An algorithm based on the YOLOv5 model is proposed to address safety incidents such as tearing and blockage at transfer points on belt conveyors in coal mines caused by foreign objects mixed in with the coal flow. Given the tough underground conditions and images acquired with low quality, recursive filtering and MSRCR image enhancement algorithms were utilized to preprocess the dynamic images collected by underground monitoring devices, substantially enhancing image quality. The YOLOv5 model has been improved by introducing a multi-scale attention module (MSAM) during the channel map slicing, thereby increasing the model’s resistance to interference from redundant image features. Deep separable convolution was utilized in place of conventional convolution to detect, identify, and process large foreign objects on the belt conveyor as well as to increase detection speed. The MSAM-YOLOv5 model was trained before being installed on the NVIDIA Jetson Xavier NX platform and utilized to identify videos gathered from the coal mine belt conveyor. According to the experimental findings, the upgraded MSAM-YOLOv5 model has a greater recognition accuracy than YOLOv5L, with an average recall rate for different foreign objects of 96.27%, an average detection accuracy of 97.35%, and a recognition speed of 44 frames/s. The algorithm assures detection accuracy while increasing detection speed, satisfying the requirements for large foreign object detection on belt conveyors in coal mines.

This study addresses the challenges of low accuracy and high computational demands in Tibetan speech recognition by investigating the application of end-to-end networks. We propose a decoding strategy that integrates Connectionist Temporal Classification (CTC) and Attention mechanisms, capitalizing on the benefits of automatic alignment and attention weight extraction. The Conformer architecture is utilized as the encoder, leading to the development of the Conformer-CTC/Attention model. This model first extracts global features from the speech signal using the Conformer, followed by joint decoding of these features through CTC and Attention mechanisms. To mitigate convergence issues during training, particularly with longer input feature sequences, we introduce a Probabilistic Sparse Attention mechanism within the joint CTC/Attention framework. Additionally, we implement a maximum entropy optimization algorithm for CTC, effectively addressing challenges such as increased path counts, spike distributions, and local optima during training. We designate the proposed method as the MaxEnt-Optimized Probabilistic Sparse Attention Conformer-CTC/Attention Model (MPSA-Conformer-CTC/Attention). Experimental results indicate that our improved model achieves a word error rate reduction of 10.68% and 9.57% on self-constructed and open-source Tibetan datasets, respectively, compared to the baseline model. Furthermore, the enhanced model not only reduces memory consumption and training time but also improves generalization capability and accuracy.

The dim lighting and excessive dust in underground mines often result in uneven illumination, blurriness, and loss of detail in surveillance images, which hinders subsequent intelligent image recognition. To address the limitations of the existing image enhancement algorithms in terms of generalization and accuracy, this paper proposes an unsupervised method for enhancing mine images in the hue–saturation–value (HSV) color space. Inspired by the HSV color space, the method first converts RGB images to the HSV space and integrates Retinex theory into the brightness (V channel). Additionally, a random perturbation technique is designed for the brightness. Within the same scene, a U-Net-based reflectance estimation network is constructed by enforcing consistency between the original reflectance and the perturbed reflectance, incorporating ResNeSt blocks and a multi-scale channel pixel attention module to improve accuracy. Finally, an enhanced image is obtained by recombining the original hue (H channel), brightness, and saturation (S channel), and converting back to the RGB space. Importantly, this image enhancement algorithm does not require any normally illuminated images during training. Extensive experiments demonstrated that the proposed method outperformed most existing unsupervised low-light image enhancement methods, qualitatively and quantitatively, achieving a competitive performance comparable to many supervised methods. Specifically, our method achieved the highest PSNR value of 22.18, indicating significant improvements compared to the other methods, and surpassing the second-best WCDM method by 10.3%. In terms of SSIM, our method also performed exceptionally well, achieving a value of 0.807, surpassing all other methods, and improving upon the second-place WCDM method by 19.5%. These results demonstrate that our proposed method significantly enhanced image quality and similarity, far exceeding the performance of the other algorithms.

The abnormal structural state of the pantograph skateboard is a significant and highly concerning issue that has a significant impact on the safety of high-speed railway operation. In order to obtain real-time information on the abnormal state of the skateboard in advance, an intelligent defect identification model suitable to be used as a monitoring device for the pantograph skateboard was designed using a computer vision-based intelligent detection technology for pantograph skateboard defects, combined with an improved YOLO v8 model and traditional image processing algorithms such as edge extraction. The results show that the anomaly detection algorithm for the pantograph sliding plate structure has good robustness, maintaining recognition accuracy of 90% or above in complex scenes, and the average runtime is 12.32 ms. Railway field experiments have proven that the intelligent recognition model meets the actual detection requirements of railway sites and has strong practical application value.

The abnormal structural state of the pantograph skateboard is a significant and highly concerned issue that has a sig-nificant impact on the safety of high-speed railway operation. In order to obtain real-time information on the abnormal state of the skateboard in advance, a defect intelligent identification model suitable for the monitoring device of the pantograph skate-board was designed using computer vision based intelligent detection technology for pantograph skateboard defects, combined with improved YOLO v8 model and traditional image processing algorithms such as edge extraction. The results show that the anomaly detection algorithm for the pantograph sliding plate structure has good robustness, maintaining recognition accuracy of 90% or above in complex scenes, and the average time is 12.32ms. Railway field experiments have proven that the intelligent recognition model meets the actual detection requirements of railway sites and has strong practical application value.

In an effort to overcome the difficulty of real-time early warning via traditional infrared imaging technology caused by the complex working environment in coal mines, this paper proposes a mine early warning method based on uncooled infrared focal plane technology. The infrared thermal spectrogram of the detected object was visually displayed in a pseudo-color image with high resolution and high sensitivity, which can realize the real-time detection and early warning of personnel safety in modern mines. The multipoint compression correction algorithm based on human visual characteristics divided the response units of all acquisition units into gray intervals according to a threshold value, then the corresponding parameters were set in different intervals, and finally, each interval was compressed using a two-point correction algorithm. The volume of stored data was the sum of the calibration curve and the data from an encode table corrected by a MATLAB simulation, and the number of CPU cycles was run by a CCS 3.3 clock calculation algorithm. The results showed that when the temperature of the blackbody reached 115 °C, the nonuniformity before correction was 6.32%, and the nonuniformity after the multipoint correction of human eyes was 2.99%, which implied that the algorithm proposed in this paper had good denoising ability. The number of CPU cycles occupied by this algorithm was 18,257,363 cycles/frame with a frequency of 29.97 Hz. The sharpness of the compressed infrared images was obviously improved, and the uniformity was better. The method proposed in this paper can meet the need for modern mine personnel search and rescue, equipment supervision and dangerous area detection and other early warning requirements so as to achieve the goal of developing smart mines and ensuring safety in coal mine production.