Abstract:Much of the developed world's construction workforce is increasing in average age, and yet construction workers typically retire well before they reach the age of sixty. One reason is that their bodies are worn out because of the nature of the work. We therefore face the challenge of both reducing their physical stress and increasing their productive work life, if we wish to avert an economic and social crunch given the demographic trends towards an aging population in most developed countries. In particular, … Show more
“…They focused on distinct actions such as fetch and spread mortar, fetch and lay brick, and fill joints. Alwasel and Haas (2011) developed a joint angle sensor system to detect workrelated musculoskeletal disorders (WMSDs). The main components of the system were a permanent magnet as a magnetic field source and a sensing element.…”
Section: Background Automatic Human Action Recognition In Constructionmentioning
confidence: 99%
“…The magnet is attached to a moving part, such as an upper arm, and a sensing part is attached to the torso. The sensor system detects the angle of the arm and monitors the worker's musculoskeletal disorders (Alwasel and Haas, 2011).…”
Section: Background Automatic Human Action Recognition In Constructionmentioning
This paper presents a novel action recognition method for observing human workers using interactions between actions and related objects on an internal construction site. This method can be used to measure work rates for labour productivity monitoring. This monitoring is critical because the performance of a construction project is significantly impacted by labour productivity. However, construction sites are generally crowded with a large number of workers and objects. Such congestion disrupts the accurate, automatic recognition of construction workers' actions. This congestion is one reason that existing automatic action recognition studies of construction areas mainly focus on workers' actions themselves. However, the crowded conditions mean that sites could offer a great deal of clues that could be used for automatic action recognition. According to psychological studies, interactions clearly take place between human actions and related objects, such as between hammering and a hammer. Humans use these interactions to recognize actions or objects more accurately. On the construction site, workers, materials, tools, and equipment are carefully planned out ahead of actual construction. The categories of workers and objects are pre-defined and, as noted, specific interactions define relations between worker actions and objects. In this paper, the interactions are limited to human workers and their hand-held objects. Action recognition results can be combined with hand-held object information to improve recognition accuracy. With the limited interactions, experiments in this paper show a significant improvement in action recognition. This paper describes the utilization of these interactions to improve construction action recognition accuracy based on human skeleton data and 2D color video from Microsoft KINECT sensor.
“…They focused on distinct actions such as fetch and spread mortar, fetch and lay brick, and fill joints. Alwasel and Haas (2011) developed a joint angle sensor system to detect workrelated musculoskeletal disorders (WMSDs). The main components of the system were a permanent magnet as a magnetic field source and a sensing element.…”
Section: Background Automatic Human Action Recognition In Constructionmentioning
confidence: 99%
“…The magnet is attached to a moving part, such as an upper arm, and a sensing part is attached to the torso. The sensor system detects the angle of the arm and monitors the worker's musculoskeletal disorders (Alwasel and Haas, 2011).…”
Section: Background Automatic Human Action Recognition In Constructionmentioning
This paper presents a novel action recognition method for observing human workers using interactions between actions and related objects on an internal construction site. This method can be used to measure work rates for labour productivity monitoring. This monitoring is critical because the performance of a construction project is significantly impacted by labour productivity. However, construction sites are generally crowded with a large number of workers and objects. Such congestion disrupts the accurate, automatic recognition of construction workers' actions. This congestion is one reason that existing automatic action recognition studies of construction areas mainly focus on workers' actions themselves. However, the crowded conditions mean that sites could offer a great deal of clues that could be used for automatic action recognition. According to psychological studies, interactions clearly take place between human actions and related objects, such as between hammering and a hammer. Humans use these interactions to recognize actions or objects more accurately. On the construction site, workers, materials, tools, and equipment are carefully planned out ahead of actual construction. The categories of workers and objects are pre-defined and, as noted, specific interactions define relations between worker actions and objects. In this paper, the interactions are limited to human workers and their hand-held objects. Action recognition results can be combined with hand-held object information to improve recognition accuracy. With the limited interactions, experiments in this paper show a significant improvement in action recognition. This paper describes the utilization of these interactions to improve construction action recognition accuracy based on human skeleton data and 2D color video from Microsoft KINECT sensor.
“…Due to the rapid growth of labor cost, increasing worker efficiency and reducing labor costs have become serious challenges in the architecture, engineering, and construction (AEC) field. Haas et al presented for a prototype of a simple, low-cost, sensing solution for automatically monitoring undesirable movements and patterns of motion to help reduce Construction Workrelated Musculoskeletal Disorders and help the workers work in a more efficient and safe way [9]. Gatti et al propose that assessing physical strain in construction workforce is the first step for improving Safety and productivity management [10].…”
Due to the increasing growth of labor cost, academics and practitioners in this field have focused on finding ways to improve work productivity. Many previous studies have indicated that mental status has a deep influence on productivity. However, the relationship among work productivity, psychological state, and physical status has not been explored in the field of architecture, engineering, and construction (ACE). As an initial exploration, this paper proposes a system to analyze how the psychological and physical status of construction workers influence their productivity. In this exploration, smart bands are adopted to measure the physical status of the bricklayers, STAI is used to collect the psychological data, and the time taken by construction workers to complete a unit of work (i.e., wall building) is recorded to reflect work productivity. Analysis on the correlations of the three dimensions (work productivity, psychological state, and physical status) was conducted. The initial experiment was conducted in Chongqing, China, from May 1st to May 3rd, 2018. The results show that bricklayers are in a relatively low level of anxiety, and that anxiety and heart rate levels are positively correlated with work productivity. The wearable device-based system facilitates the real-time monitoring of construction workers' psychological and physical status. In turn, such information can help in planning their working schedules to enable them to work more efficiently.
“…However, these measurements all entail job interruption. The solution, then, is to conduct indirect physiological measurement by means of a Kinect range camera or computer vision-based approach, which is also commonly used to capture motion and to conduct body posture assessment [7][8] [9][10] [11]. Some studies use a video-based computer visualization approach to automatically assess the captured motion [11] [12].…”
-Conventional ergonomic risk assessment of physical work is conducted through observation and direct/indirect physiological measurements. However, these methods are time-consuming and require human subjects to actually perform the motion in order to obtain detailed body movement data. 3D visualization, alternatively, allows users to simulate an operational task on the computer screen, a process that is less timeconsuming and which eliminates the need for costly onsite devices, as well as the detrimental effect of human error during experimentation. It can also proactively visualize a proposed design prior to implementation in the real world. This paper presents an automated ergonomic risk assessment framework based on 3D modelling with the support of a user-friendly interface for data-post processing. 3ds Max is utilized together with its built-in MAXScript. The presented system enables the automation of body motion risk identification by detecting awkward body postures, evaluating the handled force/load and frequency that cause ergonomic risk during body movements of workers. As the outcome, it provides detailed risk scores for body segments, such that users are able to review the continuous motion and corresponding risk by precise time frame. The capability of this 3D visualizationbased ergonomic risk assessment can be extended to support the re-design of the workplace and optimization of human body movement accordingly. The ultimate goal of this study is to proactively mitigate ergonomic risk and further reduce potential injuries and workers' compensation insurance costs in the long term.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.