; Wang, B.T.; Li, G.B.; et al. Wheat stripe rust epidemic and virulence of Puccinia striiformis f. sp tritici in China in 2002. Plant Dis. 2004, 88, 896–904. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Pan, Y.; Gu, Y.; Luo, Y.; Ma, Z.; Huang, C.; Shi, L.; Yu, X. Study on relationship between the quantity of Puccinia striiformis f. sp. tritici in latent during overwinter and the disease index in Xiangyang area. Acta Phytopathol. Sin. 2016, 46, 679–685. [Google Scholar]
- Wan, A.M.; Chen, X.M.; He, Z.H. Wheat stripe rust in China. Aust. J. Agric. Res. 2007, 58, 605–619. [Google Scholar] [CrossRef]
- Huang, C.; Jiang, Y.; Li, P.; Peng, H.; Cui, Y.; Yang, J.; Xie, F. Epidemics analysis of wheat stripe rust in China in 2017. Plant Prot. 2018, 2, 162–166. [Google Scholar] [CrossRef]
- Chen, W.; Kang, Z.; Ma, Z.; Xu, S.; Jin, S.; Jiang, Y. Integrated Management of Wheat Stripe Rust Caused by Puccinia striiformis f. sp. tritici in China. Sci. Agric. Sin. 2013, 46, 4254–4262. [Google Scholar] [CrossRef]
- Pu, C.J.; Liu, W.H.; Chen, Z. Discussion on the forecasting method of mid-long term epidemic trend of wheat stripe rust. Acta Phytopathol. Sin. 2012, 42, 556. [Google Scholar]
- Alom, M.Z.; Taha, T.M.; Yakopcic, C.; Westberg, S.; Sidike, P.; Nasrin, M.S.; Hasan, M.; Van Essen, B.C.; Awwal, A.A.S.; Asari, V.K. A State-of-the-Art Survey on Deep Learning Theory and Architectures. Electronics 2019, 8, 292. [Google Scholar] [CrossRef] [Green Version]
- Singh, S.; Gupta, M.; Pandher, S.; Kaur, G.; Rathore, P.; Palli, S.R. Selection of housekeeping genes and demonstration of RNAi in cotton leafhopper, Amrasca biguttula biguttula (Ishida). PLoS ONE 2018, 13, 0191116. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Lin, K.; Gong, L.; Huang, Y.; Liu, C.; Pan, J. Deep Learning-Based Segmentation and Quantification of Cucumber Powdery Mildew Using Convolutional Neural Network. Front. Plant Sci. 2019, 10, 155. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Liang, Q.; Xiang, S.; Hu, Y.; Coppola, G.; Zhang, D.; Sun, W. (PDSE)-S-2-Net: Computer-assisted plant disease diagnosis and severity estimation network. Comput. Electron. Agric. 2019, 157, 518–529. [Google Scholar] [CrossRef]
- Esgario, J.G.M.; Krohling, R.A.; Ventura, J.A. Deep learning for classification and severity estimation of coffee leaf biotic stress. Comput. Electron. Agric. 2020, 169, 105162. [Google Scholar] [CrossRef] [Green Version]
- Hayit, T.; Erbay, H.; Varcin, F.; Hayit, F.; Akci, N. Determination of the severity level of yellow rust disease in wheat by using convolutional neural networks. J. Plant Pathol. 2021, 103, 923–934. [Google Scholar] [CrossRef]
- Mi, Z.; Zhang, X.; Su, J.; Han, D.; Su, B. Wheat Stripe Rust Grading by Deep Learning with Attention Mechanism and Images from Mobile Devices. Front. Plant Sci. 2020, 11, 558126. [Google Scholar] [CrossRef] [PubMed]
- Haixiang, G.; Yijing, L.; Shang, J.; Mingyun, G.; Yuanyue, H.; Bing, G. Learning from class-imbalanced data: Review of methods and applications. Expert Syst. Appl. 2017, 73, 220–239. [Google Scholar] [CrossRef]
- López, V.; Fernández, A.; García, S.; Palade, V.; Herrera, F. An insight into classification with imbalanced data: Empirical results and current trends on using data intrinsic characteristics. Inf. Sci. 2013, 250, 113–141. [Google Scholar] [CrossRef]
- Denil, M.; Trappenberg, T. Overlap versus imbalance. In Proceedings of the Canadian Conference on Artificial Intelligence, Montréal, QC, Canada, 6–9 May 2014; pp. 220–231. [Google Scholar]
- Russell, B.C.; Torralba, A.; Murphy, K.P.; Freeman, W.T. LabelMe: A database and web-based tool for image annotation. Int. J. Comput. Vis. 2008, 77, 157–173. [Google Scholar] [CrossRef]
- Huang, C.; Li, Y.; Loy, C.C.; Tang, X. IEEE Learning Deep Representation for Imbalanced Classification. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 21–30 June 2016; pp. 5375–5384. [Google Scholar]
- Wen, J.; Thibeau-Sutre, E.; Diaz-Melo, M.; Samper-González, J.; Routier, A.; Bottani, S.; Dormont, D.; Durrleman, S.; Burgos, N.; Colliot, O. Convolutional neural networks for classification of Alzheimer’s disease: Overview and reproducible evaluation. Med. Image Anal. 2020, 63, 101694. [Google Scholar] [CrossRef] [PubMed]
- Xie, E.; Wang, W.; Yu, Z.; Anandkumar, A.; Alvarez, J.M.; Luo, P. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. arXiv 2021, arXiv:2105.15203. [Google Scholar]
- Yuan, Y.; Chen, X.; Chen, X.; Wang, J. Segmentation transformer: Object-contextual representations for semantic segmentation. arXiv 2019, arXiv:1909.11065. [Google Scholar]
- Chen, L.-C.; Zhu, Y.; Papandreou, G.; Schroff, F.; Adam, H. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In Proceedings of the 15th European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 833–851. [Google Scholar]
- Zhao, H.; Shi, J.; Qi, X.; Wang, X.; Jia, J. Pyramid Scene Parsing Network. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 6230–6239. [Google Scholar]
- Yin, M.; Yao, Z.; Cao, Y.; Li, X.; Zhang, Z.; Lin, S.; Hu, H. Disentangled non-local neural networks. In European Conference on Computer Vision; Springer: Cham, Switzerland, 2020; pp. 191–207. [Google Scholar]
- Wang, J.; Sun, K.; Cheng, T.; Jiang, B.; Deng, C.; Zhao, Y.; Liu, D.; Mu, Y.; Tan, M.; Wang, X. Deep high-resolution representation learning for visual recognition. In IEEE Transactions on Pattern Analysis and Machine Intelligence; IEEE: Piscataway, NJ, USA, 2020; Volume 43, pp. 3349–3364. [Google Scholar]
- Cao, Y.; Xu, J.; Lin, S.; Wei, F.; Hu, H. GCNet: Non-local networks meet squeeze-excitation networks and beyond. In Proceedings of the IEEE International Conference on Computer Vision Workshops, Seoul, Korea, 27–28 October 2019. [Google Scholar]
- Li, X.; You, A.; Zhu, Z.; Zhao, H.; Yang, M.; Yang, K.; Tan, S.; Tong, Y. Semantic Flow for Fast and Accurate Scene Parsing; Springer: Cham, Switzerland, 2020; pp. 775–793. [Google Scholar]
- Kervadec, H.; Bouchtiba, J.; Desrosiers, C.; Granger, E.; Dolz, J.; Ben Ayed, I. Boundary loss for highly unbalanced segmentation. Med. Image Anal. 2021, 67, 101851. [Google Scholar] [CrossRef] [PubMed]
- Shrivastava, A.; Gupta, A.; Girshick, R. Training region-based object detectors with online hard example mining. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 761–769. [Google Scholar]
- Berman, M.; Triki, A.R.; Blaschko, M.B. The lovász-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 4413–4421. [Google Scholar]
- Lin, T.-Y.; Goyal, P.; Girshick, R.; He, K.; Dollár, P. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2980–2988. [Google Scholar]
- Liu, Y.; Chu, L.; Chen, G.; Wu, Z.; Chen, Z.; Lai, B.; Hao, Y. PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation. arXiv 2021, arXiv:2101.06175. [Google Scholar]
- Patil, S.B.; Bodhe, S.K. Leaf disease severity measurement using image processing. Int. J. Eng. Technol. 2011, 3, 297–301. [Google Scholar]
- Lei, Y.; Han, D.-J.; Zeng, Q.-D.; He, D. Grading method of disease severity of wheat stripe rust based on hyperspectral imaging technology. Trans. Chin. Soc. Agric. Mach. 2018, 49, 226–232. [Google Scholar]
- Gupta, A.; Dollar, P.; Girshick, R. Lvis: A dataset for large vocabulary instance segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 5356–5364. [Google Scholar]
- Gan, D.; Shen, J.; An, B.; Xu, M.; Liu, N. Integrating TANBN with cost sensitive classification algorithm for imbalanced data in medical diagnosis. Comput. Ind. Eng. 2020, 140, 106266. [Google Scholar] [CrossRef]
- De Morais, R.F.; Vasconcelos, G.C. Boosting the performance of over-sampling algorithms through under-sampling the minority class. Neurocomputing 2019, 343, 3–18. [Google Scholar] [CrossRef]
- Taha, A.Y.; Tiun, S.; Abd Rahman, A.H.; Sabah, A. Multilabel Over-sampling and Under-sampling with Class Alignment for Imbalanced Multilabel Text Classification. J. Inf. Commun. Technol. 2021, 20, 423–456. [Google Scholar] [CrossRef]
- Cabezas, M.; Kentsch, S.; Tomhave, L.; Gross, J.; Caceres, M.L.L.; Diez, Y. Detection of Invasive Species in Wetlands: Practical DL with Heavily Imbalanced Data. Remote Sens. 2020, 12, 3431. [Google Scholar] [CrossRef]
- Lee, Y.O.; Jo, J.; Hwang, J. Application of deep neural network and generative adversarial network to industrial maintenance: A case study of induction motor fault detection. In Proceedings of the 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, USA, 11–14 December 2017; pp. 3248–3253. [Google Scholar]
- Zhou, F.; Yang, S.; Fujita, H.; Chen, D.; Wen, C. Deep learning fault diagnosis method based on global optimization GAN for unbalanced data. Knowl.-Based Syst. 2020, 187, 104837. [Google Scholar] [CrossRef]
Percentage of Class | Original Dataset O | Augmentation Dataset A | Under-Sampled Dataset U1 | Under-Sampled Dataset U2 | Under-Sampled Dataset U3 |
---|---|---|---|---|---|
Healthy | 48.03% | 42.80% | 44.95% | 42.66% | 38.60% |
Rust | 5.66% | 17.89% | 9.37% | 12.10% | 17.16% |
Other | 46.30% | 39.31% | 45.68% | 45.24% | 44.24% |
Total image number | 25,530 | 43,530 | 15,292 | 11,792 | 8292 |
Optimizer | Momentum | Learning Rate (LR) | LR Scheduler |
---|---|---|---|
Sgd | 0.9 | 0.01 | Polynomial decay |
end_lr | LR_power | Loss function | Iters |
0 | 0.9 | Cross-entropy loss | 26,000 |
Mini-batch size | Max epoch | Validation frequency | |
30 | 50 | Each epoch |
Models_BACKBONES | Precision | Recall | F1 Score | IOU | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Other | Healthy | Rust | Other | Healthy | Rust | Other | Healthy | Rust | Other | Healthy | Rust | |
OCRNet_Hrnetw48 | 90.3% | 86.7% | 75.1% | 88.2% | 90.8% | 58.8% | 89.2% | 88.7% | 65.9% | 80.6% | 79.7% | 49.2% |
Pspnet_Resnet101 | 88.1% | 86.4% | 68.1% | 87.3% | 88.1% | 61.9% | 87.7% | 87.2% | 64.8% | 78.0% | 77.4% | 48.0% |
Deeplabv3p_Resnet50 | 91.1% | 87.1% | 68.9% | 88.1% | 90.4% | 65.9% | 89.6% | 88.7% | 67.4% | 81.2% | 79.7% | 50.8% |
Sfnet_Resnet50 | 90.4% | 87.5% | 72.0% | 88.8% | 89.8% | 66.7% | 89.6% | 88.6% | 69.2% | 81.2% | 79.6% | 53.1% |
DNLNET_Resnet101 | 89.1% | 87.1% | 66.7% | 87.6% | 88.9% | 64.5% | 88.4% | 88.0% | 65.6% | 79.2% | 78.5% | 48.8% |
FCN_Hrnetw18 | 89.7% | 86.6% | 73.2% | 88.2% | 89.6% | 61.8% | 89.0% | 88.1% | 67.0% | 80.1% | 78.7% | 50.4% |
GCNET_Resnet150 | 88.6% | 89.0% | 72.4% | 90.1% | 88.4% | 66.5% | 89.3% | 88.7% | 69.3% | 80.7% | 79.8% | 53.0% |
Segformer_ViT_B5 | 91.3% | 87.8% | 75.6% | 88.9% | 90.9% | 69.8% | 90.1% | 89.3% | 72.6% | 82.0% | 80.7% | 57.0% |
Precision | Recall | F1 | IOU | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Other | Healthy | Rust | Other | Healthy | Rust | Other | Healthy | Rust | Other | Healthy | Rust | |
Ohem | 90.9% | 87.6% | 78.6% | 88.9% | 90.9% | 67.8% | 89.9% | 89.2% | 72.8% | 81.6% | 80.6% | 57.2% |
Lovász-Softmax | 91.3% | 87.7% | 77.1% | 88.9% | 91.1% | 68.9% | 90.0% | 89.3% | 72.8% | 81.9% | 80.7% | 57.2% |
Focal loss | 91.4% | 87.5% | 77.2% | 88.6% | 91.3% | 69.3% | 90.0% | 89.4% | 73.0% | 81.8% | 80.8% | 57.5% |
CE + boundary | 91.1% | 87.2% | 76.2% | 88.3% | 91.1% | 66.5% | 89.6% | 89.1% | 71.0% | 81.2% | 80.4% | 55.1% |
CE + dice | 90.3% | 87.7% | 77.7% | 89.1% | 90.6% | 64.9% | 89.7% | 89.1% | 70.7% | 81.3% | 80.3% | 54.7% |
CE_1:1:1 | 92.1% | 86.6% | 77.6% | 87.7% | 92.1% | 66.9% | 89.8% | 89.3% | 71.8% | 81.5% | 80.6% | 56.1% |
CE_1:1:2 | 91.2% | 87.9% | 73.8% | 88.8% | 90.6% | 71.4% | 89.9% | 89.2% | 72.6% | 81.7% | 80.6% | 57.0% |
CE_1:1:5 | 91.5% | 88.2% | 69.2% | 88.4% | 90.2% | 74.3% | 89.9% | 89.2% | 71.6% | 81.7% | 80.5% | 55.8% |
CE_1:1:10 | 91.5% | 87.8% | 63.4% | 87.5% | 89.7% | 74.5% | 89.5% | 88.7% | 68.5% | 80.9% | 79.8% | 52.1% |
DATASETS | Precision | Recall | F1 | IOU | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Other | Healthy | Rust | Other | Healthy | Rust | Other | Healthy | Rust | Other | Healthy | Rust | |
O | 91.4% | 87.5% | 77.2% | 88.6% | 91.3% | 69.3% | 90.0% | 89.4% | 73.0% | 81.8% | 80.8% | 57.5% |
A | 90.9% | 88.6% | 86.5% | 90.5% | 88.9% | 86.7% | 90.7% | 88.7% | 86.6% | 83.0% | 79.8% | 76.3% |
U1 | 92.8% | 90.7% | 81.5% | 92.3% | 90.5% | 84.0% | 92.6% | 90.6% | 82.7% | 86.2% | 82.8% | 70.6% |
U2 | 93.7% | 90.0% | 87.2% | 92.1% | 92.9% | 80.9% | 92.9% | 91.4% | 84.0% | 86.8% | 84.2% | 72.4% |
U3 | 93.7% | 87.1% | 85.1% | 90.9% | 90.4% | 84.1% | 92.3% | 88.7% | 84.6% | 85.7% | 79.7% | 73.3% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Deng, J.; Lv, X.; Yang, L.; Zhao, B.; Zhou, C.; Yang, Z.; Jiang, J.; Ning, N.; Zhang, J.; Shi, J.; et al. Assessing Macro Disease Index of Wheat Stripe Rust Based on Segformer with Complex Background in the Field. Sensors 2022, 22, 5676. https://doi.org/10.3390/s22155676
Deng J, Lv X, Yang L, Zhao B, Zhou C, Yang Z, Jiang J, Ning N, Zhang J, Shi J, et al. Assessing Macro Disease Index of Wheat Stripe Rust Based on Segformer with Complex Background in the Field. Sensors. 2022; 22(15):5676. https://doi.org/10.3390/s22155676
Chicago/Turabian StyleDeng, Jie, Xuan Lv, Lujia Yang, Baoqiang Zhao, Congying Zhou, Ziqian Yang, Jiarui Jiang, Ning Ning, Jinyu Zhang, Junzheng Shi, and et al. 2022. "Assessing Macro Disease Index of Wheat Stripe Rust Based on Segformer with Complex Background in the Field" Sensors 22, no. 15: 5676. https://doi.org/10.3390/s22155676
APA StyleDeng, J., Lv, X., Yang, L., Zhao, B., Zhou, C., Yang, Z., Jiang, J., Ning, N., Zhang, J., Shi, J., & Ma, Z. (2022). Assessing Macro Disease Index of Wheat Stripe Rust Based on Segformer with Complex Background in the Field. Sensors, 22(15), 5676. https://doi.org/10.3390/s22155676