Search

Tracking of construction site resources from on-site cameras using vision trackers has been proposed as a means to efficiently track a large number of objects operating in a congested environment. The systems proposed so far use first either a less accurate/faster motion detection approach or a more sophisticated object detection approach to mark the moving entities of interest in the camera view. The marked entities are then passed on to a vision tracker, who follows the entities in all subsequent frames. The major drawback of this two-step process is that the resulting tracking systems are very sensitive to changes and, in most cases, deteriorate and stop tracking effectively after only a few seconds/minutes. The reason is that it is common for construction resources to frequently a) enter/leave the field of view, b) be temporarily occluded, or c) significantly change their pose. To resolve this issue, this paper presents a hybrid method for locating construction workers that interchangeably fuses the methods of tracking and object detection. Specifically, the proposed approach continuously detects construction workers, and tracks them. Continuous detection allows a) for the detection of workers that enter the view or reappear after being occluded at any given time, b) for the effective termination of tracking when workers leave the view or become occluded, and c) for relocating the marked area and detection confidence to fit all object poses. On the other hand, continuous tracking allows for seamless tracking across time and smoothing of the temporal detection variations. The proposed approach was implemented into a C# prototype and tested on videos taken from construction sites in Atlanta, GA. The method could detect and track all workers, preserving stability under occlusions. It enhanced accuracy by 9.6% when compared to the use of a detection method only. This indicates that the proposed approach is a significant improvement over prior work and has the potential to effectively monitor the location of construction workers.

Construction is one of the most dangerous job sectors over the world. Any accidents that happen on the construction sites will bring the sufferings to the workers and their families and incur the delays and costs to the projects. Therefore, it is necessary for the contractors to monitor potential site safety issued and comply with existing safety regulations all the time. One of fundamental safety regulations is hardhat wearing. The wearing of the hardhats is always mandated and should not be violated anytime on the construction sites. In this paper, a novel method is proposed to facilitate the monitoring of whether any persons on the construction sites are wearing hardhats as required by the safety regulations. The method is built upon computer vision techniques. Under the method, human bodies and hardhats are first detected in the video frames captured by real-time on-site construction cameras. Then, their pair-wise matching is found. For those persons without the matching of the hardhats, they are identified as not wearing hardhats. The proposed method has been tested on real site videos. The test results showed that multiple persons could be monitored even if they are not wearing any real-time location sensors or tags. The test results demonstrate the potential of using live streaming or time-lapse construction site videos to facilitate the safety monitoring work on construction sites.