scispace - formally typeset
Open AccessJournal ArticleDOI

Knowledge graph for identifying hazards on construction sites: Integrating computer vision with ontology

Weili Fang, +5 more
- 01 Nov 2020 - 
- Vol. 119, pp 103310
TLDR
This paper integrates computer vision algorithms with ontology models to develop a knowledge graph that can automatically and accurately recognise hazards while adhering to safety regulations, even when they are subjected to change.
About: 
This article is published in Automation in Construction.The article was published on 2020-11-01 and is currently open access. It has received 73 citations till now. The article focuses on the topics: Knowledge extraction.

read more

Figures
Citations
More filters
Journal ArticleDOI

Semi‐supervised learning based on convolutional neural network and uncertainty filter for façade defects classification

Jingjing Guo, +2 more
- 01 Mar 2021 - 
TL;DR: A semi‐supervised learning algorithm that uses only a small amount of labeled data for training, but still achieves high classification accuracy is proposed, and a novel uncertainty filter to select reliable unlabeled data for initial training epochs is developed to further improve the classification accuracy.
Journal ArticleDOI

Ontology-based knowledge representation for industrial megaprojects analytics using linked data and the semantic web

Pouya Zangeneh, +1 more
- 01 Oct 2020 - 
TL;DR: The proposed Uniform Project Ontology, or UPonto, provides a data infrastructure for project analytics by enabling logical deductions and inferences, and flexible expansion and partitioning of the data utilizing linked data and the semantic web.
Journal ArticleDOI

Combining computer vision with semantic reasoning for on-site safety management in construction

Haitao Wu, +5 more
- 01 Oct 2021 - 
TL;DR: Results show that the proposed framework operates similar to the thinking model of safety managers and can facilitate on-site hazard identification and prevention by semantically reasoning hazards from images and listing corresponding mitigations.
Journal ArticleDOI

Real-time mixed reality-based visual warning for construction workforce safety

Shao Yu Wu, +3 more
- 01 Jul 2022 - 
TL;DR: Wang et al. as mentioned in this paper integrated Digital Twin (DT), Deep Learning (DL), and Mixed Reality (MR) technologies into a newly developed real-time visual warning system, which enables construction workers to proactively determine their safety status and avoid accidents.
Journal ArticleDOI

Video2Entities: A computer vision-based entity extraction framework for updating the architecture, engineering and construction industry knowledge graphs

Pan Zaolin, +3 more
- 01 May 2021 - 
TL;DR: This paper integrates zero-shot learning techniques with general KGs to present a novel framework called “video2entities” that can extract entities from videos to update the AEC KG and combines the perceptual capabilities of computer vision with the cognitive capabilities of KG to improve the accuracy and timeliness of KGs updates.
References
More filters
Proceedings ArticleDOI

ImageNet: A large-scale hierarchical image database

Jia Deng, +5 more
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI

Deep learning

Yann LeCun, +4 more
- 28 May 2015 - 
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Journal ArticleDOI

Distinctive Image Features from Scale-Invariant Keypoints

David G. Lowe
- 01 Nov 2004 - 
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Book

Deep Learning

Ian Goodfellow, +2 more
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Proceedings ArticleDOI

Histograms of oriented gradients for human detection

Navneet Dalal, +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Related Papers (5)

Detecting non-hardhat-use by a deep learning method from far-field surveillance videos

Qi Fang, +7 more
- 01 Jan 2018 - 

A deep hybrid learning model to detect unsafe behavior: Integrating convolution neural networks and long short-term memory

Lieyun Ding, +5 more
- 01 Feb 2018 - 

A deep learning-based approach for mitigating falls from height with computer vision: Convolutional neural network

Weili Fang, +7 more
- 01 Jan 2019 - 

Using ontology-based text classification to assist Job Hazard Analysis

Nai-Wen Chi, +2 more
- 01 Oct 2014 - 

An ontological approach to identify the causes of hazards for safety-critical systems

Jiale Zhou, +3 more
Frequently Asked Questions (1)
Q1. What are the contributions in this paper?

This paper integrates computer vision 39 algorithms with ontology models to develop a knowledge graph that can automatically 40 and accurately recognise hazards while adhering to safety regulations, even when they 41 are subjected to change. The authors focus on the detection of hazards associated with FFH as an example 44 to illustrate their proposed approach. The authors also demonstrate that their approach can 45 successfully detect FFH hazards in varying contexts from images. 

Trending Questions (2)
What are the risks and effects of electrical hazards in construction sites?

The paper does not provide information about the risks and effects of electrical hazards in construction sites. The paper focuses on integrating computer vision with ontology models to develop a knowledge graph for hazard identification.

See answers from 5 other papers  
What would be the future work after knowledge of graph construction and ontology?

The future work after constructing the knowledge graph and ontology would involve applying the approach to other types of hazards on construction sites.

See answers from 5 other papers