Computer vision applications in construction: Current state, opportunities & challenges

Construction safety is a matter of great concern for both practitioners and researchers world-wide. Even after enough risk assessments and implementations of adequate controls on the work environments, construction workers are still subject to safety hazards. The need for personal protective equipment (PPE) becomes important in this context. Automatic and real-time detection of non-compliance of workers towards PPE is an important concern. The developments in the field of computer vision and data analytics, especially using deep learning algorithms have the potential to address this challenge in construction. Through this study a framework is developed to sense in real time, the safety compliance of construction workers with respect to PPE, thereby allowing to integrate this framework into the safety workflow of an organization. The study makes use Convolutional Neural Networks model developed by applying transfer learning to a base version of YOLOv3 deep learning network. Based on the presence of hardhat and safety jacket, the model predicts the compliance in four categories such as NOT SAFE, SAFE, NoHardHat and NoJacket. A data set of 2509 images collected from video recordings from several construction sites and web-based collection has been used to train the model. The model reported an F1 score of 0.96 with an average precision and recall rates at 96% on test data set. Once a non “SAFE” category is detected by the model, an alarm and a time-stamped report are also incorporated to enable a real-time integration and adoption on the construction sites. Overall, the study provides evidence on the feasibility and utility of computer vision-based techniques in automating the safety related compliance processes at construction sites.

/pdf/detection-of-personal-protective-equipment-ppe-compliance-on-2an2xe7app.pdf

Detection of Personal Protective Equipment (PPE) Compliance on Construction Site Using Computer Vision Based Deep Learning Techniques

Safety is an essential topic to the architecture, engineering and construction (AEC) industry. However, traditional methods for structural health monitoring (SHM) and jobsite safety management (JSM) are not only inefficient, but also costly. In the past decade, scholars have developed a wide range of deep learning (DL) applications to address automated structure inspection and on-site safety monitoring, such as the identification of structural defects, deterioration patterns, unsafe workforce behaviors and latent risk factors. Although numerous studies have examined the effectiveness of the DL methodology, there has not been one comprehensive, systematic, evidence-based review of all individual articles that investigate the effectiveness of using DL in the SHM and JSM industry to date, nor has there been an examination of this body of evidence in regard to these methodological problems. Therefore, the objective of this paper is to disclose the state of the art of current research progress and determine the relevant gaps, challenges and future work. Methodically, CiteSpace was employed to summarize the research trends, advancements and frontiers of DL applications from 2010 to 2020. Next, an application-focused literature review was conducted, which led to a summary of research gaps, recommendations and future research directions. Overall, this review gains insight into SHM and JSM and aims to help researchers formulate more types of effective DL applications which have not been addressed sufficiently for the time being.

Deep Learning-Based Applications for Safety Management in the AEC Industry: A Review

Tag and IoT based safety hook monitoring for prevention of falls from height

Deep-learning-based visual data analytics for smart construction management

The construction industry is one of the most hazardous industries suffering from a high on-site accident rate. A lot of safety hazards result from dynamic activities of construction workers and equipment. Therefore, tracking the location and motion of workers and equipment as well as identifying the interaction between them are crucial to preventing safety hazards on construction sites. Currently, with the extensive installation of surveillance cameras, computer vision techniques can be applied to process the videos and images captured on construction sites, which can be used to monitor site safety and to identify potential hazards. With the aim to predict and prevent the safety hazards among workers and equipment, this paper proposes a methodology to monitor and analyse the interaction between workers and equipment by detecting their locations and trajectories and identifying the danger zones using computer vision and deep learning techniques. First, workers and construction equipment are automatically located from cameras and classified by a deep region-based convolutional neural network (R-CNN) model. Then, the location and classification results are further processed by another CNN-based model to obtain trajectories of those objects. Based on the detection and trajectories, the spatial-temporal relationship between workers and equipment is analysed, from which the danger zones for the workers are identified and the corresponding safety alarms are generated. Experiments are conducted to demonstrate the capability of the proposed methodology for accurately identifying and predicting safety hazards among construction workers and equipment, which can contribute to the safety conditions on construction sites.

Sudip Kumar

Papers

Predicting Safety Hazards Among Construction Workers and Equipment Using Computer Vision and Deep Learning Techniques