煤矿井下非均匀照度图像去噪研究

张旭辉; 麻兵; 杨文娟; 董征; 李语阳

doi:10.13272/j.issn.1671-251x.2023110090

煤矿井下非均匀照度图像去噪研究

doi: 10.13272/j.issn.1671-251x.2023110090

张旭辉^{1, 2,},
麻兵¹,
杨文娟^{1, 2, ,},
董征¹,
李语阳¹

1.
西安科技大学机械工程学院，陕西西安　710054
2.
陕西省矿山机电装备智能检测与控制重点实验室，陕西西安　710054

基金项目: 国家自然科学基金青年项目(52104166)；中国博士后科学基金面上项目(2022MD723826)；陕西省重点研发计划项目(2023-YBGY-063)。

详细信息

作者简介:
张旭辉（1972—），男，陕西凤翔人，教授，博士，研究方向为煤矿机电设备智能检测与控制， E-mail：zhangxh@xust.edu.cn

通讯作者:
杨文娟（1989—），女，山西文水人，副教授，研究方向为智能检测与控制，E-mail： yangwenjuan@xust.edu.cn。

中图分类号: TD76
计量
- 文章访问数: 230
- HTML全文浏览量: 44
- PDF下载量: 49
- 被引次数: 0
出版历程
- 收稿日期: 2023-11-29
- 修回日期: 2024-02-06
- 网络出版日期: 2024-03-01

Research on denoising of uneven lighting images in coal mine underground

ZHANG Xuhui^{1, 2
,},
MA Bing¹,
YANG Wenjuan^{1, 2
, ,},
DONG Zheng¹,
LI Yuyang¹

1.
College of Mechanical Engineering, Xi'an University of Science and Technology, Xi'an 710054, China
2.
Shaanxi Key Laboratory of Mine Electromechanical Equipment Intelligent Detection and Control, Xi'an 710054, China

摘要

摘要: 煤矿综采工作面空间小、照明环境复杂多变，采煤过程中伴随着大量的粉尘、大雾，导致采集的图像出现曝光、细节特征减弱等问题，难以对井下照明区域光照强度过大的图像进行有效的特征提取。针对上述问题，提出了一种煤矿井下非均匀照度图像去噪算法。首先，将视频截取为图像，判断图像是否需要进行光照抑制，将需要进行光照抑制的RGB图像拆分通道，并计算每个通道的光照调节因子，实现图像的整体光照调节；然后，将未进行整体光照抑制的图像和经整体光照抑制的图像进行反射分量提取，即将输入的图像转换为HSV空间图像，使用单尺度Retinex（SSR）算法对V通道图像中的光照分量进行单独处理，将V分量中的入射分量去除，保留反射分量，并对反射分量使用直方图均衡算法实现光照均衡化处理；最后，使用基于引导滤波的暗通道先验算法对经过光照处理后的图像进行去雾处理，并使用伽马校正函数重新调节亮度不均的图像。主观评价结果表明：提出的煤矿井下非均匀照度图像去噪算法有效抑制了因光照导致整体亮度较高的问题，且由于大雾、粉尘等因素导致图像模糊的部分更加清晰，图像的细节特征更加突出。采用信息熵、均值、标准差、空间频率4种评价指标对提出的算法效果进行客观评价，结果表明，提出的算法在信息熵、均值、标准差、空间频率上较多尺度Retinex（MSR）算法分别平均提升了21.87%，−56.06%，153.43%，294.45%，较基于颜色保持的多尺度视网膜增强（MSRCP）算法分别平均提升了1.18%，−39.56%，33.29%，−4.71%，较带色彩恢复的多尺度视网膜增强（MSRCR）算法分别平均提升了38.06%，−55.27%，462.10%，300.96%，说明提出的算法能更有效地增加图像信息量、抑制光照强度、提升边缘信息及图像清晰度。
- 综采工作面 /
- 煤矿井下图像去噪 /
- 非均匀光照 /
- 高光抑制 /
- 亮度均衡 /
- 图像去雾 /
- 伽马校正
Abstract: The space of the fully mechanized working face is small, and the lighting environment is complex and variable. During the coal mining process, there is a large amount of dust and fog, which leads to problems such as exposure and weakened detail features in the collected images. It is difficult to effectively extract features from images with excessive lighting intensity in the underground lighting area. In order to solve the above problems, a denoising algorithm for uneven lighting images in coal mines is proposed. Firstly, the video is captured as an image to determine whether lighting suppression is necessary. The RGB image that requires lighting suppression is split into channels, and the lighting adjustment factor for each channel is calculated to achieve overall lighting adjustment of the image. Secondly, the images that have not undergone overall lighting suppression and those that have undergone overall lighting suppression are subjected to reflection component extraction. The input image is converted into an HSV spatial image, and the single scale Retinex (SSR) algorithm is used to separately process the illumination component in the V channel image. The incident component in the V component is removed, while the reflection component is retained. The histogram equalization algorithm is used to achieve illumination equalization for the reflection component. Finally, a dark channel prior algorithm with guided filtering is used to defog the light-processed image. The gamma correction function is used to readjust the image with uneven brightness. The subjective evaluation results indicate that the proposed denoising algorithm for uneven lighting images in coal mines effectively suppresses the problem of high overall brightness caused by lighting. The blurry parts of the original image are clearer due to factors such as fog and dust, and the detailed features of the image are more prominent. The effectiveness of the proposed algorithm is objectively evaluated using four evaluation indicators: information entropy, mean, standard deviation, and spatial frequency. The results showed that the proposed algorithm has achieved an average improvement of 21.87%, −56.06%, 153.43%, and 294.45% in terms of information entropy, mean, standard deviation, and spatial frequency compared to the multi-scale Retinex (MSR) algorithm. The proposed algorithm has achieved an average improvement of 1.18%, −39.56%, 33.29%, and −4.71% compared to the multi-scale Retinex with color preservation (MSRCR) algorithm. The proposed algorithm has achieved an average improvement of 38.06%, −55.27%, 462.10%, and 300.96% compared to the multi-scale Retinex with color restoration (MSRCR) algorithm. The results indicate that the proposed algorithm can more effectively increase image information, suppress lighting intensity, improve edge information, and image clarity.
- fully mechanized working face /
- image denoising in coal mine underground /
- uneven lighting /
- highlight suppression /
- brightness balance /
- image defogging /
- Gamma correction

HTML全文

图 1 煤矿井下非均匀照度图像去噪算法整体方案

Figure 1. Overall scheme of denoising of uneven lighting images in coal mine underground algorithm

下载: 全尺寸图片幻灯片

图 2 光照调节流程

Figure 2. Light adjustment flow

下载: 全尺寸图片幻灯片

图 3 V分量处理流程

Figure 3. V component processing flow

下载: 全尺寸图片幻灯片

图 4 改进暗通道先验算法流程

Figure 4. Improved dark channel prior algorithm flow

下载: 全尺寸图片幻灯片

图 5 灰度分布对比

Figure 5. Comparison of gray level distribution

下载: 全尺寸图片幻灯片

图 6 算法对比

Figure 6. Algorithms comparison

下载: 全尺寸图片幻灯片

图 7 评价指标对比

Figure 7. Comparison of evaluation indexs

下载: 全尺寸图片幻灯片

表 1 均值、标准差对比

Table 1. Comparison of mean and standard deviation

标号	评价指标
	均值		标准差
	原图	本文算法处理后图像	原图	本文算法处理后图像
P₁	146	98	59	73
P₂	150	100	55	72
P₃	145	102	57	74
P₄	144	95	59	75
P₅	148	84	59	73
P₆	150	102	54	75

下载: 导出CSV

表 2 不同算法处理后图像指标比较

Table 2. Comparison of image indexes after processed by different algorithms

标号	算法	评价指标				标号	算法	评价指标
标号	算法	信息熵	均值	标准差	空间频率	标号	算法	信息熵	均值	标准差	空间频率
P₇	MSR算法	6.26	223.75	24.62	6.59	P₁₀	MSR算法	6.80	211.18	44.18	9.01
	MSRCP算法	7.62	161.77	56.39	26.6		MSRCP算法	7.72	141.76	62.85	30.89
	MSRCR算法	5.54	216.56	12.94	6.12		MSRCR算法	5.69	203.26	14.70	7.31
	本文算法	7.66	97.26	74.83	26.22		本文算法	7.66	88.43	72.84	29.68
P₈	MSR算法	6.41	220.32	30.59	7.23	P₁₁	MSR算法	6.07	227.16	25.55	7.27
	MSRCP算法	7.72	160.59	60.29	28.83		MSRCP算法	7.45	167.66	49.98	34.65
	MSRCR算法	5.92	196.57	16.82	8.03		MSRCR算法	5.28	216.14	10.63	7.42
	本文算法	7.70	97.06	72.79	25.88		本文算法	7.61	101.50	78.06	32.11
P₉	MSR算法	6.28	224.29	28.48	7.31	P₁₂	MSR算法	6.05	229.81	24.22	6.80
	MSRCP算法	7.60	167.65	55.68	31.61		MSRCP算法	7.50	172.20	52.63	30.93
	MSRCR算法	5.45	218.15	11.94	6.85		MSRCR算法	5.53	217.19	13.08	7.69
	本文算法	7.72	100.43	75.86	29.33		本文算法	7.76	102.58	75.84	31.66

下载: 导出CSV

参考文献(21)

[1]	孙林,陈圣,姚旭龙,等. 矿井智能监控目标识别的图像增强方法与应用[J/OL]. 煤炭学报:1-12[2023-11-02]. http://doi.org/10.13225/j.cnki.jccs.2023.0489. SUN Lin,CHEN Sheng,YAO Xulong,et al. Image enhancement methods and applications for target recognition in intelligent mine monitoring[J/OL]. Journal of China Coal Society:1-12[2023-11-02]. http://doi.org/10.13225/j.cnki.jccs.2023.0489.
[2]	刘志成,王殿伟,刘颖,等. 基于二维伽马函数的光照不均匀图像自适应校正算法[J]. 北京理工大学学报,2016,36(2):191-196,214 . LIU Zhicheng,WANG Dianwei,LIU Ying,et al. Adaptive adjustment algorithm for non-uniform illumination images based on 2D damma function[J]. Transactions of Beijing Institute of Technology,2016,36(2):191-196,214.
[3]	李正龙,王宏伟,曹文艳,等. 基于含噪Retinex模型的煤矿低光照图像增强方法[J]. 工矿自动化,2023,49(4):70-77. LI Zhenglong,WANG Hongwei,CAO Wenyan,et al. A method for enhancing low light images in coal mines based on Retinex model containing noise[J]. Journal of Mine Automation,2023,49(4):70-77.
[4]	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 Mine Automation,2014,40(11):76-80.
[5]	YI Renjiao,TAN Ping,LIN S. Leveraging multi-view image sets for unsupervised intrinsic image decomposition and highlight separation[C]. AAAI Conference on Artificial Intelligence,New York, 2020:12685-12692. doi: 10.1609/aaai.v34i07.6961
[6]	涂毅晗,汪普庆. 基于多尺度局部直方图均衡化的矿井图像增强方法[J]. 工矿自动化,2023,49(8):94-99. TU Yihan,WANG Puqing. Mine image enhancement method based on multi-scale local histogram equalization[J]. Journal of Mine Automation,2023,49(8):94-99.
[7]	LI Jiafeng,HAO Shuai,LI Tianshuo,et al. RDMA:low-light image enhancement based on retinex decomposition and multi-scale adjustment[J]. International Journal of Machine Learning and Cybernetics,2023. doi: 10.1007/s13042-023-01991-7
[8]	张立亚,郝博南,孟庆勇,等. 基于HSV空间改进融合Retinex算法的井下图像增强方法[J]. 煤炭学报,2020,45(增刊1):532-540. ZHANG Liya,HAO Bonan,MENG Qingyong,et al. Method of image enhancement in coal mine based on improved retex fusion algorithm in HSV space[J]. Journal of China Coal Society,2020,45(S1):532-540.
[9]	龚云,颉昕宇. 基于同态滤波方法的煤矿井下图像增强技术研究[J]. 煤炭科学技术,2023,51(3):241-250. GONG Yun,XIE Xinyu. Research on coal mine underground image recognition technology based on homomorphic filtering method[J]. Coal Science and Technology,2023,51(3):241-250.
[10]	吴仲琦,王琛珑,郭建伟,等. 基于生成对抗网络的单张图像高光去除方法[J]. 中国科技论文,2023,18(3):265-274. doi: 10.3969/j.issn.2095-2783.2023.03.006 WU Zhongqi,WANG Chenlong,GUO Jianwei,et al. Single image specular highlight removal based on a generative adversarial network[J]. China Sciencepaper,2023,18(3):265-274. doi: 10.3969/j.issn.2095-2783.2023.03.006
[11]	FU Gang,ZHANG Qing,ZHU Lei,et al. A multi-task network for joint specular highlight detection and removal[C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition,Nashville,2021:7752-7761.
[12]	王若状,臧景峰,张朋朋. 基于模拟曝光融合的非均匀光照图像增强[J]. 吉林大学学报(理学版),2023,61(3):601-611. WANG Ruozhuang,ZANG Jingfeng,ZHANG Pengpeng. Non-uniform illumination image enhancement based on simulated exposure fusion[J]. Journal of Jilin University(Science Edition),2023,61(3):601-611.
[13]	马鸿涛. 局部强光干扰下失真图像特征还原技术研究[D]. 大连:大连工业大学,2021. MA Hongtao. Research on feature restoration technology of distorted image under strong light interference[D]. Dalian:Dalian Polytechnic University,2021.
[14]	栗文静,刘静雪,周瑞云,等. 非均匀光照彩色图像的改进双直方图均衡校正[J]. 宜宾学院学报,2022,22(6):33-36,78. LI Wenjing,LIU Jingxue,ZHOU Ruiyun,et al. Improved bi-histogram equalization for color image under non-uniform illumination[J]. Journal of Yibin University,2022,22(6):33-36,78.
[15]	李灿林,朱金娟,刘金华,等. 一种自适应SSR的雾天低照度图像增强方法[J]. 计算机应用与软件,2022,39(9):233-239,268. doi: 10.3969/j.issn.1000-386x.2022.09.035 LI Canlin,ZHU Jinjuan,LIU Jinhua,et al. An adaptive SSR method for foggy low illumination image enhancement[J]. Computer Applications and Software,2022,39(9):233-239,268. doi: 10.3969/j.issn.1000-386x.2022.09.035
[16]	徐辉,贺耀宜. 一种煤矿井下监控视频图像预处理方法[J]. 工矿自动化,2016,42(1):32-34. XU Hui,HE Yaoyi. An image preprocessing method for underground monitoring video[J]. Industry and Mine Automation,2016,42(1):32-34.
[17]	孙希延,陶堃,黄建华,等. 基于暗通道的自适应图像去雾算法[J]. 计算机仿真,2022,39(6):359-364. doi: 10.3969/j.issn.1006-9348.2022.06.071 SUN Xiyan,TAO Kun,HUANG Jianhua,et al. Adaptive image dehazing algorithm based on dark channel[J]. Computer Simulation,2022,39(6):359-364. doi: 10.3969/j.issn.1006-9348.2022.06.071
[18]	刘安强,祝菁,郭少帅,等. MSR在矿井图像增强研究中的应用[J]. 煤炭技术,2023,42(9):255-257. LIU Anqiang,ZHU Jing,GUO Shaoshuai,et al. Application of MSR in mine image enhancement[J]. Coal Technology,2023,42(9):255-257.
[19]	阮顺领,刘丹洋,白宝军,等. 基于自适应MSRCP算法的煤矿井下图像增强方法[J]. 矿业研究与开发,2021,41(11):186-192. RUAN Shunling,LIU Danyang,BAI Baojun,et al. Image enhancement method for underground coal mine based on the adaptive MSRCP algorithm[J]. Mining Research and Development,2021,41(11):186-192.
[20]	王利娟,常霞,张伯妍. 基于MSRCR的自适应低照度图像增强[J]. 现代电子技术,2022,45(2):155-161. WANG Lijuan,CHANG Xia,ZHANG Boyan. Adaptive low-illumination image enhancement based on MSRCR[J]. Modern Electronics Technique,2022,45(2):155-161.
[21]	徐望明,刘召,伍世虔,等. 基于虚拟多曝光融合的不均匀光照图像增强方法[J]. 华中科技大学学报(自然科学版),2020,48(8):79-84,90. XU Wangming,LIU Zhao,WU Shiqian,et al. Non-uniform illumination image enhancement method based on virtual multi-exposure fusion[J]. Journal of Huazhong University of Science and Technology(Natural Science Edition),2020,48(8):79-84,90.