1.华中农业大学王建勇

阅读文章原文：http://ijabe.net/article/doi/10.25165/j.ijabe.20241706.8314

2.华农王建教授

基于红外热图像的笼养蛋鸭死禽检测方法严 煜，王巧华，林卫国，王树才*，谷 月，衡一帆（华中农业大学工学院，武汉430070，中国）摘要：为了准确高效的发现笼养蛋鸭中的死禽，解决笼养蛋鸭死禽巡检过度依赖人工问题

3.华中农业大学李建洪

，该研究提出了一种基于红外热成像技术和深度学习技术的笼养蛋鸭死禽检测方法该方法提出了一种轻量级目标检测算法，利用YOLO v8n作为基线模型，将主干网络替换为一种基于“Star Operate”的网络结构StarNet。

4.华中农业大学王宏杰

，同时利用StarNet中的Star Block结合C2f模块设计出C2f_Star结构，并插入至基线模型中的Neck结构中同时，引入轻量级结构LSKA替换掉基线模型中的SPPF结构提高特征增强能力此外，。

5.华中农业大学王剑

设计出一种轻量级共享卷积检测头SCSB-Head进一步降低模型运算体量综合以上对基线模型的改进构建出一种轻量级目标检测算法SLSS-YOLO试验结果显示，在检测性能上，SLSS-YOLO评价指标mAP@50%-95%、Precision和Recall 分别为80.50%、99.44%和98.46%。

6.华中农业大学王教授

与基线模型相比分别提高了1.00、1.98和0.26个百分点在模型大小和检测速度上，SLSS-YOLO的Parameters为1.44M，FLOPs为4.6G，FPS为134.9 f/s与基线模型相比Parameters和FLOPs分别降低了52.16%和43.90%，。

7.华中农业大学王红

FPS增加了5.4 f/s此外，该研究基于SLSS-YOLO和Hybrid-SORT建立目标跟踪模型，跟踪试验结果表明，Hybrid-SORT的跟踪效果ID-Switch次数为0，检测速度为10.9 ms/f。

8.华中农业大学王建鸿图片

与Bot-SORT、ByteTrack、Deep OC-SORT以及OC-SORT相比表现出了优异的跟踪检测性能因此，该研究提出的热红外检测方法能在复杂的笼舍环境背景下实现死禽识别与跟踪检测，为笼养蛋鸭死禽的无人巡检提供参考。

9.华中农业大学王永健

关键词：笼养蛋鸭；目标检测算法；YOLO；红外热成像；死禽DOI：10.25165/j.ijabe.20241706.8314引用信息：Yan Y, Wang Q H, Lin W G, Wang S C, Gu Y, Heng Y F. Method for detecting dead caged laying ducks based on infrared thermal imaging. Int J Agric & Biol Eng, 2024; 17(6): 101–110.

10.华中农业大学王创

Method for detecting dead caged laying ducks based on infrared thermal imagingYu Yan, Qiaohua Wang, Weiguo Lin, Shucai Wang* , Yue Gu, Yifan Heng

(College of Engineering, Huazhong Agricultural University, Wuhan 430070, China)Abstract：To accurately and efficiently detect dead caged laying ducks, thereby reducing reliance on manual inspection, this study proposes a method that integrates infrared thermography with deep learning technology. A lightweight object detection algorithm is developed, utilizing YOLO v8n as the baseline model. The backbone network is replaced with StarNet, which is based on “Star Operate”. Additionally, the C2f-Star structure is designed by combining the Star Block from StarNet with the C2f module, and it is inserted into the Neck structure of the baseline model. Lightweight module L-SPPF replaces the SPPF module in the baseline model to enhance feature augmentation. Furthermore, a lightweight shared convolutional detection head, termed SCSB-Head, is introduced to reduce computational complexity. These improvements collectively form a lightweight object detection algorithm named SLSS-YOLO. Experimental results show that SLSS-YOLO achieves mAP@50%-95%, precision, and recall scores of 80.50%, 99.44%, and 98.46%, respectively. Compared to the baseline model, these metrics improve by 1%, 1.98%, and 0.26%, respectively. In terms of model size and detection speed, SLSS-YOLO has 1.44 M parameters and 4.6 G FLOPs, achieving an FPS rate of 134.9 f/s. This represents a reduction of 52.16% and 43.90% in parameters and FLOPs, respectively, while increasing FPS by 5.4 f/s compared to the baseline model. Moreover, an object tracking model is constructed using SLSS-YOLO and Hybrid-SORT. Tracking tests demonstrate that Hybrid-SORT achieves zero ID-Switches, with a detection speed of 10.9 ms/f. It outperforms Bot-SORT, ByteTrack, Deep OC-SORT, and OC-SORT in terms of tracking performance. Therefore, the proposed thermal infrared detection method can effectively identify and track dead ducks in complex cage environments, providing a reference for automated inspection in caged duck farms.

Keywords: caged laying duck, object detection algorithm, YOLO, infrared thermal imaging, dead poultry

DOI: 10.25165/j.ijabe.20241706.8314Citation: Yan Y, Wang Q H, Lin W G, Wang S C, Gu Y, Heng Y F. Method for detecting dead caged laying ducks based on infrared thermal imaging. Int J Agric & Biol Eng, 2024; 17(6): 101–110.