基于前背景特性的逆光交通场景图像增强  

Backlit Traffic Scene Image Enhancement Based on Foreground and Background Characteristics

作　　者：马荣贵[1] 魏子仲 何逸煦 黄训燕 MA Ronggui;WEI Zizhong;HE Yixu;HUANG Xunyan(School of Information Engineering,Chang'an University,Xi'an 710064,China)

机构地区：[1]长安大学信息工程学院,陕西西安710064

出　　处：《无线电工程》2024年第5期1146-1154,共9页Radio Engineering

基　　金：国家重点研发计划(2021YFB1600104);国家自然科学基金(52002031)。

摘　　要：由于逆光交通场景下采集到的图像存在前景亮度过低、背景亮度失真等特点,导致采集图像清晰度低、信息丢失严重和可识别性差,针对逆光图像前背景的不同特性,研究提出了一种分区域增强方法。对逆光图像使用最大类间方差法(OTSU法)分割图像的前景和背景;对逆光图像全局使用LIME方法,提升前景亮度的同时保持色彩的失真度;单独将背景部分RGB三个通道上的全局直方图均衡化结果一一映射到对应的限定区间内,提高了背景的对比度;使用Canny算子检测出前背景拼接处的黑边,根据黑边生成3个自适应的滤波模板对黑边进行分步均值滤波处理,消除了黑色边缘,提升了图像的视觉质量。在实验室自建的CHD_B数据集上,所提方法在4种常用客观评价指标上综合占优。实验结果表明,所提出的图像增强算法能有效地消除图像中的逆光现象。The characteristics of low foreground brightness and distorted background brightness in images collected under backlit traffic scenes result in low clarity,serious information loss,and poor identifiability of the collected images.To solve the above problems,a sub-regional enhancement method is proposed to study the different characteristics of the foreground/background of backlit images.Firstly,the maximum inter class variance(OTSU)method is used to segment the foreground and background of the backlight image;next,the LIME method is used globally for the backlight image to enhance foreground brightness while maintaining color distortion;then,the global histogram equalization results on the three RGB channels of background portion are individually mapped to the corresponding limited intervals,improving the contrast of the background.The Canny operator is used to detect the black edges at the stitching part between the foreground and background,and three adaptive filtering templates are generated based on the black edges to perform step-by-step mean filtering on the black edges,eliminating the black edges and improving the visual quality of the image.On a dataset CHD_B self-built in the laboratory,the proposed method is superior in terms of four commonly used objective evaluation indicators.Experimental results show that the proposed image enhancement algorithm can effectively eliminate the backlighting in images.

关 键 词：逆光图像 LIME 直方图均衡 边缘优化 图像增强 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]