Open Access

ARTICLE

Improving Hornet Detection with the YOLOv7-Tiny Model: A Case Study on Asian Hornets

Yung-Hsiang Hung, Chuen-Kai Fan, Wen-Pai Wang^*

1 Department of Industrial Engineering & Management, National Chin-Yi University of Technology, Taichung, 411030, Taiwan

* Corresponding Author: Wen-Pai Wang. Email:

Computers, Materials & Continua 2025, 83(2), 2323-2349. https://doi.org/10.32604/cmc.2025.063270

Received 10 January 2025; Accepted 13 March 2025; Issue published 16 April 2025

Abstract

Bees play a crucial role in the global food chain, pollinating over 75% of food and producing valuable products such as bee pollen, propolis, and royal jelly. However, the Asian hornet poses a serious threat to bee populations by preying on them and disrupting agricultural ecosystems. To address this issue, this study developed a modified YOLOv7tiny (You Only Look Once) model for efficient hornet detection. The model incorporated space-to-depth (SPD) and squeeze-and-excitation (SE) attention mechanisms and involved detailed annotation of the hornet’s head and full body, significantly enhancing the detection of small objects. The Taguchi method was also used to optimize the training parameters, resulting in optimal performance. Data for this study were collected from the Roboflow platform using a 640 × 640 resolution dataset. The YOLOv7tiny model was trained on this dataset. After optimizing the training parameters using the Taguchi method, significant improvements were observed in accuracy, precision, recall, F1 score, and mean average precision (mAP) for hornet detection. Without the hornet head label, incorporating the SPD attention mechanism resulted in a peak mAP of 98.7%, representing an 8.58% increase over the original YOLOv7tiny. By including the hornet head label and applying the SPD attention mechanism and Soft-CIOU loss function, the mAP was further enhanced to 97.3%, a 7.04% increase over the original YOLOv7tiny. Furthermore, the Soft-CIOU Loss function contributed to additional performance enhancements during the validation phase.

---

Keywords

---