Forestry pest detection method based on improved YOLOv8n

Chen Wanzhi; Yuan Hang

doi:10.12171/j.1000-1522.20240326

Journal of Beijing Forestry University > 2025 > 47(2): 119-131. > DOI: 10.12171/j.1000-1522.20240326

Chen Wanzhi, Yuan Hang. Forestry pest detection method based on improved YOLOv8n[J]. Journal of Beijing Forestry University, 2025, 47(2): 119-131. DOI: 10.12171/j.1000-1522.20240326

Citation:

Chen Wanzhi, Yuan Hang. Forestry pest detection method based on improved YOLOv8n[J]. Journal of Beijing Forestry University, 2025, 47(2): 119-131. DOI: 10.12171/j.1000-1522.20240326

Citation:

Chen Wanzhi, Yuan Hang. Forestry pest detection method based on improved YOLOv8n[J]. Journal of Beijing Forestry University, 2025, 47(2): 119-131. DOI: 10.12171/j.1000-1522.20240326

PDF (2896 KB)

Forestry pest detection method based on improved YOLOv8n

School of Software, Liaoning Technical University, Huludao 125105, Liaoning, China

More Information

Received Date: October 06, 2024
Revised Date: November 13, 2024
Accepted Date: December 06, 2024
Available Online: December 10, 2024

Graphical Abstract

Abstract

Abstract

Objective
In response to the problem of slow speed, narrow categories, and poor detection of small-target pests in existing forestry pest detection methods, a forestry pest detection method based on the improved YOLOv8n was proposed.
Method
Firstly, an efficient multi-scale cascade attention feature extraction network EfficientViT was adopted as the backbone of improved model to reduce computational complexity and enhance detection speed. Secondly, a multi-scale adaptive feature fusion module DA-C2F was constructed to improve the model’s ability to focus on and accurately identify pest targets in complex backgrounds. Additionally, a newly added small-object detection head XSH further enhanced the detection capability for small pest objects. Finally, a minimum point distance IoU loss function MPDIoU was implemented as the bounding box loss for the model, accelerating convergence speed and further improving the accuracy of pest target localization.
Result
The improved model achieved a detection precision of 98.6%, recall of 95.7%, mean average precision of 98.3%, mean average precision at different thresholds (mAP50-95) of 85.6%, and an F₁-score of 0.979. These metrics represented improvements of 3.9, 2.6, 2.8, 2.5 percentage points and 4.4%, respectively over the original model. The detection speed reached 95 frames per second with an improvement of 15.9%, also surpassed that of the lighter-weight model. Furthermore, in comparison with other detection models, the improved model demonstrated an increase of 11.2 percentage points in detection precision for moth pests, and exhibited superior overall performance in detection of two independent moth pest species.
Conclusion
The proposed method has higher detection accuracy and faster detection speed for forestry pests, better detection accuracy for multiple categories of pests, and better generalization ability of the improved model.

FullText(HTML)

References (38)

References

[1]	Zhao Z H, Yang M, Yang L M, et al. Predicting the spread of forest diseases and pests[J]. IEEE Access, 2020, 8: 199803−199812. doi: 10.1109/ACCESS.2020.3035547
[2]	赵严, 刘应安, 业巧林, 等. 基于深度学习的林业害虫检测优化[J]. 液晶与显示, 2022, 37(9): 1216−1227. doi: 10.37188/CJLCD.2022-0077 Zhao Y, Liu Y A, Ye Q L, et al. Forestry pest detection based on deep learning[J]. Chinese Journal of Liquid Crystals and Displays, 2022, 37(9): 1216−1227. doi: 10.37188/CJLCD.2022-0077
[3]	Zha M F, Qian W B, Yi W K, et al. Lightweight YOLOv4-based forestry pest detection method using coordinate attention and feature fusion[J]. Entropy, 2021, 23: 1587−1605. doi: 10.3390/e23121587
[4]	Liu D Y, Lü F, Guo J, et al. Detection of forestry pests based on improved YOLOv5 and transfer learning[J]. Forests, 2023, 14: 1484−1500. doi: 10.3390/f14071484
[5]	王中天, 邹颖波, 吴昌霖, 等. 超越单一感知的农田害虫检测算法MRA-YOLOX[J]. 计算机工程与应用, 2024, 60(16): 206−216. doi: 10.3778/j.issn.1002-8331.2305-0318 Wang Z T, Zou Y B, Wu C L, et al. MRA-YOLOX, for pest detecting in farmland beyond single perception[J]. Computer Engineering and Applications, 2024, 60(16): 206−216. doi: 10.3778/j.issn.1002-8331.2305-0318
[6]	Huang J Y, Huang Y, Huang H L, et al. An improved YOLOX algorithm for forest insect pest detection[J]. Computational Intelligence and Neuroscience, 2022, 5787554: 1−12.
[7]	Xie C J, Zhang J, Li R, et al. Automatic classification for field crop insects via multiple-task sparse representation and multiple-kernel learning[J]. Computers and Electronics in Agriculture, 2015, 119: 123−132. doi: 10.1016/j.compag.2015.10.015
[8]	Ebrahimi M A, Khoshtaghaza M H, Minaei S, et al. Vision-based pest detection based on SVM classification method[J]. Computers and Electronics in Agriculture, 2017, 137: 52−58. doi: 10.1016/j.compag.2017.03.016
[9]	Wang J N, Lin C T, Ji L Q, et al. A new automatic identification system of insect images at the order level[J]. Knowledge-Based Systems, 2012, 33: 102−110. doi: 10.1016/j.knosys.2012.03.014
[10]	Li Y, Xia C L, Lee J M. Detection of small-sized insect pest in greenhouses based on multifractal analysis[J]. Optik-International Journal for Light and Electron Optics, 2015, 126: 2138−2143. doi: 10.1016/j.ijleo.2015.05.096
[11]	赵辉, 黄镖, 王红君, 等. 基于改进YOLOv7的农田复杂环境下害虫识别算法研究[J]. 农业机械学报, 2023, 54(10): 246−254. doi: 10.6041/j.issn.1000-1298.2023.10.024 Zhao H, Huang B, Wang H J, et al. Pest identification method in complex farmland environment[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(10): 246−254. doi: 10.6041/j.issn.1000-1298.2023.10.024
[12]	姜晟, 曹亚芃, 刘梓伊, 等. 基于改进Faster RCNN的茶叶叶部病害识别[J]. 华中农业大学学报, 2024, 43(5): 41−50. Jiang S, Cao Y F, Liu Z Y, et al. Recognition of tea leaf diseases based on improved Faster RCNN[J]. Journal of Huazhong Agricultural University, 2024, 43(5): 41−50.
[13]	蒋心璐, 陈天恩, 王聪, 等. 农业害虫检测的深度学习算法综述[J]. 计算机工程与应用, 2023, 59(6): 30−44. doi: 10.3778/j.issn.1002-8331.2205-0604 Jiang X L, Chen T E, Wang C, et al. Survey of deep learning algorithms for agricultural pest detection[J]. Computer Engineering and Applications, 2023, 59(6): 30−44. doi: 10.3778/j.issn.1002-8331.2205-0604
[14]	王金, 李颜娥, 冯海林, 等. 基于改进的Faster R-CNN的小目标储粮害虫检测研究[J]. 中国粮油学报, 2021, 36(9): 164−171. doi: 10.3969/j.issn.1003-0174.2021.09.027 Wang J, Li Y E, Feng H L, et al. Detection of small target stored grain pests detection based on improved Faster R-CNN[J]. Journal of the Chinese Cereals and Oils Association, 2021, 36(9): 164−171. doi: 10.3969/j.issn.1003-0174.2021.09.027
[15]	候瑞环, 杨喜旺, 王智超, 等. 一种基于YOLOv4-TIA的林业害虫实时检测方法[J]. 计算机工程, 2022, 48(4): 255−261. Hou R H, Yang X W, Wang Z C, et al. A real-time detection method for forestry pest based on YOLOv4-TI-A[J]. Computer Engineering, 2022, 48(4): 255−261.
[16]	孙海燕, 陈云博, 封丁惟, 等. 基于注意力模型和轻量化YOLOv4的林业害虫检测方法[J]. 计算机应用, 2022, 42(11): 3580−3587. doi: 10.11772/j.issn.1001-9081.2021122164 Sun H Y, Chen Y B, Feng D W, et al. Forestry pest detection method based on attention model and lightweight YOLOv4[J]. Journal of Computer Applications, 2022, 42(11): 3580−3587. doi: 10.11772/j.issn.1001-9081.2021122164
[17]	Cai H, Li J, Hu M, et al. EfficientViT: lightweight multi-scale attention for high-resolution dense prediction[C]//Cristina C. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris: IEEE, 2023: 17256−17267.
[18]	Ma S L, Xu Y. MPDIoU: a loss for efficient and accurate bounding box regression[J/OL]. arXiv: 2307.07662v1. [2023−07−14]. https://doi.org/10.48550/arXiv.2307.07662.
[19]	Liu B, Liu L Y, Zhou R, et al. A dataset for forestry pest identification[J]. Frontiers in Plant Science, 2022, 13: 1−10.
[20]	Varghese R, Sambath M. YOLOv8: a novel object detection algorithm with enhanced performance and robustness[C]//Curran Associates, Inc. 2024 International Conference on advances in data engineering and intelligent computing systems (ADICS). Chennai: IEEE, 2024: 1−6.
[21]	彭菊红, 张弛, 高谦, 等. 基于改进的YOLOv8算法的钢材缺陷检测[J/OL]. 计算机工程 [2024−07−15]. https://doi.org/10.19678/j.issn.1000-3428.00EC0069283. Peng J H, Zhang C, Gao Q, et al. Steel defect detection based on improved yolov8 algorithm[J/OL]. Computer Engineering [2024−07−15]. https://doi.org/10.19678/j.issn.1000-3428.00EC0069283.
[22]	惠卓凡, 李鹏龙, 沈烈, 等. 基于改进YOLOv8的渔港船舶进出港目标检测与统计方法[J]. 大连海洋大学学报, 2024, 39(3): 498−505. Hui Z F, Li P L, Shen L, et al. Detection and statistics method of ship entry and exit in a fishing port based on improved YOLOv8[J]. Journal of Dalian Ocean University, 2024, 39(3): 498−505.
[23]	Wang C Y, Liao H Y M, Wu Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]// O’Conner L. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Seattle: IEEE, 2020: 1571−1580.
[24]	He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904−1916. doi: 10.1109/TPAMI.2015.2389824
[25]	Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]// O’Conner L. Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul : IEEE, 2019: 1314−1324.
[26]	Ma N, Zhang X, Zheng H T, et al. Shufflenet v2: practical guidelines for efficient cnn architecture design[C]//Ferrari V. Proceedings of the European conference on computer vision (ECCV). Munich: EACV, 2018: 116−131.
[27]	廖晓辉, 谢子晨, 辛忠良, 等. 基于轻量化YOLOv5的电气设备外部缺陷检测[J]. 郑州大学学报(工学版), 2024, 45(4): 117−124. Liao X H, Xie Z C, Xin Z L, et al. Electrical equipment external defect detection based on YOLOv5[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(4): 117−124.
[28]	徐杨, 熊举举, 李论, 等. 采用改进的YOLOv5s检测花椒簇[J]. 农业工程学报, 2023, 39(16): 283−290. doi: 10.11975/j.issn.1002-6819.202306119 Xu Y, Xiong J J, Li L, et al. Detection pepper clusters using improved YOLOv5s[J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(16): 283−290. doi: 10.11975/j.issn.1002-6819.202306119
[29]	Sanghyun W, Jongchan P, Joon Y L, et al. CBAM: convolutional block attention module[C]// Ferrari V. Proceedings of the European conference on computer vision (ECCV). Munich: EACV, 2018: 3−19.
[30]	Liu Y, Shao Z, Hoffmann N. Global attention mechanism: retain information to enhance channel-spatial interactions[J/OL]. arXiv: 2112.05561. [2023−07−14]. https://doi.org/10.48550/arXiv.2112.05561.
[31]	Farzad S, Nader A, Soroush S, et al. DAS: a deformable attention to capture salient information in CNNs[J/OL]. arXiv: 2311.12091. [2024−07−14]. https://doi.org/10.48550/arXiv.2311.12091.
[32]	Yu F, Koltun V, Funkhouser T. Dilated residual networks[C]// O’Conner L. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 472−480.
[33]	赵文仓, 徐长凯, 王春鑫. 基于优化边界框回归的目标检测[J]. 高技术通讯, 2021, 31(7): 747−753. doi: 10.3772/j.issn.1002-0470.2021.07.008 Zhao W C, Xu C K, Wang C X. Target detection based on optimized bounding box regression[J]. Chinese High Technology Letters, 2021, 31(7): 747−753. doi: 10.3772/j.issn.1002-0470.2021.07.008
[34]	周涛, 王骥, 麦仁贵. 基于改进YOLOv8的实时菠萝成熟度目标检测方法[J/OL]. 华中农业大学学报 [2024−07−16]. http://kns.cnki.net/kcms/detail/42.1181.S.20240422.1423.006.html. Zhou T, Wang J, Mai R G. Real-time object detection method of pineapple ripeness based on improved YOLOv8[J/OL]. Journal of Huazhong Agricultural University [2024−07−16]. http://kns.cnki.net/kcms/detail/42.1181.S.20240422.1423.006.html.
[35]	李爽, 张潇巍, 谭旭, 等. 基于深度学习的树木根系探地雷达多目标参数反演识别[J]. 北京林业大学学报, 2024, 46(4): 103−114. doi: 10.12171/j.1000-1522.20230259 Li S, Zhang X W, Tan X, et al. Deep learning-based inverse identification of multi-target parameters for tree rooting ground-penetrating radar[J]. Journal of Beijing Forestry University, 2024, 46(4): 103−114. doi: 10.12171/j.1000-1522.20230259
[36]	Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[C]// O’Conner L. 2017 IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, 2017: 618−626.
[37]	张新月, 胡广锐, 李浦航, 等. 基于改进YOLOv8n的轻量化红花识别方法[J]. 农业工程学报, 2024, 40(13): 163−170. Zhang X Y, Hu G R, Li P H, et al. Recognizing safflower using improved lightweight YOLOv8n[J]. Transactions of the Chinese Society of Agricultural Engineering, 2024, 40(13): 163−170.
[38]	陈中垚. 基于YOLOv5s的林业害虫目标检测方法分析[J]. 电子技术, 2024, 53(3): 53−57. Chen Z Y. Analysis of forest pest target detection method based on YOLOv5s[J]. Electronic Technology, 2024, 53(3): 53−57.

[1]	Liu Xiaojing, Wen Xin, Zhao Rui, Chen Shaoliang, Zhao Nan, Li Jinke, Zhou Xiaoyang, Yao Jun. Overexpression of Populus euphratica PeCSP1 negatively regulating salt tolerance in Arabidopsis thaliana[J]. Journal of Beijing Forestry University, 2023, 45(7): 9-17. DOI: 10.12171/j.1000-1522.20220020
[2]	Wu Xia, Zhang Yinan, Zhao Nan, Zhang Ying, Zhao Rui, Li Jinke, Zhou Xiaoyang, Chen Shaoliang. Overexpression of PeAnn1 from Populus euphratica negatively regulates drought resistance in transgenic Arabidopsis thaliana[J]. Journal of Beijing Forestry University, 2020, 42(6): 14-25. DOI: 10.12171/j.1000-1522.20200031
[3]	Li Pingping, Zeng Ming, Li Wenhai, Zhao Yuanyuan, Zheng Caixia. Comparative study on antioxidant capacity of heteromorphic leaves of Populus euphratica[J]. Journal of Beijing Forestry University, 2019, 41(8): 76-83. DOI: 10.13332/j.1000-1522.20190134
[4]	DENG Jia-yin, ZHANG Yan-li, ZHANG Yi-nan, ZHAO Rui, LI Jin-ke, ZHOU Xiao-yang, LIU Xiang-fen, CHEN Shao-liang. PeAPY1 and PeAPY2 of Populus euphratica regulating salt tolerance in Arabidopsis thaliana[J]. Journal of Beijing Forestry University, 2017, 39(6): 13-21. DOI: 10.13332/j.1000-1522.20170034
[5]	WANG Shao-jie, ZHAO Nan, SHEN Ze-dan, SA Gang, SUN Hui-min, ZHAO Rui, SHEN Xin, CHEN Shao-liang. Mediation of NO on Cd2+ uptake in Populus euphratica cells under cadmium stress[J]. Journal of Beijing Forestry University, 2015, 37(6): 11-16. DOI: 10.13332/j.1000-1522.20150023
[6]	ZHANG Xiao-fei, LU Xin, DUAN Hui, LIAN Cong-long, XIA Xin-li, YIN Wei-lun. Cloning and functional analysis of PeNAC045 from Populus euphratica[J]. Journal of Beijing Forestry University, 2015, 37(6): 1-10. DOI: 10.13332/j.1000-1522.20150066
[7]	BAI Xue, ZHANG Shu-jing, ZHENG Cai-xia, HAO Jian-qing, LI Wen-hai, YANG Yang. Comparative study on photosynthesis and water physiology of polymorphic leaves of Populus euphratica[J]. Journal of Beijing Forestry University, 2011, 33(6): 47-52.
[8]	MA Hong-shuang, XIA Xin-li, YIN Wei-lun. Cloning and analysis of SCL7 gene from Populus euphratica[J]. Journal of Beijing Forestry University, 2011, 33(1): 1-10.
[9]	ZHANG Zheng-hai, , KANG Xiang-yang, LIU Ming-hu, DUAN Wu-la. Organization of microtubule during microsporogenesis in Populus simonii × P. euphratica.[J]. Journal of Beijing Forestry University, 2008, 30(6): 36-40.
[10]	LI Li, ZHOU Yan, GAO Shu-min, WANG Ying, LIU Yan. Protein vacuoles in the egg cells of Pinus tabulaeformis Carr.and specific proteins relating to the development of egg cells[J]. Journal of Beijing Forestry University, 2007, 29(5): 57-61. DOI: 10.13332/j.1000-1522.2007.05.011

Cited By

Cited by

Periodical cited type(7)

1.	钟思琪，宁金魁，黄锦程，陈鼎泸，欧阳勋志，臧颢. 基于混合效应的杉木人工林冠幅模型. 森林与环境学报. 2024(02): 127-135 .
2.	张晓姗，高嘉，王洪永，王霞，庞薇，陈寅，杜振宇，马风云，马丙尧. 我国栎树引种及其营养生长研究进展. 江苏林业科技. 2024(02): 48-52 .
3.	邓坦，李文博，张向阳，王新建. 河南省栎类经营技术研究与建议. 河南林业科技. 2023(01): 1-5+30 .
4.	廖科，刘振华，童方平，陈瑞，吴敏，蒋龙，龚发武，李贵. 不同混交比例对栎类混交林生长和土壤养分的影响. 中南林业科技大学学报. 2023(09): 80-88 .
5.	娄明华，杨同辉，王卫兵，毛建方，徐婧，章建红. 四明山黄山松针阔混交林的树高—胸径模型. 林业与环境科学. 2023(05): 7-14 .
6.	娄明华，白超，杨同辉. 宁波石栎-木荷天然常绿阔叶混交林的树高-胸径模型. 林业与环境科学. 2021(04): 46-54 .
7.	娄明华，杨同辉，陈文伟，许俊. 宁波天然甜槠阔叶混交林树高—胸径模型研究. 防护林科技. 2021(05): 1-5 .

Other cited types(4)

Get Citation

PDF

XML

Article views (209) PDF downloads (57) Cited by(11)

Turn off MathJax

Article Contents

Abstract

References

Forestry pest detection method based on improved YOLOv8n