RESEARCH ON PERSON IDENTIFICATION AT CONSTRUCTION SITES USING DEEP LEARNING

Abstract

 In recent years, the number of surveillance cameras installed in towns and commercial facilities has been increasing steadily. By identifying and tracking people captured by each camera, an improvement in the efficiency of criminal investigations or flow analysis within facilities can be expected. Moreover, applying cameras to construction sites enables operators working there to recognise their invasion into dangerous places with risks of falling or tumbling as well as recording near-misses with construction machinery, thus improving safety management. To realize these goals, it is necessary to implement the technology of automatic person identification.

 Many existing studies have applied deep learning in recent years, which reports that face authentication, gait identification, and human identification lead to results with a higher precision than ever before. On construction sites, however, it may not be possible to apply the existing technology as operators’ clothes tend to be similar to each other and it is necessary to identify construction machines. In this study, we propose a method for human identification based on the convolutional neural network of deep learning with excellent image recognition, with special attention to drawing patterns on items that operators always wear on construction sites such as safety vests and helmets. Evaluation experiments were conducted to verify identification precision, and prove the applicability of the proposed method for the safety management of construction sites.