Indian Journal of Agricultural Research

Indian Journal of Agricultural Research cover
Volume 60 · Issue 9 · 2026/07/25

A Novel AI-Driven Approach for Synthetic Data Generation in Camouflaged Insect and Pest Detection

Muralidhar Rao Lokerao
K. Basava Raju
191 Views

Submitted

2026/06/22

First Online

2026/07/25

doi

10.18805/IJARe.A-6613

Cite article - Muralidhar Rao Lokerao, K. Basava Raju. (2026). A Novel AI-Driven Approach for Synthetic Data Generation in Camouflaged Insect and Pest Detection. Indian Journal of Agricultural Research. 60(9): 1450–1457. doi: 10.18805/IJARe.A-6613

Abstract

Background: Data scarcity of agricultural computer vision data in the area of Camouflaged insect and pest detection remains a challenging problem, despite recent advancements in Camouflaged Object Detection (COD) and transformer based architectures. To address this problem, we introduced a novel AI-driven synthetic image generation methodology that leverages computer vision models, Large Language Models(LLMs) and Generative AI to create challenging synthetic camouflaged images of insects and pests. This synthetic data helps enhance the generalisation capabilities of COD models.

Methods: The proposed methodology includes an iterative process involving multiple AI agents performing (1) extraction of pest-crop knowledge using LLMs, (2) collecting pest and plant images in an automated way, (3) separating out the foreground pest from background, (4) generating synthetic images with varied camouflage parameters, (5) evaluating using existing detection models. (6) incorporating images that are not detected into the training dataset, enabling iterative dataset enhancement (7) retraining the model. This approach accelerates the development of intelligent, sustainable and scalable agri-tech solutions by providing critical training data that is inexhaustible and relevant.

Result: We have experimentally validated the proposed iterative methodology on the detection accuracy for camouflaged hornworm pests on tomato plants. In our ablation studies, we have seen that the baseline mAP50 for models trained on web-scraped images was 0.170 when tested with camouflaged images, whereas the models trained with images generated using our methodology have shown a mAP50 value of 0.931 when tested with the same set of camouflaged images. Using the Gradient-weighted Class Activation Mapping (Grad-CAM), we provided evidence on how the iterative blending process in our methodology is able to regularise the model and focus on the biological anatomy and texture of the pests instead of just the edges and boundaries, proving that the methodology not only solves the data scarcity of camouflaged pest images but also improves the robustness of models in complex environments.

References

  1. Bappy, M.A. (2024). AI-powered background removal for enhancing image processing in digital applications. ResearchGate. Dalal, M. and Mittal, P. (2025). A systematic review of deep learning- based object detection in agriculture: Methods, challenges and future directions. Computers, Materials and Continua . 84(1): 57-91. Dwibedi, D., Misra, I. and Hebert, M. (2017). Cut, paste and learn: Surprisingly easy synthesis for instance detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV): 1310-1319. Gao, A., Dong, Y., Liu, D., Li, A., Lin, Z. and Li, Y. (2025). SSHFormer: Optimizing spectral reconstruction with a spatial-spectral hybrid transformer. Remote Sensing. 17(9): 1585. Gao, S., Feng, Y., Wang, Q., Hong, L., Zhou, X., Fei, L., Wang, Y. and Zhang, W. (2025). MSVCOD: A large-scale multi- scene dataset for video camouflage object detection. arXiv Preprint arXiv: 2502.13859. Geirhos, R., Jacobsen, J.H., Michaelis, C. et al. (2020). Shortcut learning in deep neural networks. Nature Machine Intelligence . 2: 665-673. Giakoumoglou, N., Pechlivani, E.M. and Tzovaras, D. (2023). Generate- Paste-Blend-Detect: Synthetic dataset for object detection in the agriculture domain. Smart Agricultural Technology . 5: 100258. Hao, C., Yu, Z., Liu, X., Xu, J., Yue, H. and Yang, J. (2024). A simple yet effective network based on vision transformer for camouflaged object and salient object detection. ArXiv preprint arXiv: 2402.18922. Hupel, M. and Stütz, P. (2025). Optimized spectral indices for camouflage detection in multispectral imagery. Journal of Applied Remote Sensing . 62(1): doi: 10.1080/1548 1603.2025.2508574 Kappali, R.H., Sadyojatha, K.M. and Prashanthi, S.K. (2024). Computer vision and machine learning in paddy diseases identification and classification: A review. Indian Journal of Agricultural Research . 58(2): 183-187. doi: 10.18805/IJARe.A-6061 . Mehta, R.A., Kumar, P., Prem, G., Aggarwal, S. and Kumar, R. (2025). Leveraging artificial intelligence for disease diagnosis in agricultural crops: A review. Indian Journal of Agricultural Research. 59(5): 681-690. doi: 10.18805/IJARe.A-6363. Mondal, A. (2020). Camouflaged object detection and tracking: A survey. International Journal of Image and Graphics . 20(4): 2050028. Ruan, J., Yuan, W., Lin, Z., Liao, N., Li, Z., Xiong, F., Liu, T. and Fu, Y. (2025). MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object Scenarios. AAAI Publications. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D. and Batra, D. (2017). Grad-CAM: visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV): pp 618-626. Sharma, A. and Kumar, A. (2026). Dual-encoder variational auto encoder for detection and classification of plant leaf diseases. Indian Journal of Agricultural Research . 60(6): 912-918. doi: 10.18805/IJARe.A-6451. Shoaib, M., Sadeghi-Niaraki, A., Ali, F., Hussain, I. and Khalid, S. (2025). Leveraging deep learning for plant disease and pest detection: A comprehensive review and future directions. Frontiers in Plant Science . 16: 1538163. Tang, K., Qian, Y., Dong, H., Huang, Y., Lu, Y., Tuerxun, P. and Li, Q. (2025). SP-YOLO: A Real-Time and efficient multi- scale model for pest detection in sugar beet fields. Insects . 16(1): 102. Tang, L., Jiang, P.T., Shen, Z.H., Zhang, H., Chen, J.W. and Li, B. (2024). Chain of visual perception: Harnessing multimodal large language models for zero-shot camouflaged object detection. Proceedings of the 32 nd ACM International Conference on Multimedia: pp 8805-8814. Truong, T.D., Hoang-Quan, N., Xuan-Bac, N., Ashley, D., Xin, L., Khoa, L. (2025). Insect-foundation: A foundation model and large multimodal dataset for vision-language insect understanding. arXiv preprint arXiv: 2502.09906. Wang, J., Hong, M., Hu, X., Li, X., Huang, S., Wang, R. and Zhang, F. (2023). Camouflaged insect segmentation using a progressive refinement network. Electronics . 12(4): 804. Yin, B., Zhang, X., Hou, Q., Sun, B., Fan, D. and Gool, L.V. (2022). CamoFormer: Masked separable attention for camouflaged object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence . 46: 10362-10374.
EDITORIAL BOARD

Guided by Experienced Academic Leadership

Distinguished scholars and subject experts committed to editorial excellence, scientific integrity and rigorous peer review.

View Full Board
V. Geethalakshmi
Chief Editor

V. Geethalakshmi

Ex-Vice ChancellorTamil Nadu Agricultural University Coimbatore, INDIA

R. Sarada Jaya Lakshmi
Associate chief editor

R. Sarada Jaya Lakshmi

Ex-Vice ChancellorCoordinator, DAATTC Kurnool, Acharya N.G. Ranga Agricultural University, Andhra Pradesh, INDIA

Neetu Sharma
Editor

Neetu Sharma

ProfessorSher-e-Kashmir University of Agricultural Sciences & Technology of Jammu and Kashmir, INDIA

S. Alarmelu
Editor

S. Alarmelu

Principal ScientistICAR-Sugarcane Breeding Institute, Coimbatore, Tamil Nadu, INDIA.