ECViST: Mine Intelligent Monitoring Based on Edge Computing and Vision Swin Transformer-YOLOv5

Abstract

Mine video surveillance has a key role in ensuring the production safety of intelligent mining. However, existing mine intelligent monitoring technology mainly processes the video data in the cloud, which has problems, such as network congestion, large memory consumption, and untimely response to regional emergencies. In this paper, we address these limitations by utilizing the edge-cloud collaborative optimization framework. First, we obtained a coarse model using the edge-cloud collaborative architecture and updated this to realize the continuous improvement of the detection model. Second, we further proposed a target detection model based on the Vision Swin Transformer-YOLOv5(ViST-YOLOv5) algorithm and improved the model for edge device deployment. The experimental results showed that the object detection model based on ViST-YOLOv5, with a model size of only 27.057 MB, improved the average detection accuracy is by 25% compared to the state-of-the-art model, which makes it suitable for edge-end deployment in mining workface. For the actual mine surveillance video, the edge-cloud collaborative architecture can achieve better performance and robustness in typical application scenarios, such as weak lighting and occlusion, which verifies the feasibility of the designed architecture.

The Future of Mine Safety: A Comprehensive Review of Anti-Collision Systems Based on Computer Vision in Underground Mines

“…Connected mines [12][13][14]121,122] can be equipped with smart sensors that can monitor the environment and send real-time alerts to miners in case of danger. Cloud computing [123,124] can be used to store and analyze data collected by sensors, allowing anti-collision systems to benefit from additional computing power to improve accuracy and responsiveness. A multi-sensor system [22,62,125] uses a combination of sensors, such as cameras, radar, LIDAR, and proximity sensors to collect information about the environment around the mobile mining machines and allowing miners to more easily detect potential hazards .…”

Recent Advancements in IoT Implementation for Environmental, Safety, and Production Monitoring in Underground Mines

“…This system achieved a forecast accuracy of 94.23%. Zhang et al [31] used the Vision Swin Transformer-YOLOv5 algorithm to develop an object detection model that was capable of handling data captured by underground mine surveillance cameras. The proposed model improved the average detection accuracy by 25%, and was designed to operate at the edge due to its low memory and computational requirements.…”