Search

Abnormal activities on construction jobsites may compromise productivity and pose threat to workers' safety. This paper proposes the analysis of consecutive image sequences for automatic identification of irregular operations and their visualization. The data analytics is composed of four steps: object detection, object tracking, action recognition, and operational analysis. The Faster Region-proposal Convolutional Neural Network (Faster R-CNN) is adapted with transfer learning for detection of workers and pieces of construction equipment on the jobsite, while the Simple Online and Realtime Tracking (SORT) approach is applied for object tracking. A hybrid model integrating CNN and Long Short Term Memory (LSTM) is employed for action recognition. An alternative form of the Crew-balance Chart (CBC), called line chart in which anomalies are pre-screened, is utilized for recognized actions. Validation was carried out with earthmoving operations. The trained Faster R-CNN reached a 73% Average Precision (AP), and the SORT algorithm modified by this work successfully reduced identity switches. Irregular operations in the testing videos were identified, and truck exchanges were filtered. In addition, an activity log was produced with basic information along with starting and ending times of the identified irregular operations. With the line chart and the log provided by the proposed framework, field managers can efficiently identify potential abnormal activities, providing the opportunity for further investigations and adjustments accordingly.

Multiple construction worker tracking is an active research area critical to the planning of the job site. Challenges in multiple construction worker tracking include miss detection and mismatch due to occlusion and identity switches. To the best knowledge of the authors, the mismatch is not reported in the literature of construction for image based single camera multiple worker tracking. As a result, the mismatch should be taken into account through a representative performance index such as the Multi-Object Tracking Accuracy (MOTA). This work aims to improve the performance of the current multiple worker tracking through an approach composed of three stages: detection, matching and re-matching. In the detection stage, the deep learning detector, Mask R-CNN, is utilized. In the matching stage, we attempt to track workers between consecutive image frames through a gradient based method with feature based comparison. Several cost means and matching methods have been experimented for model selection. Trajectories of tracking objects are derived in this stage. The best cost measurements and matching methods are recommended. Trajectories of tracking objects could be interrupted because of miss detection or mismatch. We call those broken trajectories, without matched detections, orphans. In the re-matching stage, we attempt to recover unmatched detections in the current frame with previous orphans based on extracted features. A competitive MOTA of 56.7% was obtained from the proposed approach over MOTA of 55.9% from the state-of-the-art Detect-And-Track model on a human tracking benchmark dataset. On construction job sites, we have tested the approach with 4 testing videos, resulting in a total MOTA of 81.8%, average MOTA per video of 79.0% and standard deviation of 13.0%, while the maximum and minimum MOTAs are 96.0% and 69.0%, respectively. As a result, the proposed work could potentially provide better multiple worker tracking on the construction job site. Additionally, to have a better representation of the tracking errors, this work suggests to utilize the MOTA for multiple construction worker tracking.

The morality rate of patients with out-of-hospital cardiac arrest (OHCA) is 92%. Public Access Defibrillation before the arrival of emergency medical services is critical in increasing the survival rate of patients with OHCA. The American Heart Association recommends to install automated external defibrillators (AEDs) in areas that are crowded regularly or during specific times and events, including airports, stations, stadiums, schools, offices, and shopping malls. While the importance of deploying AEDs in public areas is widely accepted, the impact of the specific locations and quantities of these AEDs, in terms of efficiency, remains largely un-evaluated. We propose to evaluate the in-building travels through a network, particularly to avoid penetrating the structural obstacles (walls, corners, floors and ceilings), with the aid of Building Information Modeling (BIM) models. The constructed network enables four main decision models in this work: 1) efficient routing to access an AED, 2) optimal location planning of AEDs, 3) a coverage targeting model that finds suitable numbers of AEDs and their corresponding locations, and 4) an AED placement evaluation model. A case study is presented for an actual building, and the coverage rate is increased from 28.33% to 50% given the same amount of AED through the proposed approach.

After an eXtreme Event (XE) hits an urban area, well-organized response operations are required to mitigate the chaotic situation. Efficient allocation of resources such as construction equipment is critical to the performance of disaster response operations. This paper presents a Geographic Information System (GIS) based framework that facilitates equipment allocation in response to disasters. The framework is composed of three subsystems to facilitate information gathering and decision making for equipment distribution. First, an application that runs on mobile devices for on-field resource request is developed. Second, a resource repository is implemented with a geosaptial database that enables spatial query of resources with a graphical interface. In addition, a GIS which enables automated decision making such as resource matching and route finding for resource distribution is presented. Integration of decision models into the framework to support complex decision making for equipment distribution is also proposed. With the framework in place, disaster response operations could become more efficient. Simulated test cases have been carried out for Champaign, IL, the City of Chicago and the New York City. Future research will be directed towards further expansion and validation of the framework through interaction with emergency management agencies in the US.