Enhancing Tuta absoluta Detection on Tomato Plants: Ensemble Techniques and Deep Learning
Abstract
:1. Introduction
2. Related Work
2.1. Tomato Disease and Pest Identification
2.2. Tuta Absoluta Identification
3. Methodology
3.1. Dataset
3.2. Object Detection Models
3.3. Ensemble Techniques
3.4. Object Detection and Ensemble Workflow
3.5. Object Detection Model Training
3.6. Evaluation Metrics
4. Results and Discussion
4.1. Initial Model Evaluations
4.2. Qualitative Results
4.3. Ensemble Results
4.4. Comparison with State-of-the-Art
4.5. Benchmark Analysis with YOLOv8
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
C4 | Convolutional Layer 4 |
COCO | Common Objects in Context |
CLAHE | Contrast Limited Adaptive Histogram Equalization |
CNN | Convolutional Neural Network |
DC5 | Dilated Convolutional Layer 5 |
FPN | Feature Pyramid Network |
Faster R-CNN | Faster Region-Based Convolutional Neural Network |
IoU | Intersection over Union |
mAP | mean Average Precision |
NMS | Non-Maximum Suppression |
NMW | Non-Maximum Weighted |
ResNet | Residual Network |
SGD | Stochastic Gradient Descent |
Soft NMS | Soft Non-Maximum Suppression |
WBF | Weighted Boxes Fusion |
YOLO | You Only Look Once |
References
- Zhang, S.; Griffiths, J.S.; Marchand, G.; Bernards, M.A.; Wang, A. Tomato brown rugose fruit virus: An emerging and rapidly spreading plant RNA virus that threatens tomato production worldwide. Mol. Plant Pathol. 2022, 23, 1262–1277. [Google Scholar] [CrossRef] [PubMed]
- Tomato News. The Global Tomato Processing Industry. 2018. Available online: https://www.tomatonews.com/en/background_47.html (accessed on 1 May 2023).
- Zekeya, N.; Chacha, M.; Ndakidemi, P.; Materu, C.; Chidege, M.; Mbega, E. Tomato Leafminer (Tuta absoluta Meyrick 1917): A Threat to Tomato Production in Africa. J. Agric. Ecol. Res. Int. 2017, 10, 1–10. [Google Scholar] [CrossRef]
- Urbaneja, A.; Vercher, R.; Navarro, V.; Marí, F.G.; Porcuna, J.L. La polilla del tomate, Tuta absoluta. Phytoma España 2007, 194, 16–23. [Google Scholar]
- Chidege, M.; Al-zaidi, S.; Hassan, N.; Julie, A.; Kaaya, E.; Mrogoro, S. First record of tomato leaf miner Tuta absoluta (Meyrick) (Lepidoptera: Gelechiidae) in Tanzania. Agric. Food Secur. 2016, 5, 17. [Google Scholar] [CrossRef]
- Guimapi, R.Y.; Mohamed, S.A.; Okeyo, G.O.; Ndjomatchoua, F.T.; Ekesi, S.; Tonnang, H.E. Modeling the risk of invasion and spread of Tuta absoluta in Africa. Ecol. Complex. 2016, 28, 77–93. [Google Scholar] [CrossRef]
- Guedes, R.N.C.; Picanço, M.C. The tomato boreri Tuta absoluta/iin South America: Pest status, management and insecticide resistance. EPPO Bull. 2012, 42, 211–216. [Google Scholar] [CrossRef]
- Zahedi, S.R.; Zahedi, S.M. Role of Information and Communication Technologies in modern agriculture. Int. J. Agric. Crop Sci. 2012, 4, 1725–1728. [Google Scholar]
- Singh, A.; Ganapathysubramanian, B.; Singh, A.K.; Sarkar, S. Machine Learning for High-Throughput Stress Phenotyping in Plants. Trends Plant Sci. 2016, 21, 110–124. [Google Scholar] [CrossRef]
- Giakoumoglou, N.; Pechlivani, E.M.; Katsoulas, N.; Tzovaras, D. White Flies and Black Aphids Detection in Field Vegetable Crops using Deep Learning. In Proceedings of the 2022 IEEE 5th International Conference on Image Processing Applications and Systems (IPAS), Genova, Italy, 5–7 December 2022; Volume 5, pp. 1–6. [Google Scholar] [CrossRef]
- Giakoumoglou, N.; Pechlivani, E.M.; Sakelliou, A.; Klaridopoulos, C.; Frangakis, N.; Tzovaras, D. Deep learning-based multi-spectral identification of grey mould. Smart Agric. Technol. 2023, 4, 100174. [Google Scholar] [CrossRef]
- Giakoumoglou, N.; Pechlivani, E.M.; Tzovaras, D. Generate-Paste-Blend-Detect: Synthetic Dataset for Object Detection in the Agriculture Domain. Smart Agric. Technol. 2023, 5, 100258. [Google Scholar] [CrossRef]
- Wang, Q.; Qi, F.; Sun, M.; Qu, J.; Xue, J. Identification of Tomato Disease Types and Detection of Infected Areas Based on Deep Convolutional Neural Networks and Object Detection Techniques. Comput. Intell. Neurosci. 2019, 2019, 9142753. [Google Scholar] [CrossRef] [PubMed]
- Wang, X.; Liu, J.; Liu, G. Diseases Detection of Occlusion and Overlapping Tomato Leaves Based on Deep Learning. Front. Plant Sci. 2021, 12, 792244. [Google Scholar] [CrossRef]
- Fuentes, A.; Yoon, S.; Kim, S.; Park, D. A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition. Sensors 2017, 17, 2022. [Google Scholar] [CrossRef]
- Zaborowicz, M.; Boniecki, P.; Koszela, K.; Przybylak, A.; Przybył, J. Application of neural image analysis in evaluating the quality of greenhouse tomatoes. Sci. Hortic. 2017, 218, 222–229. [Google Scholar] [CrossRef]
- Zaborowicz, M.; Boniecki, P.; Koszela, K.; Przybył, J.; Mazur, R.; Kujawa, S.; Pilarski, K. Use of artificial neural networks in the identification and classification of tomatoes. In Proceedings of the SPIE Proceedings, Beijing, China, 21–22 April 2013. [Google Scholar] [CrossRef]
- Brahimi, M.; Boukhalfa, K.; Moussaoui, A. Deep Learning for Tomato Diseases: Classification and Symptoms Visualization. Appl. Artif. Intell. 2017, 31, 299–315. [Google Scholar] [CrossRef]
- Ferentinos, K.P. Deep learning models for plant disease detection and diagnosis. Comput. Electron. Agric. 2018, 145, 311–318. [Google Scholar] [CrossRef]
- Liang, Q.; Xiang, S.; Hu, Y.; Coppola, G.; Zhang, D.; Sun, W. PD2SE-Net: Computer-assisted plant disease diagnosis and severity estimation network. Comput. Electron. Agric. 2019, 157, 518–529. [Google Scholar] [CrossRef]
- Rangarajan, A.K.; Purushothaman, R.; Ramesh, A. Tomato crop disease classification using pre-trained deep learning algorithm. Procedia Comput. Sci. 2018, 133, 1040–1047. [Google Scholar] [CrossRef]
- Trivedi, N.K.; Gautam, V.; Anand, A.; Aljahdali, H.M.; Villar, S.G.; Anand, D.; Goyal, N.; Kadry, S. Early Detection and Classification of Tomato Leaf Disease Using High-Performance Deep Neural Network. Sensors 2021, 21, 7987. [Google Scholar] [CrossRef]
- Loyani, L.K.; Bradshaw, K.; Machuve, D. Segmentation of Tuta absoluta’s Damage on Tomato Plants: A Computer Vision Approach. Appl. Artif. Intell. 2021, 35, 1107–1127. [Google Scholar] [CrossRef]
- Georgantopoulos, P.; Papadimitriou, D.; Constantinopoulos, C.; Manios, T.; Daliakopoulos, I.; Kosmopoulos, D. A Multispectral Dataset for the Detection of Tuta absoluta and Leveillula Taurica in Tomato Plants. Smart Agric. Technol. 2023, 4, 100146. [Google Scholar] [CrossRef]
- Rubanga, D.P.; Loyani, L.K.; Richard, M.; Shimada, S. A Deep Learning Approach for Determining Effects of Tuta absoluta in Tomato Plants. arXiv 2020, arXiv:2004.04023. [Google Scholar]
- Mkonyi, L.; Rubanga, D.; Richard, M.; Zekeya, N.; Sawahiko, S.; Maiseli, B.; Machuve, D. Early identification of Tuta absoluta in tomato plants using deep learning. Sci. Afr. 2020, 10, e00590. [Google Scholar] [CrossRef]
- Tsiakas, K.; Papadimitriou, A.; Pechlivani, E.M.; Giakoumis, D.; Frangakis, N.; Gasteratos, A.; Tzovaras, D. An Autonomous Navigation Framework for Holonomic Mobile Robots in Confined Agricultural Environments. Robotics 2023, 12, 146. [Google Scholar] [CrossRef]
- Pechlivani, E.M.; Gkogkos, G.; Giakoumoglou, N.; Hadjigeorgiou, I.; Tzovaras, D. Towards Sustainable Farming: A Robust Decision Support System’s Architecture for Agriculture 4.0. In Proceedings of the 2023 24th International Conference on Digital Signal Processing (DSP), Rhodes, Greece, 11–13 June 2023. [Google Scholar] [CrossRef]
- Ren, S.; He, K.; Girshick, R.; Sun, J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv 2015, arXiv:1506.01497. [Google Scholar] [CrossRef] [PubMed]
- Lin, T.; Goyal, P.; Girshick, R.B.; He, K.; Dollár, P. Focal Loss for Dense Object Detection. arXiv 2017, arXiv:1708.02002. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. arXiv 2015, arXiv:1512.03385. [Google Scholar]
- Lin, T.; Dollár, P.; Girshick, R.B.; He, K.; Hariharan, B.; Belongie, S.J. Feature Pyramid Networks for Object Detection. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Bodla, N.; Singh, B.; Chellappa, R.; Davis, L.S. Soft-NMS—Improving Object Detection With One Line of Code. arXiv 2017, arXiv:cs.CV/1704.04503. [Google Scholar]
- Zhou, H.; Li, Z.; Ning, C.; Tang, J. CAD: Scale Invariant Framework for Real-Time Object Detection. In Proceedings of the 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, Italy, 22–29 October 2017; pp. 760–768. [Google Scholar] [CrossRef]
- Solovyev, R.; Wang, W.; Gabruseva, T. Weighted boxes fusion: Ensembling boxes from different object detection models. Image Vis. Comput. 2021, 107, 104117. [Google Scholar] [CrossRef]
- Mohammed, A.; Kora, R. A comprehensive review on ensemble deep learning: Opportunities and challenges. J. King Saud Univ. Comput. Inf. Sci. 2023, 35, 757–774. [Google Scholar] [CrossRef]
- Lin, T.Y.; Maire, M.; Belongie, S.; Bourdev, L.; Girshick, R.; Hays, J.; Perona, P.; Ramanan, D.; Zitnick, C.L.; Dollár, P. Microsoft COCO: Common Objects in Context. arXiv 2014, arXiv:1405.0312. [Google Scholar]
- Pizer, S.; Johnston, R.; Ericksen, J.; Yankaskas, B.; Muller, K. Contrast-limited adaptive histogram equalization: Speed and effectiveness. In Proceedings of the 1990 First Conference on Visualization in Biomedical Computing, Atlanta, GA, USA, 22–25 May 1990. [Google Scholar] [CrossRef]
- Wu, Y.; Kirillov, A.; Massa, F.; Lo, W.Y.; Girshick, R. Detectron2. 2019. Available online: https://github.com/facebookresearch/detectron2 (accessed on 1 May 2023).
- Paszke, A.; Gross, S.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L.; et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32; Curran Associates, Inc.: Red Hook, NY, USA, 2019; pp. 8024–8035. [Google Scholar]
- Gong, Z.; Zhong, P.; Hu, W. Diversity in Machine Learning. IEEE Access 2019, 7, 64323–64350. [Google Scholar] [CrossRef]
- Patrício, D.I.; Rieder, R. Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review. Comput. Electron. Agric. 2018, 153, 69–81. [Google Scholar] [CrossRef]
- Sagi, O.; Rokach, L. Ensemble learning: A survey. WIREs 2018, 8, e1249. [Google Scholar] [CrossRef]
- Jocher, G.; Chaurasia, A.; Qiu, J. YOLO by Ultralytics. 2023. Available online: https://github.com/ultralytics/ultralytics (accessed on 1 May 2023).
Model | Backbone | Head | Inference Time | |
---|---|---|---|---|
Faster R-CNN | ResNet-101 | C4 | 0.56 | 0.139 |
Faster R-CNN | ResNet-101 | DC5 | 0.58 | 0.086 |
Faster R-CNN | ResNet-101 | FPN | 0.56 | 0.051 |
Faster R-CNN | ResNet-50 | C4 | 0.58 | 0.103 |
Faster R-CNN | ResNet-50 | DC5 | 0.58 | 0.069 |
Faster R-CNN | ResNet-50 | FPN | 0.55 | 0.038 |
Faster R-CNN | ResNeXt-101 | FPN | 0.56 | 0.098 |
RetinaNet | ResNet-101 | FPN | 0.57 | 0.054 |
RetinaNet | ResNet-50 | FPN | 0.57 | 0.041 |
Ensemble Configuration | WBF | NMW | Soft NMS | NMS |
---|---|---|---|---|
All models | 0.70 | 0.66 | 0.63 | 0.61 |
All Faster R-CNN | 0.69 | 0.66 | 0.63 | 0.61 |
All RetinaNet | 0.64 | 0.63 | 0.60 | 0.59 |
All Faster R-CNN ResNet-101 | 0.64 | 0.62 | 0.60 | 0.59 |
All Faster R-CNN ResNet-50 | 0.67 | 0.64 | 0.61 | 0.60 |
All Faster R-CNN C4 | 0.63 | 0.61 | 0.60 | 0.59 |
All Faster R-CNN DC5 | 0.63 | 0.62 | 0.60 | 0.60 |
All Faster R-CNN FPN | 0.61 | 0.60 | 0.58 | 0.56 |
Model | Depth | Width | Recall | Precision | |
---|---|---|---|---|---|
YOLOv8n | 0.33 | 0.25 | 0.55 | 0.53 | 0.60 |
YOLOv8s | 0.33 | 0.50 | 0.57 | 0.55 | 0.61 |
YOLOv8m | 0.67 | 0.75 | 0.58 | 0.54 | 0.61 |
YOLOv8l | 1.00 | 1.00 | 0.58 | 0.57 | 0.62 |
YOLOv8x | 1.00 | 1.25 | 0.58 | 0.54 | 0.65 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 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
Giakoumoglou, N.; Pechlivani, E.-M.; Frangakis, N.; Tzovaras, D. Enhancing Tuta absoluta Detection on Tomato Plants: Ensemble Techniques and Deep Learning. AI 2023, 4, 996-1009. https://doi.org/10.3390/ai4040050
Giakoumoglou N, Pechlivani E-M, Frangakis N, Tzovaras D. Enhancing Tuta absoluta Detection on Tomato Plants: Ensemble Techniques and Deep Learning. AI. 2023; 4(4):996-1009. https://doi.org/10.3390/ai4040050
Chicago/Turabian StyleGiakoumoglou, Nikolaos, Eleftheria-Maria Pechlivani, Nikolaos Frangakis, and Dimitrios Tzovaras. 2023. "Enhancing Tuta absoluta Detection on Tomato Plants: Ensemble Techniques and Deep Learning" AI 4, no. 4: 996-1009. https://doi.org/10.3390/ai4040050