Crowd Counting Camera Array and Correction

“Crowd Counting” is a term used to describe the process of calculating the number of people in a given context. Originally answered with basic sensors and cameras, crowd counting has multiple challenges especially when images representing a given crowd span multiple images. In this paper, we propose a Crowd Counting Camera Array and Correction (CCCAC) method using a camera array of scaled, rotated, geometrically corrected, combined, processed, and then evaluated images to determine the number of people within the newly created combined crowd field. We present our approaches for each step and present our mean-squared-error (MSE) and mean-absolute-error (MAE) results. Experimental results using real data from multiple cameras show that CCCAC methods perform superior to raw image processing methods with an accuracy of approximately 95%.