DHSW-YOLO: A duck flock daily behavior recognition model adaptable to bright and dark conditions

Abstract

Accurate monitoring of animal behavioral rhythms is essential. Currently, it is challenging to identify the behavior of animals under low-light conditions. In this study, we proposed a deep learning model DHSW-YOLO (DH-SENet-WIoU-YOLO) to detect the daily behaviors of duck flocks under bright and dark conditions, meeting the speed requirement for real-time detection, using White Muscovy ducks (WMD) as the research object. Based on the YOLOv8 of network structure, we simplify the detection head of YOLOv8 and introduce the SENet attention mechanism and WIoU v3 loss function. The results showed that DHSW-YOLO could significantly improve the detection effect compared with the original YOLOv8. The mAP was improved from 92.2 % to 94.4 %, the Model size was reduced by 2.8 MB, the Inference time was faster by 1.2 ms, and the number of parameters were reduced by 8.7 %. The mAP of DHSW-YOLO under bright condition was 94.8 %, and that under dark condition was 93.6 %. This indicated that DHSW-YOLO could effectively monitor the behavior of WMD under bright and dark conditions. These results demonstrated that the lightweight and the optimization methods proposed in this paper are effective and provide a technical reference for the automated monitoring and warning system of duck flock behavior rhythms.