一种适应于远程红外监控的图像增强方法  

An image enhancement approach for long-range surveillance based on infrared

作　　者：夏永泉[1] 董向滢[1] 王慧敏[1] 

机构地区：[1]郑州轻工业学院计算机与通信工程学院,河南郑州450001

出　　处：《郑州轻工业学院学报（自然科学版）》2012年第6期78-81,共4页Journal of Zhengzhou University of Light Industry:Natural Science

基　　金：国家科技支撑计划项目(2006BAK01A38);河南高校青年骨干教师资助计划项目(2010GGJS-114);郑州轻工业学院博士基金项目(2007BSJJ005)

摘　　要：针对远距离捕获的红外图像对比度低、亮度低以及感兴趣的目标比较小等问题,提出了一种新的自适应直方图均衡的方法.该方法利用图像直方图的2种不同信息,自动生成混合累积直方图,达到对红外图像进行自动均衡化的目的.试验结果表明,该方法可以有效地提高红外图像的对比度,对红外图像中小目标的增强效果更为明显.The infrared images that are captured at long range usually have low contrast, low brightness, and small hot objects of interest. A novel adaptive histogram-based equalization was put forward to enhance the contrast of infrared images in order to overcome the defects of infrared image itself. It can automatically generate a hybrid cumulative histogram based on two different pieces of information about the image histo- gram. The proposed adaptive equalization approach can automatically realize image equalization. Experi- mental results demonstrated that the approach proposed in this paper can improve the contrast of infrared images ,and the effect is more obvious to the small objects embedded in infrared images.

关 键 词：远程红外图像监控 直方图均衡 混合累积直方图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]