Research on Monitoring of Workers' Helmet Wearing at the Construction Site
Liu Yunb · Electronic Science and Technology · 2015
To monitor workers' helmet wearing in the construction site and keep its statistics,this paper proposes a method of monitoring workers helmet wearing in the construction site based on computer vision. First,using the background difference method the foreground is extracted from the video image,its binary image is obtained and the moving target is split; second,it is distinguished whether the moving target is representing a person according to the characteristics of the moving targets by the scaling filtering method and so on,and the moving target representing a person needs to be tracked and marked; finally,two test lines are set in the middle of the road. When a moving target representing a person reaches the middle of the two lines,the distribution of pixel color values in its upper third area is detected to determine whether a person is wearing a helmet and the color of the helmet. Experimental results demonstrate that this method can meet the requirements on accuracy and efficiency.