Real-time estrus detection in cattle using deep learning-based pose estimation

Accurate estrus detection is of paramount importance for optimizing the reproductive efficiency of livestock. Traditional methods are often labor-intensive and subjective. The cow estrus period, which only lasts 12-24 hours in a cycle that repeats every 18-24 days, causes the opportunity to mate or perform artificial insemination to be missed. This study proposes a novel approach that utilizes pose estimation with a deep learning model for real-time estrus detection in female cows. We collected a dataset of annotated images of cows at different estrus stages and developed a deep learning model based on the EfficientPose architecture. The cow estrus parameter analyzed was locomotion activity, which was categorized into lying down and standing classes with an integrated system and LCD-displayed detection results. The Jetson Nano and YOLOv5 algorithms processed the input parameter data with a mean average precision (mAP) of 0.8 and a final loss prediction value of 0.01. If the female cow is classified as active (number of lying down classes < 57,600 classes/h), then the cow is considered to be in the estrus period. This system provides reliable and non-invasive estrus detection, enabling timely intervention for improved reproductive management in cattle farming.