Skip to content
2000
Volume 19, Issue 2
  • ISSN: 2666-2558
  • E-ISSN: 2666-2566

Abstract

Background

Pest detection plays a crucial role in smart agriculture; it is one of the primary factors that significantly impact crop yield and quality.

Objective

In actual field environments, pests often appear as dense and small objects, which pose a great challenge to field pest detection. Therefore, this paper addresses the problem of dense small pest detection.

Methods

We combine a pyramid vision transformer and prime sample attention (named PVT-PSA) to design an effective pest detection model. Firstly, a pyramid vision transformer is adopted to extract pest feature information. Pyramid vision transformer fuses multi-scale pest features through pyramid structure and can capture context information of small pests, which is conducive to the feature expression of small pests. Then, we design prime sample attention to guide the selection of pest samples in the model training process to alleviate the occlusion effect between dense pests and enhance the overall pest detection accuracy.

Results

The effectiveness of each module is verified by the ablation experiment. According to the comparison experiment, the detection and inference performance of the PVT-PSA is better than the other eleven detectors in field pest detection. Finally, we deploy the PVT- PSA model on a terrestrial robot based on the Jetson TX2 motherboard for field pest detection.

Conclusion

The pyramid vision transformer is utilized to extract relevant features of pests. Additionally, prime sample attention is employed to identify key samples that aid in effectively training the pest detection models. The model deployment further demonstrates the practicality and effectiveness of our proposed approach in smart agriculture applications.

© 2026 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/rascs/10.2174/0126662558345887241127062525
2024-12-10
2026-01-02

  • From This Site

    /content/journals/rascs/10.2174/0126662558345887241127062525
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. OikonomidisA. CatalC. KassahunA. Deep learning for crop yield prediction: A systematic literature review.N. Z. J. Crop Hortic. Sci.202351112610.1080/01140671.2022.2032213
     [Google Scholar]
  2. JiaF. LuoS. YinG. YeY. A novel variant of the salp swarm algorithm for engineering optimization.J. Artif. Intell. Soft Comput. Res.202313313114910.2478/jaiscr‑2023‑0011
     [Google Scholar]
  3. Al-MekhlafiZ.G. Al-ShareedaM.A. ManickamS. MohammedB.A. AlreshidiA. AlazmiM. AlshudukhiJ.S. AlsaffarM. AlsewariA. Chebyshev polynomial-based fog computing scheme supporting pseudonym revocation for 5G-enabled vehicular networks.Electronics202312487210.3390/electronics12040872
     [Google Scholar]
  4. Al-MekhlafiZ.G. Al-ShareedaM.A. ManickamS. MohammedB.A. QtaishA. Lattice-based lightweight quantum resistant scheme in 5g-enabled vehicular networks.Mathematics202311239910.3390/math11020399
     [Google Scholar]
  5. MohammedB.A. Al-ShareedaM.A. ManickamS. FC-PA: Fog computing-based pseudonym authentication scheme in 5G-enabled vehicular networks.IEEE Access202311185711858110.1109/ACCESS.2023.3247222
     [Google Scholar]
  6. Al-ShareedaM.A. ManickamS. COVID-19 vehicle based on an efficient mutual authentication scheme for 5G-enabled vehicular fog computing.Int. J. Environ. Res. Public Health202219231561810.3390/ijerph19231561836497709
     [Google Scholar]
  7. DaiM. DorjoyM.M.H. MiaoH. ZhangS. A new pest detection method based on improved YOLOv5m.Insects20231415410.3390/insects1401005436661982
     [Google Scholar]
  8. WangX. DuJ. XieC. WuS. MaX. LiuK. DongS. ChenT. Prior knowledge auxiliary for few-shot pest detection in the wild.Front. Plant Sci.202313103354410.3389/fpls.2022.103354436777532
     [Google Scholar]
  9. WangX. ZhangS. WangX. XuC. Crop pest detection by three-scale convolutional neural network with attention.PLoS One2023186e027645610.1371/journal.pone.027645637267397
     [Google Scholar]
  10. GaoT. WushouerM. TuerhongG. Dms-YOLOv5: A decoupled multi-scale YOLOv5 method for small object detection.Applied Sci.20231310612410.3390/app13106124
     [Google Scholar]
  11. QuJ. TangZ. ZhangL. ZhangY. ZhangZ. Remote sensing small object detection network based on attention mechanism and multi-scale feature fusion.Remote Sens.20231511272810.3390/rs15112728
     [Google Scholar]
  12. LiuW. ZhouB. WangZ. YuG. YangS. Fppnet: A fixed- perspective-perception module for small object detection based on background difference.IEEE Sens. J.20232310110571106910.1109/JSEN.2023.3263539
     [Google Scholar]
  13. LiX. LvC. WangW. LiG. YangL. YangJ. Generalized focal loss: Towards efficient representation learning for dense object detection.IEEE Trans. Pattern Anal. Mach. Intell.20234533139315335679384
     [Google Scholar]
  14. ZhuC. LiangJ. ZhouF. Transfer learning-based YOLOv3 model for road dense object detection.Information2023141056010.3390/info14100560
     [Google Scholar]
  15. GaoZ. Yoloca: Center aware yolo for dense object detection.J. Phys. Conf. Ser.20232425101201910.1088/1742‑6596/2425/1/012019
     [Google Scholar]
  16. WangR. LiuL. XieC. YangP. LiR. ZhouM. Agripest: A large-scale domain-specific benchmark dataset for practical agri- cultural pest detection in the wild.Sensors2021215160110.3390/s2105160133668820
     [Google Scholar]
  17. ZouZ. ChenK. ShiZ. GuoY. YeJ. Object detection in 20 years: A survey.Proc. IEEE2023111325727610.1109/JPROC.2023.3238524
     [Google Scholar]
  18. WangW. XieE. LiX. FanD-P. SongK. LiangD. LuT. LuoP. ShaoL. Pyramid vision transformer: A versatile backbone for dense prediction without convolutionsInternational Conference on Computer VisionMontreal, QC, Canada202154855810.1109/ICCV48922.2021.00061
     [Google Scholar]
  19. HendersonP. FerrariV. End-to-end training of object class detectors for mean average precision13th Asian Conference on Computer VisionTaipei, Taiwan2016198213
     [Google Scholar]
  20. LiuS. QiL. QinH. ShiJ. JiaJ. Path aggregation network for instance segmentationConference on Computer Vision and Pattern RecognitionSalt Lake City, UT, USA201887598768
     [Google Scholar]
  21. WangJ. ChenK. XuR. LiuZ. LoyC.C. LinD. Carafe: Content-aware reassembly of featuresIEEE/CVF International Conference on Computer VisionSeoul, Korea (South)201930073016.
     [Google Scholar]
  22. ZhangH. WangY. DayoubF. SunderhaufN. Varifocalnet: An iou-aware dense object detectorIEEE/CVF Conference on Computer Vision and Pattern RecognitionUnited States of America202185108519
     [Google Scholar]
  23. ZhuB. WangJ. JiangZ. ZongF. LiuS. LiZ. SunJ. Au- toassign: Differentiable label assignment for dense object detectionarXiv2020
     [Google Scholar]
  24. LinT-Y. GoyalP. GirshickR. HeK. Dolla’rP. Focal loss for dense object detectionIEEE International Conference on Computer VisionVenice, Italy201729993007.
     [Google Scholar]
  25. TianZ. ShenC. ChenH. HeT. FCOS: Fully convolutional one- stage object detectionIEEE/CVF International Conference on Computer Vision (ICCV)Seoul, Korea (South)20199626963510.1109/ICCV.2019.00972
     [Google Scholar]
  26. LiuZ. LinY. CaoY. HuH. WeiY. ZhangZ. LinS. GuoB. SWIN transformer: Hierarchical vision transformer using shifted windowsIEEE/CVF International Conference on Computer VisionMontreal, QC, Canada202199921000210.1109/ICCV48922.2021.00986
     [Google Scholar]
  27. LyuC. ZhangW. HuangH. ZhouY. WangY. LiuY. ZhangS. ChenK. RTMDet: An empirical study of designing real-time object detectorsarXiv2022
     [Google Scholar]
  28. LiuS. LiF. ZhangH. YangX. QiX. SuH. ZhuJ. ZhangL. DAB-DETR: Dynamic anchor boxes are better queries for DETRarXiv2022
     [Google Scholar]
  29. ZhangS. WangX. WangJ. PangJ. LyuC. ZhangW. LuoP. ChenK. Dense distinct query for end-to-end object detectionIEEE/CVF Conference on Computer Vision and Pattern RecognitionVancouver, BC, Canada20237329733810.1109/CVPR52729.2023.00708
     [Google Scholar]
  30. ZhangH. LiF. LiuS. ZhangL. SuH. ZhuJ. NiL.M. ShumH-Y. Dino: Detr with improved denoising anchor boxes for end-to-end object detectionarXiv2023
     [Google Scholar]
/content/journals/rascs/10.2174/0126662558345887241127062525
Loading
Field Pest Detection via Pyramid Vision Transformer and Prime Sample Attention
Recent Advances in Computer Science and Communications 19, E26662558345887 (2026); https://doi.org/10.2174/0126662558345887241127062525
/content/journals/rascs/10.2174/0126662558345887241127062525
/content/journals/rascs/10.2174/0126662558345887241127062525
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): attention mechanism; deep learning; destruction of plant tissues; pest detection; Smart agriculture; vision transformer

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test