Enhancement of UAV-Aerial Images Using Weighted Differential Evolution Algorithm


Karkınlı A. E., Kesikoğlu A.

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol.7, no.2, pp.196-206, 2021 (Peer-Reviewed Journal)

Abstract

Depending on technological developments, the use of Unmanned Aerial Vehicles (UAVs) is increasing day by day and is a valuable source of data for different applications. Generally, low-cost and lightweight non-metric digital cameras are used in UAV systems. During the data collection phase, exposure parameters such as camera shutter speed, aperture value, ISO value, and various weather and light conditions have significant effects on image quality. Image enhancement methods can be used to increase image quality in accordance with the desired purpose. In this study, image enhancement is considered as an optimization problem and Weighted Differential Evolution (WDE) Algorithm is used to solve it. The image quality is enhanced by using an objective function in which performance measures of entropy value, sum of edge density and number of edge pixel are maximized. In the proposed color image enhancement method, aerial images defined in RGB color space are transformed into HSV color space images. the brightness component (V) of HSV color space is modified for image improvement with WDE algorithm. The performance of the proposed method has been compared with other existing techniques such as histogram equalization, linear contrast stretching and evolutionary computing-based image enhancement method like Artificial Bee Colony (ABC) Algorithm in terms of fitness value and image quality.