Crowdsourced reliable labeling of safety-rule violations on images of complex construction scenes for advanced vision-based workplace safety

Wang, Yanyu; Liao, Pin; Zhang, Cheng; Ren, Yi; Sun, Xinlu; Tang, Pingbo

doi:10.1016/j.aei.2019.101001

Cited by 28 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, the wages of these experts could be much higher than ordinary annotators. To save annotation costs, some studies proposed to use crowdsourcing for data annotation (Liu & Golparvar‐Fard, 2015; Wang et al., 2019). Nonetheless, it is difficult to ensure the annotation quality especially when there are many complex rules in the guideline.…”

Section: Methodsmentioning

confidence: 99%

Informativeness‐guided active learning for deep learning–based façade defects detection

Guo

Wang

et al. 2023

Computer aided Civil Eng

View full text Add to dashboard Cite

Annotation work is burdensome and challenging for developing a façade defects detector, especially when the raw data set is large but not all useful. To alleviate the problem, this study proposes an informativeness‐guided active learning methodology to effectively select informative data to train a robust façade defects detector. A novel data annotation workflow is developed to ensure the high quality of labels. Then, an active learning–based model training strategy is adopted to enable the model to have both the abilities of generalization and discrimination on different defect features. Besides, an innovative informativeness assessment method is proposed by flexibly combining the degree of uncertainty and the degree of representativeness. Through the proposed method, the performance of façade defects detection can be further boosted with the same amount but more informative training data so that the cost‐efficiency of human annotation work can be improved.

show abstract

Section: Methodsmentioning

confidence: 99%

Informativeness‐guided active learning for deep learning–based façade defects detection

Guo

Wang

et al. 2023

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…To further explore the hotspots and the inter-relationship of these topics, the top ten documents of each of these topics were shortlisted and investigated for more details. Object tracking was primarily conducted with the help of sensors [48,49], computer vision techniques [50][51][52], and other real-time technologies [53]; real-time technologies have been widely adopted for various safety-related monitoring tasks on the job site [48,[54][55][56][57][58][59]; machine learning (or deep learning) algorithms have been commonly utilized to understand and classify accident narratives or safety reports [60][61][62][63] and predict injury severity and outcomes [64][65][66][67]; computer vision techniques have been frequently leveraged for safety equipment monitoring [68][69][70] and unsafe behavior detection [71][72][73]; and structural equation modeling has been generally adopted to understand the relationship between safety and health performance and various other factors like stress [74,75], safety culture and climate [76,77], psycholog- Despite the rapid growth and increasing popularity of the above-mentioned emerging topics, many of the traditional topics have not lost their momentum yet. For example, safety climate has been continuously recognized as a critical factor in safety performance [81,82] and has influenced workers' behaviors through organizational structure [83,84] and supervisors' management …”

Section: Research Trends and Insightsmentioning

confidence: 99%

Discovering the Research Topics on Construction Safety and Health Using Semi-Supervised Topic Modeling

et al. 2023

View full text Add to dashboard Cite

Safety and health have been one of the major issues in the construction industry worldwide for decades, and the relevant research has correspondingly drawn much attention in the academic field. Considering the expanding size and increasing heterogeneity of this research field, this paper proposes the topic modeling approach to cluster latent topics, extract coherent keywords, and discover evolving trends over the past three decades. Focusing on a total of 1984 articles published in 27 different journal sources until February 2023, this paper applied both unsupervised topic modeling techniques—Latent Dirichlet Allocation (LDA) and Correlation Explanation (CorEx)—and their semi-supervised versions—Guided LDA and Anchored CorEx. The evolving trends and inter-relationship of 15 research topics generated by the Anchored CorEx model (the best-performing model) were analyzed. Top-listed documents of major topics were analyzed to discuss their standalone research focuses. The results of this paper provided helpful insights and implications of existing research and offered potential guides for future research on construction safety and health by helping researchers (1) select research topics of interest and clearing decaying topics; (2) extract the top words of each research topic using systematic approaches; and (3) explore the interconnection of different research topics as well as their standalone focuses.

show abstract

“…Many researchers have utilized state-of-the-art deep neural networks in various applications, including personal protective equipment detection (Wu et al, 2019), sewer pipe defect detection (Yin et al, 2020), water leak inspection (Chen et al, 2020) and construction machine detection (Xiao and Kang, 2021). Large quantities of images are necessary for training these "data-hungry" deep learning methods to achieve high detection accuracy (Wang et al, 2019). For example, Wu et al (2019) collected 3,174 images containing 18,893 hardhat instances for constructing the hardhat wearing detection benchmark dataset and achieved 83.89% mean average precision (mAP) while using the SDD model.…”

Section: Object Detection Applications In Constructionmentioning

confidence: 99%

Machine learning using synthetic images for detecting dust emissions on construction sites

Xiong

Tang

2021

SASBE

Self Cite

View full text Add to dashboard Cite

PurposeAutomated dust monitoring in workplaces helps provide timely alerts to over-exposed workers and effective mitigation measures for proactive dust control. However, the cluttered nature of construction sites poses a practical challenge to obtain enough high-quality images in the real world. The study aims to establish a framework that overcomes the challenges of lacking sufficient imagery data (“data-hungry problem”) for training computer vision algorithms to monitor construction dust.Design/methodology/approachThis study develops a synthetic image generation method that incorporates virtual environments of construction dust for producing training samples. Three state-of-the-art object detection algorithms, including Faster-RCNN, you only look once (YOLO) and single shot detection (SSD), are trained using solely synthetic images. Finally, this research provides a comparative analysis of object detection algorithms for real-world dust monitoring regarding the accuracy and computational efficiency.FindingsThis study creates a construction dust emission (CDE) dataset consisting of 3,860 synthetic dust images as the training dataset and 1,015 real-world images as the testing dataset. The YOLO-v3 model achieves the best performance with a 0.93 F1 score and 31.44 fps among all three object detection models. The experimental results indicate that training dust detection algorithms with only synthetic images can achieve acceptable performance on real-world images.Originality/valueThis study provides insights into two questions: (1) how synthetic images could help train dust detection models to overcome data-hungry problems and (2) how well state-of-the-art deep learning algorithms can detect nonrigid construction dust.

show abstract

Crowdsourced reliable labeling of safety-rule violations on images of complex construction scenes for advanced vision-based workplace safety

Cited by 28 publications

References 32 publications

Informativeness‐guided active learning for deep learning–based façade defects detection

Informativeness‐guided active learning for deep learning–based façade defects detection

Discovering the Research Topics on Construction Safety and Health Using Semi-Supervised Topic Modeling

Machine learning using synthetic images for detecting dust emissions on construction sites

Contact Info

Product

Resources

About