Detecting disasters in underground mining, such as explosions and structural damage, has been a persistent challenge over the years. This problem is compounded for first responders, who often have no clear information about the extent or nature of the damage within the mine. The poor light or even total darkness inside the mines makes rescue efforts incredibly difficult, leading to a tragic loss of life. In this paper, we propose a novel instance segmentation method called DIS-Mine, specifically designed to identify disaster-affected areas within underground mines under low-light or poor visibility conditions, aiding first responders in rescue efforts. DIS-Mine is capable of detecting objects in images, even in complete darkness, by addressing challenges such as high noise, color distortions, and reduced contrast. The key innovations of DIS-Mine are built upon four core components: i) Image brightness improvement, ii) Instance segmentation with segment anything model (SAM) integration, iii) Mask R-CNN-based segmentation, and iv) Mask alignment with feature matching. On top of that, we have collected real-world images from an experimental underground mine, introducing a new dataset named ImageMine, specifically gathered in low-visibility conditions. This dataset serves to validate the performance of DIS-Mine in realistic, challenging environments. Our comprehensive experiments on the ImageMine dataset, as well as on various other datasets demonstrate that DIS-Mine achieves a superior F1 score of 86% and mIoU of 72%, outperforming state-of-the-art instance segmentation methods, with at least 15x improvement and up to 80% higher precision in object detection.We have made our dataset publicly accessible through ImageMine Dataset.

Detecting disasters in underground mining, such as explosions and structural damage, has been a persistent challenge over the years. This problem is compounded for first responders, who often have no clear information about the extent or nature of the damage within the mine. The poor light or even total darkness inside the mines makes rescue efforts incredibly difficult, leading to a tragic loss of life. In this paper, we propose a novel instance segmentation method called DIS-Mine, specifically designed to identify disaster-affected areas within underground mines under low-light or poor visibility conditions, aiding first responders in rescue efforts. DIS-Mine is capable of detecting objects in images, even in complete darkness, by addressing challenges such as high noise, color distortions, and reduced contrast. The key innovations of DIS-Mine are built upon four core components: i) Image brightness improvement, ii) Instance segmentation with segment anything model (SAM) integration, iii) Mask R-CNN-based segmentation, and iv) Mask alignment with feature matching. On top of that, we have collected real-world images from an experimental underground mine, introducing a new dataset named ImageMine, specifically gathered in low-visibility conditions. This dataset serves to validate the performance of DIS-Mine in realistic, challenging environments. Our comprehensive experiments on the ImageMine dataset, as well as on various other datasets demonstrate that DIS-Mine achieves a superior F1 score of 86% and mIoU of 72%, outperforming state-of-the-art instance segmentation methods, with at least 15x improvement and up to 80% higher precision in object detection.We have made our dataset publicly accessible through ImageMine Dataset.

Location-based distributed communication in underground mines has been a hard problem to solve due to unreliable centralized architecture such as leaky feeder systems, high attenuation, and the unavailability of GPS signals. Delay Tolerant Networks (DTN) enable decentralized message routing using the store-carry-forward method that can help in creating situational awareness needed to handle emergency and disaster scenarios. The ability to predict where the DTN nodes (miner) might have been at/are headed to (with respect to the mine regions and pillars) at different times, combined with contact-based routing and intelligent handling of buffer, can be used for better delivery of messages. To this end, we propose a hybrid approach, called MinerRouter, that uses Random Forest (RF) and Graph Autoencoder (GAE) - Long Short Term Memory (LSTM) model to exploit the short- and long-mobility patterns of miners, respectively for faster message/content dissemination. Our simulations show that MinerRouter outperforms Opportunistic RF (RF), Opportunistic Contact Graph Routing (O-CGR), MaxProp, SemiBlind, and Blind routing protocols in terms of the delivery ratio of messages received, message latency, buffer occupancy Rate, communication overhead costs, and hop count.

Recent reports by the Mine Safety and Health Administration suggest that several injuries and fatalities could be attributed to the inability to accurately locate miners in case of disasters. Since underground mines have a complicated geometrical landscape and technological constraints such as no GPS information available, it is difficult to predict the location of a miner and hence may cause delays and inefficiencies in rescue operations during a disaster. A significant amount of research has been done to capture complex spatio-temporal relationships of movement of the nodes/people/things with time, spatial and temporal features to separately extract these relationships for location prediction. Although Markov Chains (MC) and Recurrent Neural Network (RNN) based methods have been used to predict locations, not all of them specifically mention the spatial locations, their connections and the aggregation techniques which would allow for the actual representations of the trajectory of miners. Addressing these concerns, we develop a first-of-its-kind end-to-end system entitled MinerFinder to predict the future location of the miners by incorporating Long Short Term Memory (LSTM) for trajectory information with Graph Autoencoder (GAE) for spatial environmental information representing the node connectivity. In addition, our approach will combine the miners' previous trajectories and daily repetitive patterns enhancing the prediction robustness. We evaluated MinerFinder over synthetic dataset to analyze the structure and location topology of an underground mine compared with foreground locations. Our model outperforms state of the art models and achieves an AP score ranging from (0.62 - 0.68) and Receiver Operating Characteristics (ROC) ranging from (0.63--0.68) with increasing percentage of prominent locations (most visited) to 50%.