基于改进YOLOv5s算法的母猪发情检测研究

打开文本图片集

中图分类号：S126：S828 文献标识号：A 文章编号：1001-4942（2026）01-0164-09

AbstractIn order to solve the problems of low effciency and precision of traditional manual detection， this study proposed an estrus detection method of sows based on improved YOLOv5s，aiming at the characteristics of vulva becoming red and swolln during estrus.Specific improvements included adding the Coordinate Attention （CA）mechanism to the backbone network of YOLOv5s，replacing the original interpolation-based upsampling with CARAFE upsampling，and substituting the original CIoU loss function with the EIoU loss function.Furthermore，the ablation experiments and comparative tests with other models were conducted to verify the effctiveness of the proposed method.The results showed that the improved model achieved the precision of 94.5% ， recall of 93.3% and mean average precision （ χmAP@0.5′ ）of 93.8% for sow vulvar morphology recognition，respectively. Compared with some YOLO series models （including the original YOLOv5s） and the Faster R-CNN model， the improved model maintained the highest precision，recall and mAP@0.5 for sow vulvar morphology recognition. Meanwhile，its model weight，parameter count and computational complexity were 16.3MB ， 7.2M and 16.3G ，respectively，which was slightly higher than those of the original YOLOv5s （15.8 MB，7.O M，14.5G） but significantly lower than those of other comparative models.In terms of detection speed，the frame rate （FPS）of the improved model reached 64.3 frames per second （fps），which was slightly lower than those of the original YOLOv5s （73.2 fps）and YOLOv8s （67.1 fps）but notably higher than those of the other models.These results indicated that the improved YOLOv5s model proposed in this study could significantly enhance detection accuracy and promote real-time detection performance，thereby providing technical support for sow estrus detection.

KeywordsYOLOv5s； Sow estrus;； Coordinate Attntion mechanism; CARAFE upsampling； EIoU losfunction

我国是世界第一养猪大国，生猪产业是我国农业重要支柱产业之一[1]。（剩余11014字）