Chonthisa Wateosot and Nikom Suvonvorn, Top-view Based People Counting Using Mixture of Depth and Color Information, The Second Asian Conference on Information Systems, ACIS 2013, October 31 – November 2 , 2013. Phuket,Thailand
Abstract
People counting is very important for some applications, such as, surveillance, event organization, flow control application and etc. In this paper, we propose a novel technique for people counting using the mixture of color and depth images from top-view camera. The U-disparity as depth image projection is introduced in order to increase the accuracy of counting number. Our method can count accurately at 93% in real-time.
Keywords: People counting, Color U-disparity, RGB-D image