Wen-Der Yu

Computer vision is increasingly used for fall safety monitoring, but it struggles in subtle hazard scenarios, causing delays in hazard detection. Therefore, this issue was addressed in this study using transfer learning on pre-trained models that were fine-tuned with target datasets to enhance accuracy. We tested two scenarios—“scaffolding transverse brace installation” and “correct safety lifeline hook-up”—with MobileNet v2, GoogleNet, Inception v3, and ResNet-50. GoogleNet achieved an accuracy of 95.2% in brace installation recognition, while MobileNet v2 and Inception v3 achieved an accuracy of 96% for lifeline hook-up recognition, demonstrating excellent capability in complex hazard detection.

Construction accidents are a major contributor to occupational fatalities. To tackle this issue, improved monitoring for hazard elimination is crucial. By introducing a deep-learning image captioning system, we identified hazards via closed-circuit television in construction sites. By leveraging Inception-v3 for feature extraction and the gated recurrent unit for caption generation, real-time hazard monitoring was enabled. Bilingual evaluation understudy scores were determined for continuous and effective hazard detection, helping construction managers enhance safety.

The emerging advances in deep learning and computer vision have enabled traditional cloud-based decision-making through edge computing with artificial intelligent internet of things (AIoT) image sensors (AIoT-IS). As a result, the timeliness and security of image recognition can be obtained. This study aims to develop an AIoT-IS-based smart safety control device for construction sites (“SmartCon” hereafter) for the operations of mobile cranes. The research is carried out to include the definition of hazardous control areas and the identification of unsafe scenarios for crane operations, the development of an intelligent prototype system for the safety control of lifting operations, system application demonstrations, and the evaluation of effectiveness. It is intended to assist labor inspection agencies and industry practitioners with a tool for monitoring lifting operations. The results of two empirical field tests show that the proposed SmartCon improves the safety monitoring of the operation of the machine through the real-time response to the identified potential risks on construction sites.