Detecting Hook Attachments of a Safety Harness Using Inertial Measurement Unit Sensors

Construction workers are required to wear a safety harness while working at height, and safety managers need to ensure that a safety hook is attached to proper anchorage points to prevent falls from height. However, it is difficult for the managers to monitor all the worker's hook attachments continuously and remotely in dynamic workplace environments. This study developed an approach to detect an individual worker's hook attachments by assessing the relative movements between the hook and the worker's body. An Inertial Measurement Unit sensor was attached to the hook and the body strap to monitor the relative movements. The collected IMU data was transformed into image data by Markov Transition Field. The detection algorithm was developed based on the convolution neural networks that classify the worker's postures, activities, and hook attachments simultaneously, and the developed detection system provided classification accuracies of 86.40%, 86.97%, and 96.58, respectively. The results validated that the relative movement between the hook and the worker's body is a key feature for hook attachment detection.