Falling from a height is the most common accident on construction sites. Vision-based techniques can be used to automatically monitor the construction sites and give early warnings. In this study, a lightweight object detection method, Efficient-YOLOv5, was proposed for detecting whether workers are wearing safety harnesses when working at height. Furthermore, a matching-recheck strategy was proposed to improve the mean average precision (mAP). The safety status evaluation model was designed to evaluate the safety status of workers in different construction scenarios. An edge computing-based security monitoring and alarm system suitable for deployment on construction sites was proposed to assist manual management. Efficient-YOLOv5 was trained and evaluated on our newly created dataset. Experiments demonstrated that our proposed method outperformed other comparison methods, as the precision and recall rates were 97.7% and 89.3%, respectively. The mAP was 94%. The rate of frames per second (FPS) was 72, which met real-time application requirements. Thus, the proposed method could easily be applied in the construction industry.

Cyber physical system (CPS) is a complex system combining computation, network and physics; object tracking is an important application of CPS. To solve the problem that the traditional kernel correlation filtering tracking algorithm cannot recover the lost object, the authors propose a re-detection object tracking algorithm. The proposed algorithm mainly designs a new adaptive detection criterion. By comparing the value of detection criterion and the value of the experience threshold, it can be judged whether the current target is lost or not. When the object tracking fails, the proposed method can generate target candidate boxes by using the edge boxes algorithm and select the best target location by applying the non-maximum suppression and the Euclidean metric methods. In addition, a fast multi-scale estimation method and an adaptive updating method are added to the tracking procedure to further improve the overall performance of the algorithm. Experimental results show that the proposed approach has a good performance in terms of precision and success rates.