Computer vision-based street-width measurement for urban aesthetics identification

This paper presents a computer vision-based street-width measurement system for urban aesthetics identification. In this system, the image is captured using a digital camera. In the preprocessing section, the image is scaled in high to low resolution. The methodology used to identify objects is contour tracing and canny edge detection algorithm. The object is measured by generalizing the pixel mapping. The finding output is matched with the standard street measurement. The measurement findings in this proposed methodology are analyzed. Based on some criteria, the street aesthetics of Dhaka, the capital of Bangladesh, is provided.