提升小波变换域矿井光照不均匀图像双直方图均衡化增强
|
摘要
由于矿井光照不均匀,加之大量粉尘附着于监控摄像头表面,导致获取的视频图像对比度不高且含有大量随机分布的颗粒状噪声。为提高该类图像的对比度,充分发挥矿井视频监控系统的效能,基于提升小波变换(Lifting wavelet transform LWT),提出了一种矿井不均匀光照图像的自适应增强算法。首先采用直方图规定化算法(Histogram specification,HS)对获取的矿井图像进行初步增强;其次对初步增强后的图像进行提升小波变换,由于图像中的随机噪声主要集中分布于高频小波分解系数中,低频小波分解系数基本不存在噪声,故保留低频小波分解系数,对高频小波分解系数提出了一种基于反正弦函数的改进阈值函数去噪模型进行噪声抑制;然后对低频小波分解系数和去噪后的高频小波分解系数进行重构,得到不含噪声的矿井图像;最后采用双直方图均衡化算法(Bi-histogram equalization,BHE)对去噪后的图像进行进一步增强。将所提算法分别与直方图规定化、反锐化掩膜、小波阈值去噪等算法进行性能对比,并采用峰值信噪比(Peak noise to ratio,PSNR)、均方根误差(Root mean square error,RMSE)以及边缘保持指数(Edge protection index,EPI)等指标对试验结果进行评价,结果表明:所提算法对于矿井光照不均匀图像的处理效果相对于其余算法而言效果较优,对于高效处理矿井视频图像有一定的参考价值。
Undermine illumination is uneven and the surfaces of surveillance cameras are covered by a large number of dust,so,the contrast of obtained video surveillance image is low and there are a large number of granular noise random distributed in video surveillance image.In order to improve the contrast of this kind of image and make full of the effectiveness of the underground video surveillance system,based on lifting wavelet transform(LWT),a adaptive enhancement method of underground uneven illumination image algorithm is proposed.Firstly,the histogram specification(HS)algorithm is adopted to conduct preliminary enhancement of the underground uneven illumination image;secondly,the preliminary enhancement image is conducted lifting wavelet transform,the low-frequency wavelet decomposition coefficient,based on the characteristics of them,the low-frequency wavelet decomposition coefficient is remained unchanged,a new wavelet thresholding function model based on the arcsine function is put forward to filter out the noise distributed in the high-frequency wavelet decomposition coefficients;then,the low-frequency wavelet decomposition coefficients and the filtered high-frequency wavelet decomposition coefficients are conducted refactoring,the underground image without noise is obtained;finally,the bi-histogram equalization(BHE)algorithm is used to improve the visual effects of the filtered underground image without noise.The performances of the algorithm proposed in this paper,histogram specification,counter-peaked mask and wavelet thresholding method are analyzed,besides that,peak signal noise to ratio(PSNR),root mean square error(RMSE)and edge protection index(EPI)are adopted to evaluate the preference of the above algorithms,the results show that the processing effects of the algorithm proposed in this paper is superior to the other algorithms,if has some reference for processing the undermine video surveillance image.
Undermine illumination is uneven and the surfaces of surveillance cameras are covered by a large number of dust,so,the contrast of obtained video surveillance image is low and there are a large number of granular noise random distributed in video surveillance image.In order to improve the contrast of this kind of image and make full of the effectiveness of the underground video surveillance system,based on lifting wavelet transform(LWT),a adaptive enhancement method of underground uneven illumination image algorithm is proposed.Firstly,the histogram specification(HS)algorithm is adopted to conduct preliminary enhancement of the underground uneven illumination image;secondly,the preliminary enhancement image is conducted lifting wavelet transform,the low-frequency wavelet decomposition coefficient,based on the characteristics of them,the low-frequency wavelet decomposition coefficient is remained unchanged,a new wavelet thresholding function model based on the arcsine function is put forward to filter out the noise distributed in the high-frequency wavelet decomposition coefficients;then,the low-frequency wavelet decomposition coefficients and the filtered high-frequency wavelet decomposition coefficients are conducted refactoring,the underground image without noise is obtained;finally,the bi-histogram equalization(BHE)algorithm is used to improve the visual effects of the filtered underground image without noise.The performances of the algorithm proposed in this paper,histogram specification,counter-peaked mask and wavelet thresholding method are analyzed,besides that,peak signal noise to ratio(PSNR),root mean square error(RMSE)and edge protection index(EPI)are adopted to evaluate the preference of the above algorithms,the results show that the processing effects of the algorithm proposed in this paper is superior to the other algorithms,if has some reference for processing the undermine video surveillance image.
引文
[1]孙继平.煤矿信息化与自动化发展趋势[J].工矿自动化,2015,41(4):1-5.Sun Jiping.Development trend of coal mine informatization and automation[J].Industry and Automation,2015,41(4):1-5.
[2]孙继平.煤矿信息化与智能化要求与关键技术[J].煤炭科学技术,2014,42(9):22-25.Sun Jiping.Requirement and key technology on mine informatization and intelligent technology[J].Coal Science and Technology,2014,42(9):22-25.
[3]芦燕.矿井视频监控系统的设计与选型[J].煤矿机电,2010(3):38-40.Lu Yan.Design and selection of mine video supervison system[J].Colliery Mechanical&Electrical Technology,2010(3):38-40.
[4]严毅.基于ARM和C/OS-Ⅱ的井下视频监控系统的研究[J].煤矿机械,2012,33(8):241-243.Yan Yi.Study of the video monitoring based on ARM and C/OS-Ⅱsystem[J].Coal Mine Machinery,2012,33(8):241-243.
[5]李文峰,苏谢明,徐克强.基于S3C6410的井下救援视频处理终端[J].现代矿业,2013(3):44-46.Li Wenfeng,Su Xieming,Xu Keqiang.Underground rescue video processing terminal based on S3C6410[J].Modern Mining,2013(3):44-46.
[6]陈烨,鲍捷,池庆.基于矿山井下视频监控系统的图像增强方法研究[J].电视技术,2014,38(3):190-192.Chen Ye,Bao Jie,Chi Qing.Research on image enhancement based on mine video monitoring system[J].Video Engineering,2014,38(3):190-192.
[7]李亚东,王洪栋,朱美强.改进单尺度Retinex算法在矿井图像中的运用[J].煤矿机械,2015,36(5):282-284.Li Yadong,Wang Hongdong,Zhu Meiqiang.Application of improved single scale Retinex algorithm in mine images[J].Coal Mine Machinery,2015,36(5):282-284.
[8]蔡利梅,钱建生,赵杰,等.基于模糊理论的煤矿井下图像增强算法[J].煤炭科学技术,2009,27(8):94-96.Cai Limei,Qian Jiansheng,Zhao Jie,et al.Enhancement algorithm of underground mine image based on fuzzy theory[J].Coal Science and Technology,2009,27(8):94-96.
[9]张英俊,雷耀花,潘理虎.基于暗原色先验的煤矿井下图像增强技术[J].工矿自动化,2015,41(3):80-83.Zhang Yingjun,Lei Yaohua,Pan Lihu.Enhancement technique of underground image based on dark channel prior[J].Industry and Automation,2015,41(3):80-83.
[10]王利娟.基于相似度测量和模糊熵的矿井图像增强方法[J].计算机工程与设计,2012,33(7):2696-2700.Wang Lijuan.Image enhancement algorithm underground mine based on homogeneity measurement[J].Computer Engineering and Design,2012,33(7):2696-2700.
[11]雷煌.基于提升小波变换的煤仓雷达物位计信号降噪研究[J].煤炭工程,2015,47(8):113-115.Lei Huang.Study on signal noise reduction of coal bunker radar level meter based on wavelet lifting transform[J].煤炭工程,2015,47(8):113-115.
[12]蒋晨,于瑞鹏,鲍国,等.副井振动信号处理的提升小波变换方法[J].金属矿山,2015(4):233-237.Jiang Chen,Yu Ruipeng,Bao Guo,et al.Auxiliary shaft vibration processing based on lifting wavelet transform[J].Metal Mine,2015(4):233-237.
[13]Kim Y T.Contrast enhancement using brightness preserving bi-histogram equalization[J].IEEE Transactions on Consumer Electronics,1997,43(1):1-8.
[14]左飞飞,王海彬,马捷,等.基于小波变换的改进去噪阈值函数[J].探测与控制学报,2015,37(1):80-85.Zuo Feifei,Wang Haibin,Ma Jie,et al.Improved denoise threshold function based on wavelet transform[J].Journal of Detection&Control,2015,37(1):80-85.
[15]王小兵,姚雪晴,邱银国,等.一种新型煤矿视频监控图像滤波算法[J].工矿自动化,2014,40(11):76-80.Wang Xiaobing,Yao Xueqing,Qiu Yinguo,et al.A new filtering algorithm for video monitoring image of coal mine[J].Industry and Automation,2014,40(11):76-80.
[16]王万国,王滨海,张晶晶,等.基于直方图规定化的图像去雾算法[J].计算机技术与发展,2014,24(9):241-244.Wang Wanguo,Wang Binhai,Zhang Jingjing,et al.Image haze removal algorithm based on histogram specification[J].Computer Technology and Development,2014,24(9):241-244.
[17]阿依古力·吾布力,贾振红,覃锡忠,等.基于剪切波变换的反锐化掩膜遥感图像增强[J].计算机工程与设计,2015,36(4):987-990.Ayiguli·Wubuli,Jia Zhenhong,Qin Xizhong,et al.Remote sensing image enhancement based on shearlet transform and unsharp masking[J].Computer Engineering and Design,2015,36(4):987-990.
[18]苏成志,陈洪印,孟凡一,等.新阈值二进小波去噪算法在齿轮信号中的应用[J].计算机工程与应用,2014,50(18):206-209.Su Chengzhi,Chen Hongyin,Meng Fanyi,et al.Application of new threshold dyadic wavelet denoising algorithm on gear signal[J].Computer Engineering and Applications,2014,50(18):206-209.
[19]李贺,秦志远,周丽雅.SAR图像斑点噪声整体变分偏微分方程滤波算法研究[J].中国图象图形学报,2010,15(6):910-914.Li He,Qin Zhiyuan,Zhou Liya.Study on SAR image speckle noise smoothing algorithm with TV-PDE[J].Journal of Image and Graphics,2010,15(6):910-914.
[2]孙继平.煤矿信息化与智能化要求与关键技术[J].煤炭科学技术,2014,42(9):22-25.Sun Jiping.Requirement and key technology on mine informatization and intelligent technology[J].Coal Science and Technology,2014,42(9):22-25.
[3]芦燕.矿井视频监控系统的设计与选型[J].煤矿机电,2010(3):38-40.Lu Yan.Design and selection of mine video supervison system[J].Colliery Mechanical&Electrical Technology,2010(3):38-40.
[4]严毅.基于ARM和C/OS-Ⅱ的井下视频监控系统的研究[J].煤矿机械,2012,33(8):241-243.Yan Yi.Study of the video monitoring based on ARM and C/OS-Ⅱsystem[J].Coal Mine Machinery,2012,33(8):241-243.
[5]李文峰,苏谢明,徐克强.基于S3C6410的井下救援视频处理终端[J].现代矿业,2013(3):44-46.Li Wenfeng,Su Xieming,Xu Keqiang.Underground rescue video processing terminal based on S3C6410[J].Modern Mining,2013(3):44-46.
[6]陈烨,鲍捷,池庆.基于矿山井下视频监控系统的图像增强方法研究[J].电视技术,2014,38(3):190-192.Chen Ye,Bao Jie,Chi Qing.Research on image enhancement based on mine video monitoring system[J].Video Engineering,2014,38(3):190-192.
[7]李亚东,王洪栋,朱美强.改进单尺度Retinex算法在矿井图像中的运用[J].煤矿机械,2015,36(5):282-284.Li Yadong,Wang Hongdong,Zhu Meiqiang.Application of improved single scale Retinex algorithm in mine images[J].Coal Mine Machinery,2015,36(5):282-284.
[8]蔡利梅,钱建生,赵杰,等.基于模糊理论的煤矿井下图像增强算法[J].煤炭科学技术,2009,27(8):94-96.Cai Limei,Qian Jiansheng,Zhao Jie,et al.Enhancement algorithm of underground mine image based on fuzzy theory[J].Coal Science and Technology,2009,27(8):94-96.
[9]张英俊,雷耀花,潘理虎.基于暗原色先验的煤矿井下图像增强技术[J].工矿自动化,2015,41(3):80-83.Zhang Yingjun,Lei Yaohua,Pan Lihu.Enhancement technique of underground image based on dark channel prior[J].Industry and Automation,2015,41(3):80-83.
[10]王利娟.基于相似度测量和模糊熵的矿井图像增强方法[J].计算机工程与设计,2012,33(7):2696-2700.Wang Lijuan.Image enhancement algorithm underground mine based on homogeneity measurement[J].Computer Engineering and Design,2012,33(7):2696-2700.
[11]雷煌.基于提升小波变换的煤仓雷达物位计信号降噪研究[J].煤炭工程,2015,47(8):113-115.Lei Huang.Study on signal noise reduction of coal bunker radar level meter based on wavelet lifting transform[J].煤炭工程,2015,47(8):113-115.
[12]蒋晨,于瑞鹏,鲍国,等.副井振动信号处理的提升小波变换方法[J].金属矿山,2015(4):233-237.Jiang Chen,Yu Ruipeng,Bao Guo,et al.Auxiliary shaft vibration processing based on lifting wavelet transform[J].Metal Mine,2015(4):233-237.
[13]Kim Y T.Contrast enhancement using brightness preserving bi-histogram equalization[J].IEEE Transactions on Consumer Electronics,1997,43(1):1-8.
[14]左飞飞,王海彬,马捷,等.基于小波变换的改进去噪阈值函数[J].探测与控制学报,2015,37(1):80-85.Zuo Feifei,Wang Haibin,Ma Jie,et al.Improved denoise threshold function based on wavelet transform[J].Journal of Detection&Control,2015,37(1):80-85.
[15]王小兵,姚雪晴,邱银国,等.一种新型煤矿视频监控图像滤波算法[J].工矿自动化,2014,40(11):76-80.Wang Xiaobing,Yao Xueqing,Qiu Yinguo,et al.A new filtering algorithm for video monitoring image of coal mine[J].Industry and Automation,2014,40(11):76-80.
[16]王万国,王滨海,张晶晶,等.基于直方图规定化的图像去雾算法[J].计算机技术与发展,2014,24(9):241-244.Wang Wanguo,Wang Binhai,Zhang Jingjing,et al.Image haze removal algorithm based on histogram specification[J].Computer Technology and Development,2014,24(9):241-244.
[17]阿依古力·吾布力,贾振红,覃锡忠,等.基于剪切波变换的反锐化掩膜遥感图像增强[J].计算机工程与设计,2015,36(4):987-990.Ayiguli·Wubuli,Jia Zhenhong,Qin Xizhong,et al.Remote sensing image enhancement based on shearlet transform and unsharp masking[J].Computer Engineering and Design,2015,36(4):987-990.
[18]苏成志,陈洪印,孟凡一,等.新阈值二进小波去噪算法在齿轮信号中的应用[J].计算机工程与应用,2014,50(18):206-209.Su Chengzhi,Chen Hongyin,Meng Fanyi,et al.Application of new threshold dyadic wavelet denoising algorithm on gear signal[J].Computer Engineering and Applications,2014,50(18):206-209.
[19]李贺,秦志远,周丽雅.SAR图像斑点噪声整体变分偏微分方程滤波算法研究[J].中国图象图形学报,2010,15(6):910-914.Li He,Qin Zhiyuan,Zhou Liya.Study on SAR image speckle noise smoothing algorithm with TV-PDE[J].Journal of Image and Graphics,2010,15(6):910-914.