Search

The distribution features of coal particle size are closely related to the analysis of methane gas propagation in coal. At present, the coal particle size analysis method based on image segmentation has become one of the mainstream solutions to obtain coal particle size. But there are problems such as loss of contextual information, improper fusion of coal particle features resulting in missed segmentation and over-segmentation of coal particles. In order to solve the above problems, a coal particle size analysis model based on bi-level routing attention (BRA) is designed. The BRA module is embedded in the residual U-shaped network ResNet-UNet to obtain the B-ResUNet network model. To reduce the problem of missed segmentation in coal particle segmentation, a BRA module is added before upsampling in the ResNet-UNet network. It allows the network to adjust the importance of the current feature layer based on the features of the previous layer, enhance the expression capability of features, and improve the transmission capability of long-distance information. To reduce the problem of over segmentation in coal particle segmentation, a BRA module is added after the feature concatenation module of the ResNet-UNet network. By dynamically selecting and aggregating important features, more effective feature fusion is achieved. The feature information from the segmented coal particles is extracted. The coal particle size of the coal particle dataset used in the experimental analysis is equivalent to the cell size. In order to accurately characterize the coal particle size, equivalent circular particle size is used to obtain the coal particle size and size distribution. The experimental results show the following points. ① The accuracy, average intersection to union ratio, and recall of the B-ResUNet network model have been improved by 06.%, 14.3%, and 35.9% compared to the ResNet-UNet basic network, with an accuracy of 99.6%, an average intersection to union ratio of 92.6%, and a recall of 94.4%. The B-ResUNet network model has good segmentation performance in coal samples and can detect relatively complete particle structures. ② When the BRA module is introduced before upsampling and after feature concatenation, the network pays sufficient attention to the edge areas of coal particles and reduces attention to some less important areas, thereby improving the computational efficiency of the network. ③ The particle size of coal particles shows a relatively balanced distribution trend within 1-2 mm, with the maximum proportion of coal particles within 1-2 mm being 99.04% and the minimum being 90.59%. It indicates that the image processing method based on BRA has high accuracy in particle size analysis.

The existing image super-resolution reconstruction networks are difficult to apply to noise intensive application scenarios in coal mines. Most networks improve performance by increasing depth, which leads to problems such as ineffective extraction of key features and loss of high-frequency information. In order to solve the above problems, a dense residual connected U-shaped network is proposed for super-resolution reconstruction of low resolution noisy images. The denoising module based on dense residual connections is introduced in the feature extraction path, fully extracting image features through dense connections. The features of residual learning are used to effectively denoise low resolution noisy images. The residual feature attention distillation module is introduced in the reconstruction path, by incorporating enhanced feature attention blocks into the residual blocks, different weights are assigned to features in different spaces to enhance the network's capability to extract key image features. The loss of image detail features is reduced in the residual blocks, thus better restoring image detail information. Comparative experiments are conducted on coal mine underground image datasets and public datasets, and the results show that in terms of objective evaluation index, structure similarity and image perception similarity of the proposed network are superior to the comparison network. It has a good balance in complexity and running speed. In terms of subjective visual effects, the image reconstructed by the proposed network basically eliminates the original image noise and effectively restores the detailed features of the image.

Intelligence is the direction of coal mine development, and intelligent video analysis is an effective way to promote coal mine intelligence. The mine-wide intelligent video analysis technology has real-time monitoring, early warning, and decision support capabilities. It helps to improve the safety, production efficiency, resource utilization efficiency, and environmental sustainability of mining enterprises. The key technologies of mine-wide intelligent video analysis are introduced in detail, including video acquisition and processing technologies such as video acquisition equipment, video pre-processing, video compression and coding, basic video analysis technologies such as object detection and tracking, motion detection and analysis, object recognition and classification, and advanced video analysis technologies such as behaviour recognition and analysis, event detection and alarm, video monitoring and arming. A mining intelligent AI visual intelligence service platform that integrates video recognition analysis and industrial linkage control functions is developed. The paper introduces the application of intelligent video analysis technology in mining production scenarios such as intelligent water and gas exploration and discharge systems, coal rock recognition and cutting systems, heading working faces, fully mechanized working faces, coal flow transportation systems, mine hoist systems, auxiliary transportation systems, coal preparation plants, and intelligent loading and coal blending systems. The analysis points out that the current mine-wide intelligent video analysis technology still faces challenges in terms of video quality, complex backgrounds, real-time requirements, data privacy and security, system reliability and stability, etc. It is suggested to strengthen the research on algorithm improvement and optimization, multimodal data fusion, real-time analysis and edge computing, enhanced learning and independent decision-making, data privacy and security protection, hardware equipment and sensor technology in the future. Therefore, the development of mine-wide intelligent video analysis technology is comprehensively promoted and promote the process of mine intelligence is promoted.

The video analysis and identification technology of coal mine safety production is the core technical support to ensure the intelligent construction of our country's coal mines and the high-quality development of the coal industry. In order to carry out real-time monitoring and early warning for potential safety hazards in coal mines, the key technologies of video AI (Artificial Intelligence) identification have become the research hotspot in the field of safety production in coal mines. In this paper, the development status of safety monitoring in the process of intelligent construction of coal mines are first expounded. Then, the problems of low efficiency, slow response and poor effect of the current mine video monitoring and safety hazard identification as well as early warning system are concluded. Combined with advanced technologies such as computer vision, edge computing, big data processing, cloud services, and intelligent terminals, the top-level design of AI recognition for coal mine safety production video is carried out. Furthermore, the “cloud-edge-terminal” collaborative computing system architecture of “human-machine-environment” global video AI perception in coal mines is also proposed, followed with a video recognition end node sensor, edge computing equipment, and video recognition scene cloud service application system constructed. By this way, the intelligent identification and early warning linkage control response mechanism are clarified, and the “cloud-edge-terminal” information interactive perception and linkage control data chain has been dredged, resulting with data sharing linkage and early warning coordination. At the same time, around the construction of the “human-machine-environment” global AI visual information intelligent perception and holographic generalized scene platform, the technical processing process of visual perception and identification and early warning of mine safety hazards has been sorted out. What’s more, the characteristic of the processing-enhancement-reconstruction-detection-recognition method are also summarized, and the mainstream direction and trend of the key technology development of coal mine safety production video AI recognition are also pointed out. Secondly, based on the application cases of representative mines such as Wangjialing Coal Mine and Baodian Coal Mine, the author demonstrates the latest progress and application effects of typical application scenarios in the process of coal mine safety production. Finally, according to the key technology characteristics of coal mine safety production video AI recognition, it is concluded that the existing coal mine safety production video AI recognition system has weak technical theory, different specifications of intelligent terminals, confusing application scenarios, poor data compatibility and linkage closed-loop ability, weak database security, inconsistent evaluation mechanism as well as imperfect application standards, etc. Subsequently, this paper pointed out that the future development direction is to strengthen the research on key technologies and theories of video AI recognition, establish and improve intelligent terminal hardware specifications and applicable systems and build a new coal mine information multi-dimensional active perception model and industrial internet application platform with unified standards, perfect mechanism, real-time interconnection, dynamic prediction, collaborative control, safety and reliability, which gradually form a high-precision intelligent perception field of holographic generalization in the whole mine, so as to realize the precise perception of the underground "human-machine-environment" global video information and the coordinated control of danger sources.

Feature extraction plays a pivotal role in the context of single image super-resolution. Nonetheless, relying on a single feature extraction method often undermines the full potential of feature representation, hampering the model's overall performance. To tackle this issue, this study introduces the wide-activation feature distillation network (WFDN), which realizes single image super-resolution through dual-path learning. Initially, a dual-path parallel network structure is employed, utilizing a residual network as the backbone and incorporating global residual connections to enhance feature exploitation and expedite network convergence. Subsequently, a feature distillation block is adopted, characterized by fast training speed and a low parameter count. Simultaneously, a wide-activation mechanism is integrated to further enhance the representational capacity of high-frequency features. Lastly, a gated fusion mechanism is introduced to weight the fusion of feature information extracted from the dual branches. This mechanism enhances reconstruction performance while mitigating information redundancy. Extensive experiments demonstrate that the proposed algorithm achieves stable and superior results compared to the state-of-the-art methods, as evidenced by quantitative evaluation metrics tests conducted on four benchmark datasets. Furthermore, our WFDN excels in reconstructing images with richer detailed textures, more realistic lines, and clearer structures, affirming its exceptional superiority and robustness. [ABSTRACT FROM AUTHOR]

The Contrastive Language-Image Pre-training model (CLIP) has recently gained attention in the zero-shot domain. However it still falls short in addressing cross-modal perception, and the semantic gap between seen and unseen classes in Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR). To overcome these obstacles, we propose a Task-Like Training paradigm (TLT). In this work, we view the cross-modal perception and the semantic gap as a multi-task learning process. Before tackling the challenges, we fully utilize CLIP's text encoder and propose text-based identification learning mechanism to assist the model to learn discriminative features quickly. Next, we propose text prompt tutoring and the cross-modal consistency learning to solve cross-modal perception and the semantic gap, respectively. Meanwhile, we present a collaborative architecture to explore the potential shared information between tasks. Extensive results show that our approach significantly outperforms the state-of-the-art methods on Sketchy, Sketchy-No, Tuberlin, and QuickDraw datasets. [ABSTRACT FROM AUTHOR]

For high error matching rate and poor real-time performance of global motion vector estimation caused by foreground moving target and high noise in video image captured by mine vehicle camera system, a vehicle video image stabilization algorithm for mine was proposed which was based on ORB feature matching and improved particle filter. In motion vector estimation stage, ORB algorithm is used to complete extraction of image feature points firstly. Then continuous three-frame difference method based on image block is adopted to quickly mark foreground movement area jointing space-time consistency criteria. Combined with foreground mark area, location of feature points is selected for the first time, and retained points are registered. Finally, affine transformation model is used to estimate motion vectors among frames. In motion filtering stage, a real-time particle filter algorithm based on estimation window is used to filter jitter components, and compensation parameters are obtained. The experimental results show that the proposed algorithm can effectively avoid influence of foreground moving target on image stabilization precision, and has quick processing speed.