Automated Object Identification Using Optical Video Cameras on Construction Sites

Chi, Seokho; Caldas, Carlos H.

doi:10.1111/j.1467-8667.2010.00690.x

Cited by 177 publications

(75 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods can be further divided into feature-based (Lowe 2004), template-based (Dalal 2005), or deep learning (Krizhevsky and Sutskever 2012) techniques. In the civil engineering domain, the visual recognition output can then be applied to monitoring (Yang et al 2015;Seo et al 2015;Golparvar-Fard et al 2009), tracking (Park et al 2011;Memarzadeh et al 2013), and safety analysis tasks (Han and Lee 2013;Chi and Caldas 2011).…”

Section: Existing Object Recognition Methodsmentioning

confidence: 99%

Robotic sensing and object recognition from thermal-mapped point clouds

Kim

Chen

Cho

2017

Int J Intell Robot Appl

View full text Add to dashboard Cite

Many of the civil structures are more than half way through or nearing their intended service life; frequently assessing and maintaining structural integrity is a top maintenance priority. Robotic inspection technologies using ground and aerial robots with 3D scanning and imaging capabilities have the potential to improve safety and efficiency of infrastructure management. To provide more valuable information to inspectors and agency decision makers, automatic environment sensing and semantic information extraction are fundamental issues in this field. This paper introduces an innovative method for generating thermal-mapped point clouds of a robot's work environment and performing automatic object recognition with the aid of thermal data fused to 3D point clouds. The laser scanned point cloud and thermal data were collected using a custom-designed mobile robot. The multimodal data was combined with a data fusion process based on texture mapping. The automatic object recognition was performed by two processes: segmentation with thermal data and classification with scanned geometric features. The proposed method was validated with the scan data collected in an entire building floor. Experimental results show that the thermal integrated object recognition approach achieved better performance than a geometry only-based approach, with an average recognition accuracy of 93%, precision of 83%, and recall rate of 86% for objects in the tested environment including humans, display monitors and light fixtures.

show abstract

Section: Existing Object Recognition Methodsmentioning

confidence: 99%

Robotic sensing and object recognition from thermal-mapped point clouds

Kim

Chen

Cho

2017

Int J Intell Robot Appl

View full text Add to dashboard Cite

show abstract

“…Methods such as [2,12,13,17,18] treat detecting and tracking workers and equipment and activity recognition as two mutually independent tasks. A few studies have also focused on the end-to-end activity analysis problem [10,15,19].…”

Section: Related Workmentioning

confidence: 99%

Crowdsourcing Video-based Workface Assessment for Construction Activity Analysis

Liu

Golparvar-Fard²

2015

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

Today, the availability of multiple cameras on every jobsite is reshaping the way construction activities are being monitored. Research has focused on addressing the limitations of manual workface assessment from these videos via computer vision algorithms. Despite the rapid explosion of these algorithms, the ability to automatically recognize worker and equipment activities from videos is still limited. By crowd-sourcing the task of workface assessment from jobsite videos, this paper aims to overcome the limitations of the current practice and provides a large empirical dataset that can serve as the basis for developing video-based activity recognition methods. As such, an intuitive web-based platform for massive marketplaces such as Amazon Mechanical Turk (AMT) is introduced that engages the intelligence of non-expert crowd for interpretations of selected group of frames from these videos and then it automates remaining workface assessment tasks based on the initial interpretations. To validate, several experiments are conducted on videos from concrete placement operations. The results show that engaging AMT non-experts together with computer vision algorithms can provide assessment results with an accuracy of 85%. This minimizes the time needed for workface assessment, and allows the practitioners to focus their time on the more important task of root-cause analysis for performance improvements. This platform also provides significantly large datasets with ground truth for algorithmic development purposes.

show abstract

“…There have been a few studies on the use of computer vision techniques to detect workers in a construction scene [2][3][4][5][6]. The researchers in most previous studies employed the shape of the human body as a feature for construction worker detection.…”

Section: Introductionmentioning

confidence: 99%

“…To meet these challenges, colorbased features have obvious advantages over other features (especially in complex environments) because the color of an object of interest is independent from the positions and shapes [7]. Color-based features are commonly used in various object detection techniques such as the detection of workers, equipment, and materials in the construction sites [5,8,9]. The color property of the safety vest is expected to be an accurate and robust feature that has the potential to overcome the limitations of construction worker detection that uses shape-based features.…”

Section: Introductionmentioning

confidence: 99%

Vision-Based Safety Vest Detection in a Construction Scene

Seong¹,

Son²,

Kim³

et al. 2017

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

The computer vision-based detection of construction workers in images or videos is necessary for the safety managements and productivity of construction workers. Researchers in previous studies, detecting construction workers in the construction scene via computer vision techniques, have considered various features such as motion, shape, and color. Due to the pose changes of the workers, construction worker detection using body shape as a feature in the construction scene remains a challenging task. This study proposes a safety vest detection method, as a preceding method of the construction worker detection, which uses the motion of workers and the color pixels of safety vests for distinguishing from others in the construction scene independent of the workers' pose changes. The background subtraction method is performed by using an approximate median filter for the purpose of reducing the candidate regions that the color pixel classification will be performed as a sequential step. Then, the color pixel classification method is performed with a comparative analysis of two color spaces (Lab and HSV

show abstract

Automated Object Identification Using Optical Video Cameras on Construction Sites

Cited by 177 publications

References 28 publications

Robotic sensing and object recognition from thermal-mapped point clouds

Robotic sensing and object recognition from thermal-mapped point clouds

Crowdsourcing Video-based Workface Assessment for Construction Activity Analysis

Vision-Based Safety Vest Detection in a Construction Scene

Contact Info

Product

Resources

About