YOLO-pest: a real-time multi-class crop pest detection model

Shifeng Dong; Jie Zhang; Fenmei Wang; Xiaodong Wang

doi:10.1117/12.2637467

24 May 2022 YOLO-pest: a real-time multi-class crop pest detection model

Shifeng Dong, Jie Zhang, Fenmei Wang, Xiaodong Wang

Author Affiliations +

Proceedings Volume 12260, International Conference on Computer Application and Information Security (ICCAIS 2021); 1226003 (2022) https://doi.org/10.1117/12.2637467
Event: International Conference on Computer Application and Information Security (ICCAIS 2021), 2021, Wuhan, China

Abstract

Crop pest control is one of the important tasks for crop yield. However, multi-class pests and high similarity in appearance bring challenges to precision recognition of pests. In recent years, deep-learning based algorithms in object detection have achieved an excellent result, such as the YOLO detector, which can balance accuracy and speed. YOLO performs well in detecting normal size objects, but has low precision in detecting small objects. The accuracy decreases notably when dealing with pest dataset, which have large-scale changes and multi-class. To solve the detection problem of multi-scale pest, we propose a detector named YOLO-pest based on YOLOv4 to improve the performance of pest detection. Our approach includes using lite but efficient backbone mobileNetv3 and lite fusion feature pyramid network. The improved detector significantly increased accuracy while remaining fast detection speed. Experiments on the constructed Croppest12 dataset show that our improved algorithm outperforms other compared methods.

Citation Download Citation

Shifeng Dong, Jie Zhang, Fenmei Wang, and Xiaodong Wang "YOLO-pest: a real-time multi-class crop pest detection model", Proc. SPIE 12260, International Conference on Computer Application and Information Security (ICCAIS 2021), 1226003 (24 May 2022); https://doi.org/10.1117/12.2637467

ACCESS THE FULL ARTICLE

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY