一种矿井图像增强算法

A mine image enhancement algorithm

  • 摘要: 针对煤矿井下视频监控系统采集图像对比度低、光照不均、伴有大量噪声等问题,提出一种基于加权引导滤波同步去噪的单尺度Retinex算法对矿井图像进行增强。该算法首先采用加权引导滤波代替单尺度Retinex算法的高斯滤波对图像的低频分量进行照度估计,然后采用加权引导滤波对图像的高频分量进行去噪处理,最后由对数域转换到实数域得到增强后的图像。通过主观视觉效果和客观质量评价对该算法进行验证,结果表明该算法较传统图像增强算法可获得更好的图像视觉效果,且图像处理速度更快。

     

    Abstract: For poor images captured by coal mine video monitoring system with low contrast, uneven illumination and a lot of noise, a single scale Retinex algorithm based on simultaneous denoising of weighted guided filtering was proposed for underground image enhancement. Firstly, low-frequency components of an image are estimated by the weighted guided filter, which replaces Gaussian filter in single scale Retinex algorithm. Secondly, high-frequency components of the image are denoised by the weighted guided filter. Finally, an enhanced image is obtained through conversion from log domain to real field. The subjective visual effect and objective evaluation results show the algorithm has better visual effect and higher image processing speed than traditional image enhancement algorithms.

     

/

返回文章
返回