LW-PWDNet: a lightweight and cross-terrain adaptive framework for early pine wilt disease detection

Guardado en:
Bibliografiske detaljer
Udgivet i:Frontiers in Plant Science vol. 16 (Oct 2025), p. 1687742-1687766
Hovedforfatter: Hu, Yongkang
Andre forfattere: Wang, Fang
Udgivet:
Frontiers Media SA
Fag:
Online adgang:Citation/Abstract
Full Text
Full Text - PDF
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

MARC

LEADER 00000nab a2200000uu 4500
001 3273797497
003 UK-CbPIL
022 |a 1664-462X 
024 7 |a 10.3389/fpls.2025.1687742  |2 doi 
035 |a 3273797497 
045 2 |b d20251001  |b d20251031 
100 1 |a Hu, Yongkang 
245 1 |a LW-PWDNet: a lightweight and cross-terrain adaptive framework for early pine wilt disease detection 
260 |b Frontiers Media SA  |c Oct 2025 
513 |a Journal Article 
520 3 |a Pine wilt disease (PWD) poses a severe threat to forest ecosystems due to its high infectivity and destructive nature. Early identification of PWD-infected pines is critical to curbing disease spread and safeguarding forest resources. In order to timely detect and prevent the spread of PWD and meet the requirements of edge computing devices for real-time performance and computational efficiency, this paper proposes a lightweight model LW-PWDNet. The backbone network reconstructs HGNetV2 to achieve efficient feature extraction. It decomposes traditional convolutions into more lightweight feature generation and transformation operations, reducing computational cost while retaining discriminative power. The feature fusion layer reconstructs the path aggregation network based on RepBlock and multi-scale attention mechanism, capturing fine-grained details of small lesions, so as to better capture the detailed features of small targets. At the same time, this paper designs a lightweight D-Sample down-sampling module in the feature fusion layer to further improve the model's detection ability for multi-scale targets. Finally, this paper designs a lightweight prediction layer LightShiftHead for this model. By strengthening the local feature expression, the detection accuracy of PWD in small targets is further improved. A large number of experimental results show that LW-PWDNet maintains a high detection accuracy of mAP 89.7%, while achieving low computational complexity of 5.6 GFLOPs and only 1.9M parameters, as well as a high inference speed of 166 FPS when tested on an NVIDIA RTX 4070 GPU with a 13th Gen Intel(R) Core(TM) i7-13700KF processor, using PyTorch 2.0.1 and CUDA 12.6, based on Python 3.9. This model can provide an efficient and lightweight detection solution for PWD in resource-constrained scenarios such as unmanned aerial vehicle inspections. 
651 4 |a China 
653 |a Infections 
653 |a Feature extraction 
653 |a Accuracy 
653 |a Deep learning 
653 |a Microprocessors 
653 |a Disease 
653 |a Optimization 
653 |a Edge computing 
653 |a Unmanned aerial vehicles 
653 |a Computer applications 
653 |a Vehicle inspection 
653 |a Infectivity 
653 |a Disease detection 
653 |a Remote sensing 
653 |a Forest ecosystems 
653 |a Computational efficiency 
653 |a Target detection 
653 |a Trees 
653 |a Computing costs 
653 |a Design 
653 |a Terrestrial ecosystems 
653 |a Wilt 
653 |a Disease spread 
653 |a Real time 
653 |a Forest resources 
653 |a Satellites 
653 |a Environmental 
700 1 |a Wang, Fang 
773 0 |t Frontiers in Plant Science  |g vol. 16 (Oct 2025), p. 1687742-1687766 
786 0 |d ProQuest  |t Agriculture Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3273797497/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3273797497/fulltext/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3273797497/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch