A Methodology for Object Identification and Tracking in Construction Based on Spatial Modeling and Image Matching Techniques

Abstract

Understanding the motion characteristics of on-site objects is desirable for the analysis of construction work zones, especially in problems related to safety and productivity studies. This article presents a methodology for rapid object identification and tracking. The proposed methodology contains algorithms for spatial modeling and image matching. A high-frame-rate range sensor was utilized for spatial data acquisition. The experimental results indicated that an occupancy grid spatial modeling algorithm could quickly build a suitable work zone model from the acquired data. The results also showed that an image matching algorithm is able to find the most similar object from a model database and from spatial models obtained from previous scans. It is then possible to use the matched information to successfully identify and track objects.

Computer vision techniques for construction safety and health monitoring

“…Object detection herein refers to the technique that detects a semantic object of interest in an image by searching the image with the known object model (e.g., appearance features). Therefore, object detection methods allow for assessing absence of PPE on workers by detecting the PPE and workers, or identifying unsafe conditions similarly by detecting hazardous materials at undesignated or known unsafe areas [14,18]. Second, the location-based approach is taken to evaluate the risk in the scene based on geometry information of project entities (e.g., equipment and workers) moving around over time.…”

“…These advances bring the operational and technical advantages over other types of sensing techniques (e.g., RFID, GPS and UWB) that require installation of sensors to all of project entities to be monitored and provide limited information such as location data, providing an opportunity to complement them [10,13,23,44,45,79]. Accordingly, computer vision has been applied to various areas in construction such as progress monitoring, productivity analysis, defect detection, and automated documentation [8,11,12,14]. Computer vision technologies have also great potential as field-based safety and health monitoring tools that can address limitations of current manual observational approaches, creating opportunities to automate the risk identification and evaluation processes by extracting and analyzing relevant information from images or videos [10,14,15].…”

“…Accordingly, computer vision has been applied to various areas in construction such as progress monitoring, productivity analysis, defect detection, and automated documentation [8,11,12,14]. Computer vision technologies have also great potential as field-based safety and health monitoring tools that can address limitations of current manual observational approaches, creating opportunities to automate the risk identification and evaluation processes by extracting and analyzing relevant information from images or videos [10,14,15]. Despite recent progress made toward computer vision-based approaches to safety and health monitoring, prior works have been infrequently applied to actual practice for technical and practical issues, or any other issues.…”

Improvements to Concrete Column Detection in Live Video

“…Detecting structural elements is always the first step to automate construction applications, such as progress monitoring (Wu and Kim, 2004;Golpard-Vard et al, 2009), productivity measurement (Chi et al 2009;Gong and Caldas, 2009), and construction safety improvement (Teizer, 2008). Given a template, the structural element detection in general is regarded as the problem of locating the structural elements that "looks" similar to the template (Ge et al 2008).…”

Autonomous Modeling of Pipes within Point Clouds

“…Some of the knowledge thereby created has influenced or been adopted in practice. Additional closely related and overlapping research streams have focused on: (1) quality assessment, (2) automated progress tracking, (3) structural health monitoring, and (4) safety (Teizer et al 2007, Park et al 2007, Chi et al 2009, Ahmed et al 2012.…”