A Rapid Identification Method of Soybean Insect Pests Using SK-YOLOv8 Network Structure Improvement
Main Article Content
Abstract
Timely and accurate identification of soybean insect pests is essential for precision agriculture and sustainable crop management. This paper presents an improved pest detection method based on the YOLOv8 architecture, incorporating the Selective Kernel (SK) attention mechanism to enhance feature adaptability across multiple receptive fields. By embedding SK attention modules into the backbone of YOLOv8, the network dynamically selects appropriate kernel sizes to better capture the varying scales and visual patterns of insect pests. This design enables the model to focus on discriminative features while reducing redundant background information. To evaluate the effectiveness of the proposed approach, a
soybean insect pest dataset was constructed, and extensive experiments were conducted under real-world conditions. The results show that the improved SK-YOLOv8 model achieves a significant improvement in detection accuracy, reaching an mAP@0.5 of 87.4%, while maintaining the same computational complexity (8.2 GFLOPs) as the original YOLOv8n. This demonstrates that the proposed method not only enhances detection accuracy and robustness but also preserves computational efficiency, offering a practical and effective solution for intelligent pest monitoring in precision agriculture.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The articles published are the opinion of the author only. The author is responsible for any legal consequences. That may arise from that article.
References
A. Paul, R. Machavaram, A. D. Kumar, and H. Nagar, “Smart solutions for capsicum harvesting: Unleashing the power of YOLO for detection, segmentation, growth stage classification, counting, and real-time mobile identification,” Computers and Electronics in Agriculture, vol. 219, pp. 108832, Jan. 2024, doi: 10.1016/ j.compag.2024.10883.
X. Ji, Z. Yue, H. Yang, M. Li, and H. Han, “SCADDETR: An infrared image detection method for switchgear equipment,” IEEE Internet of Things Journal, vol. 12, no. 15, pp. 30676–30697, Aug. 2025, doi:10.1109/JIOT.2025.3571499.
E. C. Tetila, F. A. G. da Silveira, A. B. da Costa, M. M. Belete, V. G. Cavalcanti, and D. S. Maciel, “YOLO performance analysis for real-time detection of soybean pests,” Smart Agricultural Technology, vol. 7, 2024, doi: 10.1016/j.atech. 2024.100405.
K. Qin, J. Zhang, and Y. Hu, “Identification of insect pests on soybean leaves based on SP-YOLO,” Agronomy, vol. 14, no. 7, 2024, doi: 10.3390/agronomy14071586.
R. Vaghela, D. S. Vaishnani, P. N. Srinivasu, Y. Popat, J. Sarda, M. Woźniak, and M. F. Ijaz, “Land cover classification for identifying the agriculture fields using versions of YOLO v8,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 8672–8684, 2025, doi: 10.1109/ JSTARS.2025.3547058.
T. Li, L. Zhang, and J. Lin, “Precision agriculture with YOLO-Leaf: Advanced methods for detecting apple leaf diseases,” Frontiers in Plant Science, vol. 15, pp. 1452502, Apr. 2024, doi: 10.3389/fpls.2024.1452502.
K. Kanna, K. Ramalingam, P. Pazhanivelan, J. Ramasamy, and P. PC, “YOLO deep learning algorithm for object detection in agriculture: A review,” Journal of Agricultural Engineering, vol. 55, no. 4, 2024, doi: 10.4081/jae.2024.1641.
Q. Zhou, H. Li, Z. Cai, Y. Zhong, F. Zhong, X. Lin, and L. Wang, “YOLO-ACE: Enhancing YOLO with augmented contextual efficiency for precision cotton weed detection,” Sensors, vol. 25, no. 5, pp. 1635, Mar. 2025, doi: 10.3390/s25051635.
H. Fang, B. Shi, Y. Sun, N. Xiong, and L. Zhang, “APest-YOLO: A multi-scale agricultural pest detection model based on deep learning,” Applied Engineering in Agriculture, vol. 40, no. 5, pp. 553–564, 2024, doi: 10.13031/aea.15987.
J. Chu, Y. Li, H. Feng, L. Wang, and Z. Zhang, “Research on a multi-scale pest detection and identification method in granary based on improved YOLOv5,” Agriculture, vol. 13, no. 2, 2023, doi: 10.3390/agriculture13020364.
J. Xiao, G. Kang, L. Wang, W. Zhao, Z. Liu, and Y. Yang, “Real-time lightweight detection of lychee diseases with enhanced YOLOv7 and edge computing,” Agronomy, vol. 13, no. 12, 2023, doi: 10.3390/agronomy13122866.
B. Guan, Y. Wu, J. Zhu, Y. Hu, and C. Yu, “GC-Faster RCNN: The object detection algorithm for agricultural pests based on an improved hybrid attention mechanism,” Plants, vol. 14, no. 7, 2025, doi: 10.3390/plants14071106.
H. Liu, Y. Hou, J. Zhang, P. Zheng, and S. Hou, “Research on weed reverse detection methods based on improved You Only Look Once (YOLO) v8: Preliminary results,” Agronomy, vol. 14, no. 8, pp. 1667, Aug. 2024, doi: 10.3390/ agronomy14081667.
Y. Huang, H. Huang, F. Qin, Y. Chen, J. Zou, B. Liu, Z. Li, C. Liu, F. Wan, W. Qian, and X, Qiao, “YOLO-IAPs: A rapid detection method for invasive alien plants in the wild based on improved YOLOv9,” Agriculture, vol. 14, no. 12, pp. 2201, Dec. 2024, doi: 10.3390/agriculture 14122201.
X. Ji, Z. Yue, H. Yang, and Z. Zhang, “Infrared image classification and detection algorithm for power equipment based on improved YOLOv10,” IEEE Access, vol. 12, pp. 184976–184988, Dec. 2024, doi: 10.1109/ ACCESS.2024.3514103.
H. Feng, Q. Chen, and Z. Duan, “LCDDN-YOLO: Lightweight cotton disease detection in natural environment, based on improved YOLOv8,” Agriculture, vol. 15, no. 4, pp. 421, Apr. 2025, doi: 10.3390/agriculture15040421.
B. Li, L. Yu, H. Zhu, and Z. Tan, “YOLO-FDLU: A lightweight improved YOLO11s-based algorithm for accurate maize pest and disease detection,” AgriEngineering, vol. 7, pp. 323, 2025, doi:10.3390/agriengineering7100323.
X. Li, W. Wang, X. Hu, and J. Yang, “Selective kernel networks,” in Proceedings of the IEEE/ CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 510–519, doi: 10.1109/ CVPR.2019.00060.
X. Sun, P. Wu, and S. C. H. Hoi, “Face detection using deep learning: An improved Faster R-CNN approach,” Neurocomputing, vol. 299, pp. 42–50, Mar. 2018, doi: 10.1016/j.neucom. 2018.03.030.
X. Fu, A. Li, Z. Meng, J. Wang, and J. Guo, “A dynamic detection method for phenotyping pods in a soybean population based on an improved YOLO-v5 network,” Agronomy, vol. 12, no. 12, 2022, Art. no. 3209, doi: 10.3390/ agronomy12123209.
R. Khanam, M. Hussain Yolov11: An overview of the key architectural enhancements[J]. arXiv preprint arXiv:2410.17725, 2024, doi: 10.48550/ arXiv.2410.17725.
