Search

In the complex confined space of underground coal mine, some environmental factors such as uneven illumination of artificial light source, heavy concentration of dust and fog in the working face, and complex electromagnetic interference can seriously affect the high-definition imaging of underground surveillance video. Aiming at the problems of low resolution and blurring of mine images affected by complex environment, and the problems that the current image super-resolution reconstruction methods mostly improve the reconstruction effect at the expense of compromising network depth and width, which will increase the complexity of the algorithm greatly, as well as the memory usage of the network model, making it difficult to apply to actual edge mobile devices. In this study, a lightweight super-resolution reconstruction method of mine images based on blueprint separation convolution is proposed. Firstly, the high-efficiency blueprint separation convolution is used to replace the standard convolution in the residual block, and a lightweight residual attention module is designed by introducing coordinate attention mechanism and adding skip connections to improve the residual block, so that the model can achieve a better feature extraction ability while keeping low parameters and computation. Secondly, an enhanced hierarchical feature fusion module is designed to integrate local features first and then global features of different hierarchical features in the network, which can further promote the information flow in the network and enhance the feature utilization rate of the model. Finally, the pixel attention mechanism is added at the end of the network to enhance the attention of the network to the information features, which can improve the feature expression ability of the model and provide more detailed features for the image reconstruction module. Experimental results show that the image quality reconstructed by the lightweight super-resolution reconstruction network based on blueprint separation convolution is not only superior to other comparison algorithms in terms of objective indexes and visual perception, but also achieves a better trade-off between model performance and complexity. When the scaling factor is 4, in comparison to the lightweight algorithm AWSRN-M with the same number of parameters, the average PSNR and SSIM on the coal mine test set are increased by 0.177 2 dB and 0.010 7 respectively, and the floating-point computation is reduced by 66.9%. The results demonstrate that the proposed method can effectively extract the detailed feature information with different levels, achieve the deep fusion of shallow and deep features, and more efficiently reconstruct high-resolution images with clear texture details.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The visual simultaneous localization and mapping (SLAM) algorithm based on the feature point method has certain applications in coal mines. However, due to factors such as uneven lighting, variable lighting, and alternating light and dark areas, the image quality is poor and texture information is lacking. This results in low precision of feature extraction and matching in the front end of visual SLAM. The problem of tracking loss is prone to occur, which affects the positioning precision and mapping effect of the visual SLAM algorithm. This study proposes a visual SLAM algorithm of coal mine underground considering image enhancement. The overall performance of visual SLAM is improved through image enhancement processing. Retinex algorithm based on improved bilateral filter is used to enhance the coal mine underground image. The original RGB image is converted to HSI color space, and the improved bilateral filter replaces the Gaussian filter of the traditional Retinex algorithm as the central surrounding function. After the image reflection component is estimated, it is converted to RGB color space to obtain the final enhanced image. Retinex algorithm based on improved bilateral filter is introduced into the classical ORB-SLAM2 algorithm framework for pose estimation and mapping. Based on the data collection platform of the wheeled mine-used robot, the visual SLAM algorithm considering image enhancement is tested in the roadway environment of coal mine underground. The results show that, compared with the traditional Retinex algorithm, the coal mine image enhanced by the Retinex algorithm based on improved bilateral filter does not show obvious whitening and halo, and the image quality is improved. Compared with the ORB-SLAM2 algorithm, the visual SLAM algorithm considering image enhancement improves the quality and quantity of feature matching. It has a higher degree of overlap between estimated trajectories and real trajectories. It reduces the mean absolute trajector error by 76.2%. It establishes a more realistic and accurate 3D dense point cloud map of underground roadway.

Due to the impact of high dust and low illumination in underground environments, mine images have problems such as low resolution and blurry details. When existing image super-resolution reconstruction algorithms are applied to mine images, it is difficult to obtain image information at different scales. The network parameters are too large, which affects the reconstruction speed. The reconstructed images are prone to problems such as detail loss, blurry edge contours, and artifacts. A mine image super-resolution reconstruction algorithm based on multi-scale dense channel attention super-resolution generative adversarial network (SRGAN) is proposed. A multi-scale dense channel attention residual block is designed to replace the original residual block of SRGAN. Two parallel dense connected blocks with different convolutional kernel sizes are used to fully obtain image features. The efficient channel attention modules are integrated to enhance attention to high-frequency information. The depthwise separable convolution is used to lighten the network and suppress the increase of network parameters. The texture loss constraint network training is utilized to avoid artifacts during network deepening. Experiments are conducted on the proposed mine image super-resolution reconstruction algorithm and classic super-resolution reconstruction algorithms BICUBIC, SRCNN, SRRESNET, SRGAN on both underground and public datasets. The results show that the proposed algorithm outperformed the comparative algorithm in both subjective and objective evaluations. Compared to SRGAN, the proposed algorithm reduces network parameters by 2.54%. Compared to the average index values of the classic algorithms, the peak signal-to-noise ratio and structural similarity of the proposed algorithm increase by 0.764 dB and 0.053 58 respectively. It can better focus on the texture, contour and other details of the image, and the reconstructed image is more in line with human vision.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at problem that dictionary learning method was poorly effective in reconstruction of mine image with noise and complex environment, a super-resolution reconstruction method of mine image based on online multi-dictionary learning was proposed. The method uses K-means clustering algorithm to divide image training set into multiple kinds of images, and trains multiple sets of high-resolution dictionaries and low-resolution dictionaries for different kinds of images, so as to improve feature representation ability of the dictionaries for complex environmental images. According to non-local self-similarity of image, non-local constraint is introduced to further constrain solution space of sparse coefficient, and online dictionary learning is used to optimize the dictionaries in the multi-dictionary learning stage, so as to improve accuracy of sparse coefficient solution and anti-noise interference ability of image reconstruction process. The experimental results show that the method can effectively improve quality of reconstructed image, suppress image blocking effect and edge jagged effect caused by noise, enhance image details, and achieve better visual effect.

The multi-scale Retinex algorithm has some problems such as insufficient detail enhancement and long time-consumption in processing low-illumination image of underground coal mine. Aiming at the problem, a fast multi-scale Retinex algorithm based on illumination correction was proposed to enhance low-illumination image of underground coal mine. By calculating brightness value of each pixel of image after gaussian blur, the image is divided into dark and highlight areas, and illumination correction is carried out on dark and highlight areas, so as to reduce brightness of highlight area to avoid overexposure, and improve brightness of dark area to highlight more details. Three-times fast mean filtering is used instead of Gaussian filtering to estimate illumination intensity, so as to reduce time-consumption of the algorithm. The experimental results show that the algorithm can effectively improve brightness and contrast of image, enhance details of dark and highlight areas in image, and has fast processing speed.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

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.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)