Due to the complex terrain environment and limited illumination in coal mines, images acquired by video surveillance equipment often have problems such as insufficient brightness, low contrast, color distortion, and loss of detail information. To solve the above problems, a multi-scene low-light image enhancement algorithm of a coal mine based on MCGN (multi-scale calibrated gating network) is proposed. The algorithm is composed of illumination enhancement network, detail enhancement network, color correction network, and gating fusion network. Firstly, the illumination enhancement network estimates the illumination information through a pre-lighting module. On this basis, the illumination enhancement module with spatial enhanced attention is cascading to enhance the capture ability of the occluded area and the local dark area. Subsequently, a self-calibration module is introduced to further improve the overall exposure control ability of the image. Secondly, to preserve and enhance texture and edge details, a multi-level residual structure is designed to form a detail enhancement network, ensuring that important detail information is not lost. Furthermore, in view of the inherent color distortion of the image and the color distortion generated in the enhancement process, a color correction network and a color loss function are constructed. The codec structure is used to decouple the color image into a color histogram, and the natural light color characteristics are learned based on the color histogram to guide the color distribution correction. Finally, in order to realize the organic fusion of the output images of the three networks, a new gating mechanism is designed in the gated fusion network, which learns the optimal fusion weights end-to-end to achieve an effective balance of brightness enhancement, detail restoration, and color correction. Experimental results show that the proposed algorithm is effective in improving image brightness, enriching texture features, and restoring true color. At the same time, the algorithm has good multi-scene applicability and fast reasoning speed, which can meet the actual needs of coal mines and provide strong technical support for coal mine safety production.
图10中OutIEW代表光照增强网络的输出(output of light enhanced network),OutDEW代表细节增强网络的输出(output of detail enhances network),OutCCN代表颜色矫正网络的输出(output of color correction network).整个网络由一个视觉编码器、三个门控单元组成.视觉编码器由VGG16和非线性函数组成.VGG16通过多个卷积层的堆叠,能够更好捕获输入图像的局部细节[19].每个门控单元接收不同网络输出的增强图像,如式(11)所示.
The emergency management department of the state administration of mine safety,the national development and reform commission,the ministry of industry and information technology,the ministry of science and technology,the ministry of finance and the ministry of education jointly issued the guiding opinions on deepening the intelligent construction of mines and promoting the safe development of mines[J].China Occupational Safety and Health,2024,19(5): 5.(in Chinese)
PENGD X, ZHENT, LIZ H. Survey of research methods for low light image enhancement[J]. Computer Engineering and Applications, 2023, 59(18):14-27.(in Chinese)
TUY H, WANGP Q. Mine image enhancement method based on multi-scale local histogram equalization[J]. Journal of Mine Automation,2023,49(8):94-99.(in Chinese)
[9]
TIANF, WANGM J, LIUX P.Low-light mine image enhancement algorithm based on improved Retinex[J]. Applied Sciences,2024,14(5): 2213.
ZHANGL Y, HAOB N, MENGQ Y,et al .Underground image enhancement method based on HSV space improved fusion Retinex algorithm[J]. Journal of China Coal Society,2020,45(Sup.1):532-540.(in Chinese)
CAIY H, BIANH, LINJ,et al .Retinexformer:one-stage Retinex-based transformer for low-light image enhancement[C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris,France. IEEE,2023:12470-12479.
[21]
WEIC, WANGW J, YANGW H,et al .Deep Retinex decomposition for low-light enhancement[EB/OL]. 2018:1808.04560.
[22]
GUOX J, LIY, LINGH B. LIME:low-light image enhancement via illumination map estimation[J].IEEE Transactions on Image Processing, 2017,26(2):982-993.
[23]
YUZ P, HUANGH B, CHENW J, et al .YOLO-FaceV2:a scale and occlusion aware face detector[J].Pattern Recognition,2024,155:110714.
[24]
MAL, MAT Y, LIUR S,et al .Toward fast,flexible,and robust low-light image enhancement[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans,LA,USA. IEEE,2022:5627-5636.
[25]
HENDRYCKSD, GIMPELK .Gaussian error linear units (GELUs)[EB/OL].2016:1606.08415.
[26]
ZHANGZ, ZHENGH, HONGR C,et al .Deep color consistent network for low-light image enhancement[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans,LA,USA. IEEE,2022:1889-1898.
[27]
KALWARS, PATELD, AANEGOLAA,et al. GDIP: gated differentiable image processing for object detection in adverse conditions[C]//2023 IEEE International Conference on Robotics and Automation (ICRA). London,United Kingdom. IEEE, 2023:7083-7089.
CHENGD Q, CHENJ, KOUQ Q,et al.Lightweight super-resolution reconstruction method based on hierarchical features fusion and attention mechanism for mine image[J].Chinese Journal of Scientific Instrument,2022,43(8):73-84.(in Chinese)
CHENGD Q, XUJ Y, KOUQ Q,et al .Lightweight network based on residual information for foreign body classification on coal conveyor belt[J]. Journal of China Coal Society, 2022, 47(3): 1361-1369.(in Chinese)
ZHOUW, DONGL H, YEO,et al .A dataset of drilling site object detection in underground coal mines[J].China Scientific Data,2024,9(2):305-317.(in Chinese)
[34]
ZHUA Q, ZHANGL, SHENY,et al .Zero-shot restoration of underexposed images via robust Retinex decomposition[C]//2020 IEEE International Conference on Multimedia and Expo (ICME). London, United Kingdom. IEEE, 2020: 1-6.
[35]
GUOC L, LIC Y, GUOJ C,et al .Zero-reference deep curve estimation for low-light image enhancement[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,WA,USA. IEEE,2020:1780-1789.
[36]
KO K, KIMC S. IceNet for interactive contrast enhancement[J].IEEE Access,2021,9:168342-168354.
PARTHASARATHYS, SANKARANP. An automated multi scale Retinex with color restoration for image enhancement[C]//2012 National Conference on Communications (NCC). Kharagpur, India. IEEE,2012:1-5.
[39]
JIANGY F, GONGX Y, LIUD,et al. EnlightenGAN:deep light enhancement without paired supervision[J]. IEEE Transactions on Image Processing,2021,30:2340-2349.
[40]
WUW, WENGJ, ZHANGP, et al. URetinex-Net: Retinex-based deep unfolding network for low-light image enhancement[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, LA, USA. IEEE,2022: 5901-5910.
[41]
FUZ Q, YANGY, TUX T,et al .Learning a simple low-light image enhancer from paired low-light instances[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver,BC,Canada. IEEE, 2023: 22252-22261.
[42]
ZOUW B, GAOH X, YET,et al .VQCNIR:clearer night image restoration with vector-quantized codebook[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2024,38(7):7873-7881.
[43]
MITTALA, SOUNDARARAJANR, BOVIKA C .Making a “completely blind” image quality analyzer[J].IEEE Signal Processing Letters,2013,20(3):209-212.
[44]
LIS, JINW Q, LIL,et al .An improved contrast enhancement algorithm for infrared images based on adaptive double plateaus histogram equalization[J].Infrared Physics & Technology,2018,90:164-174.