Search

Menu
Search
in Ecology

Enhanced YOLO12 with spatial pyramid pooling for real-time cotton insect detection

122 Views


Abstract

Effective insect detection is crucial for sustainable cotton production, yet traditional monitoring methods remain labor-intensive, inefficient, and environmentally detrimental. This study introduces Enhanced YOLO12, a novel deep learning architecture for real-time cotton insect detection. Building on the YOLO12 framework, the proposed model integrates an optimized Spatial Pyramid Pooling (SPP) module and attention-based feature extraction to improve detection accuracy while maintaining computational efficiency. To ensure robustness, we developed and evaluated multiple baseline models (standard YOLO11 and YOLO12) and custom architectures (YOLO12_Fusion, YOLO11-BRA-Net, YOLO11_CBAM, and Enhanced Hybrid YOLO12). According to the conducted experiments, Enhanced Hybrid YOLO12 achieved the best performance, achieving 0.942, 0.876, 0.945, and 0.735 in precision, recall, mAP50 and mAP50-95, respectively. It significantly outstands the results of the standard YOLO12 (0.925, 0.848, of 0.913, and 0.662). These results demonstrate that Enhanced Hybrid YOLO12 can be considered as a state-of-the-art framework for precision agriculture, with its high detection accuracy and real-time capability. Therefore, they encourage this deep learning model in pest management applications.

Data availability

The dataset is publicly available and can be accessed at the following link: [https://www.scidb.cn/en/detail? dataSetId=3f36bce8e41849a6a33e34fb0f8ae581](https:/www.scidb.cn/en/detail? dataSetId=3f36bce8e41849a6a33e34fb0f8ae581).

Code availability

The custom code used in this study to generate and analyse the results is publicly available in a GitHub repository at https://github.com/DrDinaSaif/Enhanced-YOLO-12.

Abbreviations

A2C2F:

Attention mechanism with C2F block

AI:

Artificial intelligence

AELGNet:

Attention-based enhanced local and global features network

BERT-ResNet-PSO:

Bidirectional encoder representations from transformers-residual network-particle swarm optimization

BiFormerAF:

BiFormer attention fusion

BRA:

Bi-level routing attention

C2F:

Cross stage partial bottleneck with 2 convolutional layers

C2PSA:

Convolutional block with parallel spatial attention

C3K:

Conv ×3 with kernel

C3K2:

Conv ×3 with kernel size 2

CAM:

Channel attention module

CBAM:

Convolutional block attention module

CFNet-VoVGCSP-LSKNet-YOLOv8s:

Cross-feature network- VoVNet with ghost convolutional structure and spatial pyramid- large kernel attention network- you only look once version 8

CNN:

Convolutional neural network

COLAB:

Google collaboratory

C2PSA:

Cross-stage partial self-attention

CSP:

Cross stage partial

DenseNet121:

Densely connected convolutional network with 121 layers

DL:

Deep learning

ECENet:

EfficientNet model

InceptionResNetV2:

Inception residual network version 2

F-measure:

Fisher score-measure

FLOPS:

Floating point operations per second

FM:

Feature map

FM-SR:

Feature map-super resolution

FN:

False negative

FP:

False positive

GCSP:

Ghost CSP

GFLOPS:

Giga floating-point operations per second

mAP:

Mean average precision

ML:

Machine learning

MSP2P:

Multi-scale patch-to-patch

ResNet50:

Residual network with 50 layers

SAM:

Spatial attention module

SPPF:

Spatial pyramid pooling fast

SpemNet:

Stacking patch embedding network

SRNet-YOLO:

Super-resolution network-you only look once

TN:

True negative

TP:

True positive

TXT:

Text format

ViT:

Vision transformer

VGG16:

Visual geometry group neural network with 16 layers

XML:

Extensible markup language

YOLO:

You only look once

YOLOv8-MDN-Tiny:

YOLO version 8 with mixed density network-tiny

YOLO11:

YOLO version 11

YOLO11-BRA-Net:

YOLO11 with bi-level routing attention network

YOLO11_CBAM:

YOLO11 with convolutional block attention module

YOLO12:

YOLO version 12

YOLO12_Fusion:

YOLO12_Fusion

References

  1. Benjamin, J. et al. Cereal production in Africa: The threat of certain pests and weeds in a changing climate—A review. Agric. Food Secur. 13 (1), 18 (2024).

    Google Scholar 

  2. Askr, H., Moawad, M., Darwish, A. & Hassanien, A. E. Multiclass deep learning model for predicting lung diseases based on honey Badger algorithm. Int. J. Inform. Technol. 17 (2), 1147–1154 (2025).

    Google Scholar 

  3. Askr, H., Hssanien, A. E. & Darwish, A. Prediction of climate change impact based on air flight CO2 emissions using machine learning: towards green air flights. In The Power of Data: Driving Climate Change with Data Science and Artificial Intelligence Innovations. 27–37 (Springer, 2023).

  4. Farrag, T. A., Askr, H., Elhosseini, M. A., Hassanien, A. E. & Farag, M. A. Intelligent parcel delivery scheduling using truck-drones to cut down time and cost. Drones 8(9), 477 (2024).

  5. Askr, H., Gomaa, M. M., Rizk-Allah, R. M., Snasel, V. & Hassanien, A. E. Prediction of methane emission and electricity generation from landfills: Deep learning approach. Energy Rep. 12, 5462–5472 (2024).

    Google Scholar 

  6. Askr, H., El-dosuky, M., Darwish, A. & Hassanien, A. E. Explainable ResNet50 learning model based on copula entropy for cotton plant disease prediction. Appl. Soft Comput. 164, 112009 (2024).

    Google Scholar 

  7. Wang, J., Chen, Y., Huang, J., Jiang, X. & Wan, K. Leveraging machine learning for advancing insect pest control: A bibliometric analysis. J. Appl. Entomol. 149 (3), 293–308 (2025).

    Google Scholar 

  8. Moussa, F., Askr, H. & Hassanien, A. E. Coconut detection using deep learning: Towards sustainable, and renewable biodiesel production. In International Conference on Advanced Intelligent Systems and Informatics. 429–439. (Springer, 2025).

  9. Alves, A. N., Souza, W. S. & Borges, D. L. Cotton pests classification in field-based images using deep residual networks. Comput. Electron. Agric. 174, 105488 (2020).

    Google Scholar 

  10. Bai, M. et al. A point-based method for identification and counting of tiny object insects in cotton fields. Comput. Electron. Agric. 227, 109648 (2024).

    Google Scholar 

  11. Li, R. et al. Identification of cotton pest and disease based on CFNet-VoV-GCSP-LSKNet-YOLOv8s: A new era of precision agriculture. Front. Plant Sci. 15, 1348402 (2024).

    Google Scholar 

  12. Yang, S., Zhou, G., Feng, Y., Zhang, J. & Jia, Z. SRNet-YOLO: A model for detecting tiny and very tiny pests in cotton fields based on super-resolution reconstruction. Front. Plant Sci. 15, 1416940 (2024).

    Google Scholar 

  13. Liu, J., Sun, L., Zhou, G., Wang, J. & Xing, J. Sfce-Vt: Spatial Feature Fusion and Contrast-Enhanced Visual Transformer for Fine-Grained Agricultural Pests Visual Classification.

  14. Qiu, K. et al. SpemNet: A cotton disease and pest identification method based on efficient multi-scale attention and stacking patch embedding. Insects 15(9), 667 (2024).

  15. Sharma, S. & Vardhan, M. AELGNet: Attention-based enhanced local and global features network for medicinal leaf and plant classification. Comput. Biol. Med. 184, 109447 (2025).

    Google Scholar 

  16. Chen, D. et al. YOLOv8-MDN-Tiny: A lightweight model for multi-scale disease detection of postharvest golden passion fruit. Postharvest Biol. Technol. 219, 113281 (2025).

    Google Scholar 

  17. Dheeraj, A. & Chand, S. Deep learning based weed classification in corn using improved attention mechanism empowered by explainable AI techniques. Crop Prot. 190, 107058 (2025).

    Google Scholar 

  18. Chavan, P., Chavan, P. P. & Chavan, A. Hybrid architecture for crop detection and leaf disease detection with improved U-Net segmentation model and image processing. Crop Prot. 190, 107117 (2025).

    Google Scholar 

  19. Pavate, A. et al. Efficient model for cotton plant health monitoring via YOLO-based disease prediction. Indonesian J. Electr. Eng. Comput. Sci. 37 (1), 164–178 (2025).

    Google Scholar 

  20. Madhu, S. & RaviSankar, V. Comprehensive analysis of a YOLO-based deep learning model for cotton plant leaf disease detection. Eng. Technol. Appl. Sci. Res. 15 (1), 19947–19952 (2025).

    Google Scholar 

  21. Kumar, R. et al. Hybrid approach of cotton disease detection for enhanced crop health and yield. (IEEE Access, 2024).

  22. Singh, C., Wibowo, S. & Grandhi, A. P. S. A hybrid deep learning approach for cotton plant disease detection using Bert-Resnet-Pso. Available at SSRN 5113751.

  23. Ciccone, F. & Ceruti, A. Real-time search and rescue with drones: A deep learning approach for small-object detection based on YOLO. Drones 9(8), 514 (2025).

  24. Giri, K. J. SO-YOLOv8: A novel deep learning-based approach for small object detection with YOLO beyond COCO. Expert Syst. Appl. 280, 127447 (2025).

    Google Scholar 

  25. Zhang, H. et al. A transformer-based detection network for precision cistanche pest and disease management in smart agriculture. Plants 14(4), 499 (2025).

  26. Pushpa, B. & Rani, N. S. Dataset for Indian medicinal plant species analysis and recognition. Data Brief. 49, 109388 (2023).

    Google Scholar 

  27. Jiang, H. et al. CNN feature based graph convolutional network for weed and crop recognition in smart farming. Comput. Electron. Agric. 174, 105450 (2020).

    Google Scholar 

  28. Chavan, P., Chavan, P. P. & Chavan, A. Hybrid architecture for crop detection and leaf disease detection with improved U-Net segmentation model and image processing. Crop Protect. 107117 (2025).

  29. Plantvillage-dataset. https://www.kaggle.com/datasets/abdallahalide v/plantvillage-dataset. Accessed 2025 (2025).

  30. Plantvillage-dataset. Collected dataset. www.kaggle.com/datasets. Accessed 2025 (2025).

  31. Cotton leaf disease dataset. https://www.kaggle.com/datasets/seroshkarim/cotton-leaf-diseasedataset. Accessed 2025 (2025).

  32. Noon, S. K., Amjad, M., Qureshi, M. A. & Mannan, A. Computationally light deep learning framework to recognize cotton leaf diseases. J. Intell. Fuzzy Syst. 40 (6), 12383–12398 (2021).

    Google Scholar 

  33. Cotton-plant-disease. https://www.kaggle.com/datasets/dhamur/cotton-plant-disease/data. Accessed 2024 (2024).

  34. Zhu, P. et al. Visdrone-det2018: The vision meets drone object detection in image challenge results. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. (2018).

  35. Everingham, M. & Winn, J. The Pascal visual object classes challenge 2012 (voc2012) development kit. In Pattern Analysis, Statistical Modelling and Computational Learning, Technical Report. Vol. 8(5). 2–5 (2011).

  36. Shafik, W., Tufail, A., De Silva, L. C., A., R. A. & Apong, H. M. A lightweight deep learning model for multi-plant biotic stress classification and detection for sustainable agriculture. Sci. Rep. 15 (1), 12195 (2025).

    Google Scholar 

  37. Shafik, W. et al. A comprehensive dataset of agarwood tree (Aquilaria Malaccensis) leaf images for disease analysis in Brunei Darussalam. Data Brief 112227 (2025).

  38. https://doi.org/10.1016/j.compag.2020.105488 (2025). accessed 18-1-2025.

  39. Deserno, M. & Briassouli, A. Faster r-CNN and EfficientNet for accurate insect identification in a relabeled yellow sticky traps dataset. In 2021 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor). 209–214 (IEEE, 2021).

  40. Customized-cotton-diseasedataset. https:// www.kaggle.com/datasets/saeedazfar/customized-cotton-diseasedataset. Accessed 30 Jan 2025 (2025).

  41. Cotton-crop-disease-detection. https://www.kaggle.com/datasets/paridhijain02122001/ cotton-crop-disease-detection. Accessed 30 Jan 2025 (2025).

  42. Wah, C., Branson, S., Welinder, P., Perona, P. & Belongie, S. The caltech-ucsd birds-200-2011 dataset (2011).

  43. Wu, X., Zhan, C., Lai, Y. K., Cheng, M. M. & Yang, J. Ip102: A large-scale benchmark dataset for insect pest recognition. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8787–8796 (2019).

  44. Lei, W. C. & LiBo, L. A dataset of image-text cross-modal retrieval of Lycium barbarum pests in ningxia in 2020. Trans. Assoc. Comput. Linguist. 7 (2022).

  45. Yang, M., Chen, Y. & Li, Y. C. An image dataset for cotton field insect identification study. Sci. Data Bank (2023).

  46. Liu, C., Tao, Y., Liang, J., Li, K. & Chen, Y. Object detection based on YOLO network. In 2018 IEEE 4th Information Technology and Mechatronics Engineering Conference (ITOEC). 799–803. (IEEE, 2018).

  47. Zhuo, S. et al. SCL-YOLOv11: A lightweight object detection network for low-illumination environments. IEEE Access. 13, 47653–47662 (2025).

    Google Scholar 

  48. Pan, J., Xu, S., Cheng, Z. & Lian, S. C2F-YOLO: A coarse-to-fine object detection framework based on YOLO. In Proceedings of the 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning. 150–157 (2024).

  49. Alif, M. A. R. Yolov11 for vehicle detection: Advancements, performance, and applications in intelligent transportation systems. arXiv preprint arXiv:2410.22898 (2024).

  50. Khanam, R. & Hussain, M. Yolov11: An overview of the key architectural enhancements, arXiv preprint arXiv:2410.17725 (2024).

  51. Ji, Y. et al. Improved YOLO11 algorithm for insulator defect detection in power distribution lines. Electronics 14(6), 1201 (2025).

  52. Alkhammash, E. H. Multi-classification using YOLOv11 and hybrid YOLO11n-MobileNet models: A fire classes case study. Fire 8(1), 17 (2025).

  53. Tian, Y., Ye, Q. & Doermann, D. Yolov12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524 (2025).

  54. Kljucaric, L. & George, A. D. Deep learning inferencing with high-performance hardware accelerators. ACM Trans. Intell. Syst. Technol. 14 (4), 1–25 (2023).

    Google Scholar 

  55. Khan, T. et al. Machine learning (ML)-centric resource management in cloud computing: A review and future directions. J. Netw. Comput. Appl. 204, 103405 (2022).

    Google Scholar 

  56. Gao, Y. et al. Estimating GPU memory consumption of deep learning models. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 1342–1352 (2020).

  57. Najafabadi, M. M. et al. Deep learning applications and challenges in big data analytics. J. Big Data. 2, 1–21 (2015).

    Google Scholar 

  58. Sokolova, M. & Lapalme, G. A systematic analysis of performance measures for classification tasks. Inf. Process. Manag. 45 (4), 427–437 (2009).

    Google Scholar 

  59. Tharwat, A. Classification assessment methods. Appl. Comput. Inf. 17 (1), 168–192 (2021).

    Google Scholar 

  60. Phalke, S., Vaidya, Y. & Metkar, S. Big-O time complexity analysis of algorithm. In 2022 International Conference on Signal and Information Processing (IConSIP). 1–5. (IEEE, 2022).

Download references

Funding

Open access funding provided by The Science, Technology & Innovation Funding Authority (STDF) in cooperation with The Egyptian Knowledge Bank (EKB).

Author information

Authors and Affiliations

  1. Faculty of Artificial Intelligence, Delta University for Science and Technology, Gamasa, 35712, Egypt

    Dina Saif

  2. Faculty of Computers and Artificial Intelligence, University of Sadat City, Menoufia, Egypt

    Heba Askr

  3. Computer and Control Engineering Department, Faculty of Engineering, Tanta University, Tanta, Egypt

    Amany M. Sarhan

  4. Faculty of Engineering, Elsewedy University of Technology, 10th of Ramadan, Egypt

    Amany M. Sarhan

  5. Faculty of Computers and Artificial Intelligence, Cairo University, Cairo, Egypt

    Aboul Ella Hassanien

  6. Scientific Research School of Egypt (SRSEG), Giza, Egypt

    Dina Saif, Heba Askr, Amany M. Sarhan & Aboul Ella Hassanien

Authors

  1. Dina Saif
    View author publications

    Search author on:PubMed Google Scholar

  2. Heba Askr
    View author publications

    Search author on:PubMed Google Scholar

  3. Amany M. Sarhan
    View author publications

    Search author on:PubMed Google Scholar

  4. Aboul Ella Hassanien
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Aboul Ella Hassanein: Idea, Senior administration, Supervision, Validation and Writing – review and editing. Amany Sarhan: Supervision, Investigation, Writing- Reviewing and Validation. Dina Sief: Data curation, Investigation, Writing-results, Visualization and Software. Heba Askr: Methodology, Validation, Writing –original draft, and Writing – review and editing.

Corresponding author

Correspondence to
Dina Saif.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Reprints and permissions

About this article

Cite this article

Saif, D., Askr, H., Sarhan, A.M. et al. Enhanced YOLO12 with spatial pyramid pooling for real-time cotton insect detection.
Sci Rep (2026). https://doi.org/10.1038/s41598-026-35747-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41598-026-35747-4

Keywords

  • Cotton insect detection
  • YOLO12
  • Deep learning
  • Insect management
  • Object detection
  • Precision agriculture
  • Sustainability

Source: Ecology - nature.com

Assessment of saline-alkaline water quality and rice-crab co-culture improvement effects in the Songnen Plain

The adaptive nature of the foam proteome produced by Mahanarva spectabilis (Hemiptera: Cercopidae) when infesting forage grasses with different levels of antibiosis-type resistance

This portal is not a newspaper as it is updated without periodicity. It cannot be considered an editorial product pursuant to law n. 62 of 7.03.2001. The author of the portal is not responsible for the content of comments to posts, the content of the linked sites. Some texts or images included in this portal are taken from the internet and, therefore, considered to be in the public domain; if their publication is violated, the copyright will be promptly communicated via e-mail. They will be immediately removed.

Back to Top
Close