Online detection of automotive oil pipe surface defects based on improved YOLOv8 algorithm DOI

Zhenghang Yi,

Zhenhao Jiang,

Junhui Lu

et al.

Published: July 22, 2024

Language: Английский

Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework DOI Creative Commons
Wenxia Yuan,

L.W. Lan,

Jiayi Xu

et al.

Agronomy, Journal Year: 2025, Volume and Issue: 15(1), P. 221 - 221

Published: Jan. 17, 2025

Aiming at the problems of insufficient detection accuracy and high false rates traditional pest models in face small targets incomplete targets, this study proposes an improved target network, I-YOLOv10-SC. The network leverages Space-to-Depth Convolution to enhance its capability detecting insect targets. Convolutional Block Attention Module is employed improve feature representation attention focus. Additionally, Shape Weights Scale Adjustment Factors are introduced optimize loss function. experimental results show that compared with original YOLOv10, model generated by algorithm improves 5.88 percentage points, recall rate 6.67 balance score 6.27 mAP value 4.26 bounding box 18.75%, classification 27.27%, point 8%. oscillation has also been significantly improved. enhanced I-YOLOv10-SC effectively addresses challenges tea plantations, offering precision rates, thus providing a solid technical foundation for intelligent monitoring precise prevention smart gardens.

Language: Английский

Citations

1

DAMI-YOLOv8l: A multi-scale detection framework for light-trapping insect pest monitoring DOI Creative Commons
Xiao Chen, Xinting Yang, Huan Hu

et al.

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103067 - 103067

Published: Feb. 1, 2025

Language: Английский

Citations

1

Research on Segmentation Method of Maize Seedling Plant Instances Based on UAV Multispectral Remote Sensing Images DOI Creative Commons

Tingting Geng,

Haiyang Yu, Xinru Yuan

et al.

Plants, Journal Year: 2024, Volume and Issue: 13(13), P. 1842 - 1842

Published: July 4, 2024

The accurate instance segmentation of individual crop plants is crucial for achieving a high-throughput phenotypic analysis seedlings and smart field management in agriculture. Current monitoring techniques employing remote sensing predominantly focus on population analysis, thereby lacking precise estimations plants. This study concentrates maize, critical staple crop, leverages multispectral data sourced from unmanned aerial vehicles (UAVs). A large-scale SAM image model employed to efficiently annotate maize plant instances, constructing dataset seedling segmentation. evaluates the experimental accuracy six algorithms: Mask R-CNN, Cascade PointRend, YOLOv5, Scoring YOLOv8, various combinations bands comparative analysis. findings indicate that YOLOv8 exhibits exceptional accuracy, notably NRG band, with bbox_mAP50 segm_mAP50 accuracies reaching 95.2% 94%, respectively, surpassing other models. Furthermore, demonstrates robust performance generalization experiments, indicating its adaptability across diverse environments conditions. Additionally, this simulates analyzes impact different resolutions model’s accuracy. reveal sustains high even at reduced (1.333 cm/px), meeting criteria.

Language: Английский

Citations

6

Identification of Insect Pests on Soybean Leaves Based on SP-YOLO DOI Creative Commons

Kebei Qin,

Jie Zhang,

Yue Hu

et al.

Agronomy, Journal Year: 2024, Volume and Issue: 14(7), P. 1586 - 1586

Published: July 20, 2024

Soybean insect pests can seriously affect soybean yield, so efficient and accurate detection of is crucial for production. However, pest in complex environments suffers from the problems small targets, large inter-class feature similarity, background interference with extraction. To address above problems, this study proposes algorithm SP-YOLO based on YOLOv8n. The model utilizes FasterNet to replace backbone YOLOv8n, which reduces redundant features improves model’s ability extract effective features. Second, we propose PConvGLU architecture, enhances capture representation image details while reducing computation memory requirements. In addition, a lightweight shared header, enables parameter amount be reduced accuracy further improved by convolution GroupNorm. achieves 80.8% precision, 66.4% recall, 73% average 6%, 5.4%, 5.2%, respectively, compared FPS reaches 256.4, final size only 6.2 M, number computational quantities covariates basically comparable that original model. capability significantly enhanced existing methods, provides good solution detection. an technical support

Language: Английский

Citations

4

Camouflage detection: Optimization-based computer vision for Alligator sinensis with low detectability in complex wild environments DOI Creative Commons
Yantong Liu,

Sai Che,

Liwei Ai

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 83, P. 102802 - 102802

Published: Aug. 28, 2024

Alligator sinensis is an extremely rare species that possesses excellent camouflage, allowing it to fit perfectly into its natural environment. The use of camouflage makes detection difficult for both humans and automated systems, highlighting the importance modern technologies animal monitoring. To address this issue, we present YOLO v8-SIM, innovative technique specifically developed significantly enhance identification precision. v8-SIM utilizes a sophisticated dual-layer attention mechanism, optimized loss function called inner intersection-over-union (IoU), slim-neck cross-layer hopping. results our study demonstrate model achieves accuracy rate 91 %, recall 89.9 mean average precision (mAP) 92.3 % IoU threshold 0.5. In addition, operates at frame 72.21 frames per second (FPS) excels accurately recognizing objects are partially visible or smaller in size. further improve initiatives, suggest creating open-source collection data showcases A. native environment while using techniques. These developments collectively ability detect disguised animals, thereby promoting monitoring protection biodiversity, supporting ecosystem sustainability.

Language: Английский

Citations

4

Rice-YOLO: An Automated Insect Monitoring in Rice Storage Warehouses with the Deep Learning Model DOI

P. Vinass Jamali,

V. Eyarkai Nambi, M. Loganathan

et al.

ACS Agricultural Science & Technology, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 14, 2025

Grain storage is an essential component of grain supply chain management that guarantees food security within the nation. Inaccurate diagnosis insect infestation during might lead to misinterpretation fumigation, resulting in substantial qualitative and quantitative losses grains. This work introduces a new deep learning model called "Rice-YOLO" (You Only Look Once) addresses shortcomings existing detection methods. The offers high level accuracy real-time performance. has been optimized accurately identify Tribolium castaneum Rhyzopertha dominica stored rice grains, under different background lighting circumstances. YOLOv7 (YOLOv7 x) YOLOv8 (l/m/x/s/n) were models used train, test, validate data sets. performance these state-of-the-art was assessed. obtained remarkable outcomes on Rice set. It achieved 97.7% mean average precision (mAP) 97.5% recall for T. castaneum, as well 95.5%. R. scored mAP 96.2% 93%. took around 7.68 min process detect dominica. top-performing YOLOv8n then deployed laptop achieving speed 22 fps inference time 6.4 ms. findings indicated algorithm rapid effective detecting, identifying, quantifying pests could facilitate automatic identification insects warehouses facilities involved postharvest management.

Language: Английский

Citations

0

YOLOv9c: A Robust Framework for Insect Detection DOI
Hai Thanh Nguyen, Binh-Minh Nguyen,

Anh Kim Su

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 30 - 43

Published: Jan. 1, 2025

Language: Английский

Citations

0

Multi-species insect recognition method based on computer visions: Sustainable agricultural development DOI Creative Commons
Lijuan Zhang, Shanshan Sun, Hui Zhao

et al.

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103125 - 103125

Published: April 1, 2025

Language: Английский

Citations

0

Lightweight and accurate aphid detection model based on an improved deep-learning network DOI Creative Commons
Wen‐Hua Sun, Yane Li, Hailin Feng

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 83, P. 102794 - 102794

Published: Aug. 24, 2024

Language: Английский

Citations

1

Automatic pine wilt disease detection based on improved YOLOv8 UAV multispectral imagery DOI Creative Commons

Shaoxiong Xu,

Wenjiang Huang, Dachen Wang

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102846 - 102846

Published: Oct. 1, 2024

Language: Английский

Citations

1