Tracking-based 3D human skeleton extraction from stereo video camera toward an on-site safety and ergonomic analysis

Abstract

Purpose As a means of data acquisition for the situation awareness, computer vision-based motion capture technologies have increased the potential to observe and assess manual activities for the prevention of accidents and injuries in construction. This study thus aims to present a computationally efficient and robust method of human motion data capture for the on-site motion sensing and analysis. Design/methodology/approach This study investigated a tracking approach to three-dimensional (3D) human skeleton extraction from stereo video streams. Instead of detecting body joints on each image, the proposed method tracks locations of the body joints over all the successive frames by learning from the initialized body posture. The corresponding body joints to the ones tracked are then identified and matched on the image sequences from the other lens and reconstructed in a 3D space through triangulation to build 3D skeleton models. For validation, a lab test is conducted to evaluate the accuracy and working ranges of the proposed method, respectively. Findings Results of the test reveal that the tracking approach produces accurate outcomes at a distance, with nearly real-time computational processing, and can be potentially used for site data collection. Thus, the proposed approach has a potential for various field analyses for construction workers’ safety and ergonomics. Originality/value Recently, motion capture technologies have rapidly been developed and studied in construction. However, existing sensing technologies are not yet readily applicable to construction environments. This study explores two smartphones as stereo cameras as a potentially suitable means of data collection in construction for the less operational constrains (e.g. no on-body sensor required, less sensitivity to sunlight, and flexible ranges of operations).

A Deep Learning Approach Towards Railway Safety Risk Assessment

“…Several defect management systems based on image matching have been suggested [97]. For less operational constraints, two smartphones have been used as stereo cameras to acquire motion data and extract 3D human skeletons to track people working in construction fields [98]. Real-time machine learning models with CNN frameworks have been proposed to detect whether workers are wearing safety equipment, such as hats and vests, from images/videos [99] and to detect ground objects [100].…”

Applying Sensor-Based Technology to Improve Construction Safety Management

“…Specifically, the contour extraction, noise reduction and posture recognition relies on algorithms and models with high complexity or huge computation burden, which are not practical to perform at construction sites. Peddi et al [ 89 ] developed an algorithm to track workers, extract their contours and recognize their postures based on video information; Liu et al [ 90 ] adopted the 3D skeleton extraction method with video stream; Han [ 91 ] proposed an unsafe behavior detection framework for workers on the basis of vision analysis; Park et al [ 92 ] applied a video frame detection method to recognize workers’ unsafe behavior of not wearing safety helmets.…”

Skeleton‐based human activity recognition for elderly monitoring systems

“…Among the different 3D-based methods used to describe the human body, two major groups can be distinguished. The first group is concerned with representation using local features [6][7][8][9], and the second group focuses on 3D skeleton-based features [10][11][12]. Methods based on local features initially detect space-time interest points, and then form patches at the point locations to make use of them as encoded features using bag-of-words models.…”