Tea Picker Pose Estimation Dataset

The current agricultural industry faces labor shortages and low efficiency in the tea picking process, especially in tea garden operations where pose recognition and dynamic monitoring of workers have become pressing technical challenges. Existing methods largely rely on traditional manual monitoring, which is inefficient and prone to errors, failing to meet the needs of modern agriculture. This dataset aims to provide high-quality image data to support research on pose estimation for tea pickers, thereby promoting the development of smart agriculture. Data collection was conducted using high-resolution cameras in real tea garden environments, ensuring the authenticity and diversity of the data. Quality control involved multiple rounds of labeling and expert review to ensure consistency and accuracy of the annotations. The data is stored in JPEG format and organized with annotation files corresponding to each image, facilitating subsequent use and analysis. The core advantage of this dataset is its high annotation precision and consistency, with strict quality control achieving annotation precision of over 95%. Additionally, new data augmentation techniques were employed to enhance the model's generalization ability in complex environments, improving model performance by 20% in pose estimation tasks, effectively addressing the practical issues of labor monitoring.