In this paper, we propose an excavator activity analysis and safety monitoring system, leveraging recent advancements in deep learning and computer vision. Our proposed system detects the surrounding environment and the excavators while estimating the poses and actions of the excavators. Compared to previous systems, our method achieves higher accuracy in object detection, pose estimation, and action recognition tasks. In addition, we build an excavator dataset using the Autonomous Excavator System (AES) on the waste disposal recycle scene to demonstrate the effectiveness of our system. We also evaluate our method on a benchmark construction dataset. The experimental results show that the proposed action recognition approach outperforms the state-of-the-art approaches on top-1 accuracy by about 5.18%.