Agricultural Pest Detection Method Based on YOLOv8- MNFE Fusion Model
Abstract
MNFE fusion model. The proposed model integrates the lightweight MobileNetV3 backbone network with the Focal-EIoU loss function,
optimizing both the parameter scale and the accuracy of small target localization. Extensive experiments were conducted using the IP102
pest dataset to evaluate the models performance. Ablation studies were performed to validate the effectiveness of the improved modules,
and comparisons were made with other mainstream detection models. The results demonstrate that the YOLOv8-MNFE model achieves
a mean average precision (mAP50) of 98.4% and a mAP50-95 of 79.3%, with both detection speed and accuracy significantly surpassing
existing methods. This study contributes to the ongoing efforts to enhance pest detection technologies, thereby supporting sustainable agricultural practices and food security.
Keywords
Full Text:
PDFReferences
[1] Wen C, Guyer D E, Li W. Local feature-based identification and classification for orchard insects[J]. Biosystems engineering, 2009,
104(3): 299-307.
[2] Larios N, Deng H, Zhang W, et al. Automated insect identification through concatenated histograms of local appearance features: feature
vector generation and region detection for deformable objects[J]. Machine Vision and Applications, 2008, 19: 105-123.
[3] Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C., 2004. Visual categorization with bags of keypoints. In: Workshop on statistical learning in computer vision, ECCV. Vol. 1. p. 22.
[4] Kartikeyan P, Shrivastava G. Review on emerging trends in detection of plant diseases using image processing with machine learning[J].
International Journal of Computer Applications, 2021, 174(11): 39-48.
[5] Kayali D, Olawale P, Kirsal-Ever Y, et al. The effect of compressor-decompressor networks with different image sizes on mask detection using Convolutional Neural Networks-VGG-16[C]//2022 Innovations in Intelligent Systems and Applications Conference (ASYU).
IEEE, 2022: 1-5.
[6] Ayan E. Genetic algorithm-based hyperparameter optimization for convolutional neural networks in the classification of crop pests[J].
Arabian Journal for Science and Engineering, 2024, 49(3): 3079-3093.
[7] Tang Z, Lu J, Chen Z, et al. Improved Pest-YOLO: Real-time pest detection based on efficient channel attention mechanism and transformer encoder[J]. Ecological Informatics, 2023, 78: 102340.
[8] Wang X, Zhang S, Wang X, et al. Crop pest detection by three-scale convolutional neural network with attention[J]. Plos one, 2023,
18(6): e0276456.
[9] Wu X, Zhan C, Lai Y K, et al. Ip102: A large-scale benchmark dataset for insect pest recognition[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 8787-8796.
[10] Nanni L, Maguolo G, Pancino F. Insect pest image detection and recognition based on bio-inspired methods[J]. Ecological Informatics,
2020, 57: 101089.
[11] Luo Q, Wan L, Tian L, et al. Saliency guided discriminative learning for insect pest recognition[C]//2021 International Joint Conference
on Neural Networks (IJCNN). IEEE, 2021: 1-8.
[12] Feng F, Dong H, Zhang Y, et al. Ms-aln: Multiscale attention learning network for pest recognition[J]. IEEE Access, 2022, 10: 40888-
40898.
[13] Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLO (Version 8.0.0) [Computer software]. https://github.com/ultralytics/ultralytics
[14] Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF international conference on computer
vision. 2019: 1314-1324.
[15] Zhang Y F, Ren W, Zhang Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506:
146-157.
[16] Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.
[17] Qin Z, Chen D, Wang H. MCA-YOLOv7: An improved uav target detection algorithm based on yolov7[J]. IEEE Access, 2024, 12:
42642-42650.
[18] Zheng Hongna, Zhou Lixiang, Wang Qiang. Research on detection method of potato seedling based on YOLO-PS[J]. Journal of Chinese
Agricultural Mechanization, 2024, 45(12): 245-250.
DOI: http://dx.doi.org/10.70711/frim.v3i6.6667
Refbacks
- There are currently no refbacks.
