Vision-Based Crane Tracking for Understanding Construction Activity

Visual monitoring of construction work sites through the installation of surveillance cameras has become prevalent in the construction industry. Cameras also have practical utility for automatic observation of construction events and activities. This paper demonstrates the use of a surveillance camera for assessing tower crane activities during the course of a work day. The jib angle and the trolley position are tracked using 2D-3D rigid pose estimation and density-based tracking algorithms, respectively. A finite-state machine model for crane activity is designed to process the track signals and recognize crane activity as belonging to one of the two categories: concrete pouring and non-concrete material movement. Experimental results from a construction surveillance camera show that crane activities are correctly identified.