Abstract
Accurate recognition of personnel behavior in industrial environments is essential for asset protection and workplace safety, yet complex environmental conditions pose a significant challenge to its accuracy. This paper presents a novel, lightweight framework to address these issues. We first enhance a YOLOv8n model with Receptive Field Attention Convolution (RFAConv) and Efficient Multi-scale Attention (EMA) mechanisms, achieving a 6.9% increase in AP50 and a 4.2% increase in AP50:95 over the baseline. Continuous motion trajectories are then generated using the BOT-SORT algorithm and geometrically corrected via perspective transformation to produce a high-fidelity bird's-eye view. Finally, a set of discriminative trajectory features is classified using a Random Forest model, attaining F1-scores exceeding 82% for all behaviors on our proprietary industrial dataset. The proposed framework provides a robust and efficient solution for real-time personnel behavior recognition in challenging industrial settings. Future work will focus on exploring more advanced algorithms and validating the framework's performance on edge devices.