Image enhancement method based on exposure fusion for UAV aerial photography

基于曝光融合的无人机航拍图像增强算法

¹ School of Mechatronic Engineering, Xi'an Technological University, Xi'an 710021, China
² School of Information and Communication Engineering, Hainan University, Haikou 570228, China
³ School of Electronics and Information Engineering, Xi'an Technological University, Xi'an 710021, China
⁴ School of Optoelectronic Engineering, Xi'an Technological University, Xi'an 710021, China
⁵ School of Computer Science and Engineering, Xi'an Technological University, Xi'an 710021, China

Received: 22 March 2022

Abstract

针对无人机航拍图像光照不均匀及自然雾导致影像质量退化问题, 提出了一种无人机航拍图像增强算法。利用改进的低照度图像增强算法均衡亮度对比度; 为了解决均衡后图像过增强问题, 提出了联合去雾及曝光融合的色彩矫正增强方法; 为了保留增强图像的边缘纹理信息, 设计了一种效果更佳的细节增强算法, 处理后统计直方图更为平滑, 可在一定程度上抑制部分噪声, 细节纹理信息更强。实验结果表明, 所提的航拍图像增强算法, 能够有效解决因光照不均或自然雾引起的影像退化现象, 提高了无人机航拍图像的质量, 主客观图像质量评价指标优于现有绝大多数主流算法, 性能更佳。

摘要

Aiming at the problem of image quality degradation caused by uneven illumination of UAV aerial images and natural fog, a UAV aerial image enhancement algorithm was proposed. Firstly, an improved low-illumination image enhancement algorithm is used to balance the brightness and contrast; secondly, in order to solve the image over-enhancement after equalization, a color correction enhancement method combining dehazing and exposure fusion is proposed; finally, in order to preserve the edge texture information of the enhanced image, a detail enhancement algorithm with better effect is designed. After processing, the statistical histogram is smoother, some noise can be suppressed to a certain extent, and the detailed texture information is stronger. The experimental results show that the present aerial image enhancement algorithm can effectively solve the image degradation caused by uneven illumination or natural fog. The quality of UAV aerial images is improved, and the subjective and objective image quality evaluation indicators are better than most of the existing mainstream algorithms, and the performance is better.