Construction worker detection in video frames for initializing vision trackers

• Published in: Automation in construction Vol. 28; pp. 15 - 25
• Main Authors: Park, Man-Woo, Brilakis, Ioannis
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier B.V 01.12.2012; Elsevier
• Subjects: Applied sciences; Buildings. Public works; Color; Computer vision; Construction; Construction worker; Construction works; Cues; Detection; Exact sciences and technology; Frames; Histograms; Image processing; Measurements. Technique of testing; Monitoring; Pattern recognition; Remote sensing; Site organization; Tracking; Vision; Computer vision; Tracking; Construction worker; Image processing; Pattern recognition; Detection; Remote sensing; Video technique; Implementation; Building site; Experimental result; Worker; Monitoring
• ISSN: 0926-5805; 1872-7891
• DOI: 10.1016/j.autcon.2012.06.001

Monitoring the location of resources on large scale, congested, outdoor sites can be performed more efficiently with vision tracking, as this approach does not require any pre-tagging of resources. However, the greatest impediment to the use of vision tracking in this case is the lack of detection methods that are needed to automatically mark the resources of interest and initiate the tracking. This paper presents such a novel method for construction worker detection that localizes construction workers in video frames. The proposed method exploits motion, shape, and color cues to narrow down the detection regions to moving objects, people, and finally construction workers, respectively. The three cues are characterized by using background subtraction, the histogram of oriented gradients (HOG), and the HSV color histogram. The method has been tested on videos taken in various environments. The results demonstrate its suitability for automatic initialization of vision trackers. ► We propose a method of detecting construction workers in video frames. ► The method exploits motion, shape, and color features to characterize workers. ► Color features enable the method to differentiate workers from ordinary people. ► Experiments resulted in 99.0% precision. ► Workers were detected within 0.67s after their first appearance.