Measuring Bridge Construction Efficiency Using the Wireless Real-Time Video Monitoring System

Abstract

To enhance the efficiency of bridge construction, the wireless real-time video monitoring system (WRITE) was developed. Utilizing the advanced technologies of computer vision and artificial neural networks, the developed system first wirelessly acquired a sequence of images of work-face operations. Then human pose analyzing algorithms processed these images in real time to generate human poses associated with construction workers who performed the operations. Next, a portion of the human poses were manually classified into three categories as effective work, contributory work, and ineffective work and were used to train the built-in artificial neural networks (ANN). Finally, the trained neural networks were employed to decide the ongoing laborers’ working status by comparing the in coming images to the developed human poses. The developed system was tested for accuracy on a bridge construction project. Results of the test showed that efficiency measurements by the system were reasonably accurate when compared to the measurements produced by the manual method. Thus, the success of this research indicates promise for enabling project managers to quickly identify work-face operation problems and to take actions immediately to address these problems.