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
-
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.Abstract: 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 histogram.The proposed adaptive equalization approach can automatically realize image equalization.Experimental 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.
-
-
[1]
Dawound A,Alam M S,Bal A,et al.Target tracking in infrared imagery using weighted composite reference function-based decision fusion[J].IEEE Transactions on Image Processing,2006,15(2):404.
-
[2]
Bal A,Alam M S.Automatic target tracking in FLIR image sequences using intensity variation function and template modeling[J].IEEE Transaction on Instrumentation and Measurement,2005,54(5):1846.
-
[3]
范新南,郭建甲.一种新的自适应工程图像分割算法[J].计算机测量与控制,2006,14(3):395.
-
[4]
Qiao Yu,Hu Qingmao,Qian Guoyu,et al.Thresholding based on variance and intensity contrast[J].Pattern Recognition,2007,40(2):596.
-
[5]
Bazi Y,Bruzzone L,Melgani F.Image thresholding based on the EM algorithm and the generalized Gaussian distribution[J].Pattern Recognition,2007,40(2):619.
-
[6]
Sonka M,Hlavac V,Boyle R.Image Processing, Analysis, and Machine Vision[M].2ed.New York:PWS Publishing,1999:128-130.
-
[1]
计量
- PDF下载量: 15
- 文章访问数: 824
- 引证文献数: 0