Automatic Recognition of Construction Worker Activities Using Dense Trajectories

Wide spread monitoring cameras on construction sites provide large amount of information for construction management. The emerging of computer vision and machine learning technologies enables automatic recognition of construction activities from videos. As the executors of construction, the activities of construction workers have strong impact on productivity and progress. Compared to machine work, manual work is more subjective and may differ largely in operation flow and productivity from one worker to another. Hence only a handful of work study on vision based activity recognition of construction workers. Lacking of publicly available datasets is one of the main reasons that currently hinder advancement. The paper studies manual work of construction workers comprehensively, selects 11 common types of activities and establishes a new real world video dataset with 1176 instances. For activity recognition, a cutting-edge video description method, dense trajectories, has been applied. Support vector machines are integrated with a bag-of-features pipeline for activity learning and classification. Performance on multiple types of descriptors (Histograms of Oriented Gradients - HOG, Histograms of Optical Flow - HOF, Motion Boundary Histogram - MBH) and their combination has been evaluated. Experimental results show that the proposed system has achieved a state-of-art performance on the new dataset.