Cattle rumination behavior is strongly correlated with its health. Current methods often rely on manual observation or wearable devices to monitor ruminating behavior. However, the manual monitoring of cattle rumination is labor-intensive, and wearable devices often harm animals. Therefore, this study proposes a non-contact method for monitoring cattle rumination behavior, utilizing an improved YOLOv8-pose keypoint detection algorithm combined with multi-condition threshold peak detection to automatically identify chewing counts. First, we tracked and recorded the cattle’s rumination behavior to build a dataset. Next, we used the improved model to capture keypoint information on the cattle. By constructing the rumination motion curve from the keypoint information and applying multi-condition threshold peak detection, we counted the chewing instances. Finally, we designed a comprehensive cattle rumination detection framework to track various rumination indicators, including chewing counts, rumination duration, and chewing frequency. In keypoint detection, our modified YOLOv8-pose achieved a 96% mAP, an improvement of 2.8%, with precision and recall increasing by 4.5% and 4.2%, enabling the more accurate capture of keypoint information. For rumination analysis, we tested ten video clips and compared the results with actual data. The experimental results showed an average chewing count error of 5.6% and a standard error of 2.23%, verifying the feasibility and effectiveness of using keypoint detection technology to analyze cattle rumination behavior. These physiological indicators of rumination behavior allow for the quicker detection of abnormalities in cattle’s rumination activities, helping managers make informed decisions. Ultimately, the proposed method not only accurately monitors cattle rumination behavior but also provides technical support for precision management in animal husbandry, promoting the development of modern livestock farming.

The sleeping and eating behaviors of horses are important indicators of their health. With the development of the modern equine industry, timely monitoring and analysis of these behaviors can provide valuable data for assessing the physiological state of horses. To recognize horse behaviors in stalls, this study builds on the SlowFast algorithm, introducing a novel loss function to address data imbalance and integrating an SE attention module in the SlowFast algorithm’s slow pathway to enhance behavior recognition accuracy. Additionally, YOLOX is employed to replace the original target detection algorithm in the SlowFast network, reducing recognition time during the video analysis phase and improving detection efficiency. The improved SlowFast algorithm achieves automatic recognition of horse behaviors in stalls. The accuracy in identifying three postures—standing, sternal recumbency, and lateral recumbency—is 92.73%, 91.87%, and 92.58%, respectively. It also shows high accuracy in recognizing two behaviors—sleeping and eating—achieving 93.56% and 98.77%. The model’s best overall accuracy reaches 93.90%. Experiments show that the horse behavior recognition method based on the improved SlowFast algorithm proposed in this study is capable of accurately identifying horse behaviors in video data sequences, achieving recognition of multiple horses’ sleeping and eating behaviors. Additionally, this research provides data support for livestock managers in evaluating horse health conditions, contributing to advancements in modern intelligent horse breeding practices.

Foal nursing behavior is a crucial indicator of healthy growth. The mare being in a standing posture and the foal being in a suckling posture are important markers for foal suckling behavior. To enable the recognition of a mare’s standing posture and its foal’s suckling posture in stalls, this paper proposes an RT-DETR-Foalnursing model based on RT-DETR. The model employs SACGNet as the backbone to enhance the efficiency of image feature extraction. Furthermore, by incorporating a multiscale multihead attention module and a channel attention module into the Adaptive Instance Feature Integration (AIFI), the model strengthens feature utilization and integration capabilities, thereby improving recognition accuracy. Experimental results demonstrate that the improved RT-DETR achieves a best mAP@50 of 98.5%, increasing by 1.8% compared to the RT-DETR. Additionally, this study achieves real-time statistical analysis of the duration of the foal in the suckling posture, which is one of the important indicators for determining whether the foal is suckling. This has significant implications for the healthy growth of foals.

The sleeping and grazing behaviors of horses play a crucial role in their health and welfare. In the horse industry, with the prevalent trend of individual single-stall farming in stable, accurately identifying various behaviors of horses within stables is imperative. This study has established a spatio-temporal dataset for horse postures and behaviors, proposed an algorithm utilizing a SE-SlowFast network with an enhanced loss function. This algorithm achieves automatic recognition of multiple postures and behaviors of horse simultaneously. The model developed in this study demonstrates high accuracy in identifying three postures within the stable: Standing, Crouching, and Lying, achieving respective accuracies of 92.73%, 91.87%, and 92.58%. Additionally, it accurately recognizes two behaviors: Sleeping and Grazing, achieving best accuracies of 93.56% and 98.77%. The overall best accuracy of the model is 93.9%. Experiments on video recognition confirm that the suggested model recognizes horse video data accurately. This study marks the first time computer vision technology has been used in the horse farming industry, achieving non-intrusive recognition of multiple horse postures and behaviors. This study provides valuable data support for livestock managers to evaluate the health conditions of horses, enhances the welfare of horses in stables, and contributes to the advancement of modern horse husbandry practices.