Automatic Scaffolding Workface Assessment for Activity Analysis through Machine Learning

Abstract

Scaffolding serves as one construction trade with high importance. However, scaffolding suffers from low productivity and high cost in Australia. Activity Analysis is a continuous procedure of assessing and improving the amount of time that craft workers spend on one single construction trade, which is a functional method for monitoring onsite operation and analyzing conditions causing delays or productivity decline. Workface assessment is an initial step for activity analysis to manually record the time that workers spend on each activity category. This paper proposes a method of automatic scaffolding workface assessment using a 2D video camera to capture scaffolding activities and the model of key joints and skeleton extraction, as well as machine learning classifiers, were used for activity classification. Additionally, a case study was conducted and showed that the proposed method is a feasible and practical way for automatic scaffolding workface assessment.

Activity sampling in the construction industry: a review and research agenda

“…Hence, researchers have recently extensively researched automated data collection to replace the manual activity sampling method. The primary purpose is to minimise human intervention in the data collection, thereby minimising the cost and workforce consumption (Jiang et al, 2015;Joshua and Varghese, 2014;Luo et al, 2018;Teizer et al, 2013;Ying et al, 2021). However, because of the different tools used for traditional and automated activity sampling, automated activity sampling works slightly differently than traditional practice.…”

“…Since this feature technique interprets fine motions of labour, the labour activities are commonly categorised at level 3 (Ishioka et al, 2020;Yang et al, 2015Yang et al, , 2016. As summarised in Table 3, computer vision-based activity sampling has been conducted onsite for different construction activities such as formwork (Luo et al, 2018), rebar installation (Bai et al, 2012), concreting, carpentry (Liu and Golparvar-Fard, 2015b), scaffolding (Ying et al, 2021), bricklaying (Roberts et al, 2020) and several common construction activities. However, the findings from previous studies depict that several challenges still hinder computer visionbased activity sampling from being practical in the construction industry.…”

“…, 2018), rebar installation (Bai et al. , 2012), concreting, carpentry (Liu and Golparvar-Fard, 2015b), scaffolding (Ying et al. , 2021), bricklaying (Roberts et al.…”

Current Status and Future Research Trends of Construction Labor Productivity Monitoring: A Bibliometric Review

“…Further research is required to standardize the definitions and methodologies for measuring workflow variability. Additionally, the advancement of technology has transformed traditional work sampling into automated work sampling, with computer vision [28,82] and wearable sensors [83,84] showing potential for monitoring the physical and physiological conditions of labor. However, further investigation is required to ascertain the reliability and effectiveness of these technologies for real-world construction projects.…”

“…CLP is influenced by a range of factors, both technological and non-technological. Technological advancements, such as the adoption of Building Information Modeling (BIM) [9,22], sensor technologies [23,24], computer vision technologies [25,26], and data analytics tools [27,28], have revolutionized CLP monitoring. Non-technological factors, such as workforce characteristics (such as skill levels, experience, well-being, and motivation), project-related elements (such as task complexity, material shortage, project type, and finances) [8,29,30], as well as external factors (including weather conditions and regulatory requirements) [13,31,32], significantly contribute alongside technological factors.…”