MobileOne-YOLO: Improving the YOLOv7 network for the detection of unfertilized duck eggs and early duck embryo development - a novel approach

• Published in: Computers and electronics in agriculture Vol. 214; p. 108316
• Main Authors: Li, Qingxu, Shao, Ziyan, Zhou, Wanhuai, Su, Qianrui, Wang, Qiaohua
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2023
• Subjects: Duck eggs; Machine vision; MobileOne-YOLO; Unfertilized eggs and early dead embryo eggs; YOLOV7; Unfertilized eggs and early dead embryo eggs; Machine vision; MobileOne-YOLO; Duck eggs; YOLOV7
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2023.108316

•This study develops a practical solution by designing a duck egg suction lifter with a built-in light source to the needs of the hatching industry. Additionally, an image acquisition device was designed in conjunction with the suction lifter, enabling the capture of high-quality images for subsequent analysis.•This study has made enhancements to the YOLOV7 framework by incorporating the MobileOne network as the backbone and optimizing the YOLO head, resulting in a novel detection model named MobileOne-YOLO.•Data augmentation proves beneficial in enhancing the performance of the duck egg detection model, while transfer learning expedites the convergence of the model.•MobileOne-YOLO demonstrated remarkable accuracy, achieving 98.10% accuracy, 98.55% precision and recall, and 97.79% mAP50 for the detection of unfertilized duck eggs, dead embryo eggs, and healthy embryo eggs.•Compared to YOLOV7, MobileOne-YOLO showcased a marginal decrease of only 0.07 in mAP, while maintaining equal accuracy, yet significantly improving the FPS performance by 41.6. Unfertilized duck eggs and early dead embryo eggs can significantly harm normally developing embryo eggs if not detected and removed in a timely manner. The traditional light-illumination technique currently used for this purpose is inefficient, time-consuming, and labor-intensive, making it unsuitable for modern farms and hatcheries. To address this issue, this study focuses on duck eggs incubated for a period of 10 days. This paper introduces a newly developed duck egg image acquisition device that incorporates a duck egg suction lifter with a built-in light source. The device is designed based on the incubation process and has the potential for rapid implementation in actual production. Furthermore, this study describes an improved algorithm for identifying unfertilized duck eggs and early dead embryo eggs based on the YOLOv7 network. The algorithm incorporates the use of MobileOne as a replacement for YOLOv7′s backbone network and lightweight operations applied to the YOLO head. The test results demonstrate that the MobileOne-YOLO achieves 98.10% detection accuracy, 98.55% recall, 97.79% mAP50, 98.55% precision, and 142.8 FPS in the test set images. In comparison, the original YOLOV7 also achieves 98.10% detection accuracy, 97.10% recall, 97.86% mAP50, 100.00% precision, and 101.2 FPS. The MobileOne-YOLO network maintains the same level of detection accuracy as the YOLOV7 network while achieving significantly improved detection speed. The technical method proposed in this study meets the actual production requirements in terms of detection accuracy and speed. Moreover, the image acquisition method adopted in this study is based on the incubation process, making it readily applicable to production practice. This study provides a new foundation for the subsequent development of intelligent detection equipment for identifying unfertilized duck eggs and early dead embryo eggs.