Abstract

In the era of smart cities, infrared image enhancement techniques serve a great purpose in smart city applications such as traffic monitoring systems, intelligent urban surveillance systems, etc. Different algorithms have been proposed but most of them focus only on overemphasizing the global contrast. In this paper, we propose a differential evolution-based histogram equalization which utilizes a local entropy weighted histogram to enhance both contrasts as well as the local details contained in the noisy raw image. Initially, we generate a histogram using the local entropy of the raw infrared image. After that, we use the differential evolution algorithm to estimate the double plateau thresholds. To refine the foreground and the background contrast separately we divide the histogram into two parts using a threshold using the OTSU’s method. Finally, according to the constrained sub-local entropy weighted histogram, for each sub-image, the histogram equalization will be done independently.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call