Key points are not available for this paper at this time.
Modern intensive duck farming has improved production efficiency while facing health problems for ducks. As duck behaviors are closely related to their health status, accurately monitoring their behaviors is necessary. With the development of artificial intelligence (AI), the application of AI offers an effective approach to animal behavior recognition. Currently, accurately recognizing duck behaviors consistently from day to night remains a challenge. This challenge stems from the persistent dynamic changes in light, which can lead to significant performance degradation in conventional behavior recognition methods. To overcome this challenge, this study proposes an enhanced You Only Look Once version 11 small (YOLOv11s) with frequency feature enhancement and illumination perception for duck behavior recognition in dynamic light scenarios (FIY4DBR). Specifically, to tackle the problem of unclear edge, texture, and behavior characteristics of ducks in the low-light condition, a frequency feature enhancement mechanism (FFEM) is designed, which effectively enhances the duck feature representation ability. Additionally, to improve the model’s robustness to light variations, an illumination perception mechanism (IPM) is developed, which adjusts the contrast of objects and background features according to different brightness conditions, thereby enhancing the model’s generalization capability across different brightness scenarios. Experimental simulations on the self-built dataset show that FIY4DBR achieves an average recognition precision of 92.0% and recall of 88.8%, representing improvements of 1.8 and 3.6 percentage points over the baseline YOLOv11s. This demonstrates that the proposed FIY4DBR provides a high-precision and highly adaptive solution for intelligent livestock behavior monitoring, contributing to advancing the development of intelligent farming technologies.
Zhang et al. (Mon,) studied this question.