Precise Ground Truth Research Articles

Automatic Ground-Truth Image Labeling for Deep Neural Network Training and Evaluation Using Industrial Robotics and Motion Capture

Abstract The United States Navy (USN) intends to increase the amount of uncrewed aircraft in a carrier air wing. To support this increase, carrier-based uncrewed aircraft will be required to have some level of autonomy as there will be situations where a human cannot be in/on the loop. However, there is no existing and approved method to certify autonomy within Naval Aviation. In support of generating certification evidence for autonomy, the United States Naval Academy (USNA) has created a training and evaluation system (TES) to provide quantifiable metrics for feedback performance in autonomous systems. The preliminary use case for this work focuses on autonomous aerial refueling. Prior demonstrations of autonomous aerial refueling have leveraged a deep neural network (DNN) for processing visual feedback to approximate the relative position of an aerial refueling drogue. The training and evaluation system proposed in this work simulates the relative motion between the aerial refueling drogue and feedback camera system using industrial robotics. Ground-truth measurements of the pose between the camera and drogue are measured using a commercial motion capture system. Preliminary results demonstrate calibration methods providing ground-truth measurements with millimeter precision. Leveraging this calibration, the proposed system is capable of providing large-scale datasets for DNN training and evaluation against a precise ground truth.

Regularized Loss With Hyperparameter Estimation for Weakly Supervised Single Class Segmentation.

We propose a new image level weakly supervised segmentation approach for datasets with a single object class of interest. Our approach is based on a regularized loss function inspired by the classical Conditional Random Field (CRF) modeling. Our loss models properties of generic objects, and we use it to guide CNN towards segments that are more likely to correspond to the object, thus avoiding the need for pixel precise annotations. Training CNN with regularized loss is a difficult task for gradient descent. We develop an annealing algorithm which is crucial for a successful training. Furthermore, we develop an approach for hyperparameter setting for the most important components of our regularized loss. This is far from trivial, since there is no pixel precise ground truth for guidance. The advantage of our method is that we use a standard CNN architecture and an easy to interpret loss function, derived from classical CRF models. Furthermore, we apply the same loss function for any task/dataset. We first evaluate our approach for salient object segmentation and co-segmentation. These tasks naturally involve one object class of interest. Then we adapt our approach to image level weakly supervised multi-class semantic segmentation. We obtain state-of-the-art results.

Saliency and boundary guided segmentation framework for cell counting in microscopy images

Improving the segmentation accuracy of cells from microscopy images directly benefits medical practitioners for differential cell counting, disease diagnosis, and treatment. However, separating each cell continues to be challenging, especially when the cells appear in clumps. Recent advancements in deep learning have demonstrated success in automating cell segmentation and counting, but they necessitate large volumes of annotated data for training. Creating precise ground truth for cell segmentation is laborious and demands expertise due to the intricate and varied characteristics of microscopy images. Consequently, this complexity poses a challenge to the practicality of implementing deep neural network-based solutions for microscopy cell segmentation. This paper addresses a significant research gap by exploring the underutilized traditional image features to build a lightweight deep-learning framework for cell boundary segmentation that can be effectively trained with a limited amount of labeled data. We have developed Saliency Guided Attention Module Network (SGAM-net), which uses perceptual features inherent along the cell boundaries and poses cell segmentation as a thick boundary prediction problem with the aim to separate the cells. SGAM-net uses a specialized attention mechanism to combine the perceptual feature maps with the learned features. When tested on the three public bench-mark microscopy datasets, with respect to the base Unet model, there is an increase of 1.36%, 1.29%, and 6.35% in Dice score and 2.39%, 2.31% and 6.99% in Intersection Over Union (IOU) score. The model requires only 23.07% less parameters than Unet++ model. The potential of SGAM-net in segmenting boundaries semantically has been demonstrated, and it is further processed to compute cell counts. The model outperformed the state-of-the-art instance separation method ‘Stardist’ in cell counting by giving a reduction ratio of 2.34, 1.89, and 2.03 on the metric ‘mean absolute error’.

ZUST Campus: A Lightweight and Practical LiDAR SLAM Dataset for Autonomous Driving Scenarios

This research proposes a lightweight and applicable dataset with a precise elevation ground truth and extrinsic calibration toward the LiDAR (Light Detection and Ranging) SLAM (Simultaneous Localization and Mapping) task in the field of autonomous driving. Our dataset focuses on more cost-effective platforms with limited computational power and low-resolution three-dimensional LiDAR sensors (16-beam LiDAR), and fills the gaps in the existing literature. Our data include abundant scenarios that include degenerated environments, dynamic objects, and large slope terrain to facilitate the investigation of the performance of the SLAM system. We provided the ground truth pose from RTK-GPS and carefully rectified its elevation errors, and designed an extra method to evaluate the vertical drift. The module for calibrating the LiDAR and IMU was also enhanced to ensure the precision of point cloud data. The reliability and applicability of the dataset are fully tested through a series of experiments using several state-of-the-art LiDAR SLAM methods.

NERFBK: A HOLISTIC DATASET FOR BENCHMARKING NERF-BASED 3D RECONSTRUCTION

Abstract. Neural Radiance Field methods are innovative solutions to derive 3D data from a set of oriented images. This paper introduces new real and synthetic image datasets - called NeRFBK - specifically designed for testing and comparing NeRF-based 3D reconstruction algorithms. More and more reconstruction algorithms and techniques are available nowadays, raising the need to evaluate and compare the quality of derived 3D products currently used in various domains and applications. However, gathering diverse data with precise ground truth is challenging and may not encompass all relevant applications. The NeRFBK dataset addresses this issue by providing multi-scale, indoor and outdoor datasets with high-resolution images and videos and camera parameters for testing and comparing NeRF-based algorithms. This paper presents the design and creation of the NeRFBK set of data, various examples and application scenarios, and highlights its potential for advancing the field of 3D reconstruction.

Self-Supervised Depth Correction of Lidar Measurements From Map Consistency Loss

Depth perception is considered an invaluable source of information in the context of 3D mapping and various robotics applications. However, point cloud maps acquired using consumer-level <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">light detection and ranging</i> sensors (lidars) still suffer from bias related to local surface properties such as measuring beam-to-surface incidence angle. This fact has recently motivated researchers to exploit traditional filters, as well as the deep learning paradigm, in order to suppress the aforementioned depth sensors error while preserving geometric and map consistency details. Despite the effort, depth correction of lidar measurements is still an open challenge mainly due to the lack of clean 3D data that could be used as ground truth. In this paper, we introduce two novel point cloud map consistency losses, which facilitate self-supervised learning on real data of lidar depth correction models. Specifically, the models exploit multiple point cloud measurements of the same scene from different view-points in order to learn to reduce the bias based on the constructed map consistency signal. Complementary to the removal of the bias from the measurements, we demonstrate that the depth correction models help to reduce localization drift. Additionally, we release a data set that contains point cloud scans captured in an indoor corridor environment with precise localization and ground truth mapping information <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{1}$</tex-math></inline-formula> .

Interaction Control of a Robotic Manipulator With the Surface of Deformable Object

Robotic manipulation of deformable objects has drawn the attention of researchers over the past few years and is associated with a large spectrum of new application perspectives. In this article, we present an efficient integrated motion planning framework to effectively and accurately control a robotic manipulator executing interactive tasks on the surface of a deformable object. The proposed interactive motion planning framework is based on a mesh representation of the object, integrating three efficient preprocessing algorithmic steps, including visual object segmentation, finite element method deformation tracking, and local mesh parameterization. The use of barycentric coordinates, defined on the mesh triangles, enables the establishment of bijective transformations between the deformable part of an object surface and its planar (static and dynamic) parameterized mapping. By merging these spatial transformations with the preprocessing steps, in combination with an active stiffness scheme for robot manipulator control, we are able to achieve accurate and reactive motion planning of interactive trajectories, even under large and persistent visual occlusions (such as due to the presence of the robot in the visual scene). An extensive experimental evaluation study is presented, involving a robotic manipulator in interaction with a hemispherical model of controllable periodic active deformation, which permits precise ground truth derivation. Motion planning accuracy is evaluated in comparison with our previous direct vision-based approach, showing clearly superior performance of the proposed approach under all experimental conditions. The performance of the proposed framework is also further highlighted in tasks involving physical point tracking, interactive programming by human demonstration, as well as contact force regulation.

Weakly supervised identification of microscopic human breast cancer-related optical signatures from normal-appearing breast tissue.

With the latest advancements in optical bioimaging, rich structural and functional information has been generated from biological samples, which calls for capable computational tools to identify patterns and uncover relationships between optical characteristics and various biomedical conditions. Constrained by the existing knowledge of the novel signals obtained by those bioimaging techniques, precise and accurate ground truth annotations can be difficult to obtain. Here we present a weakly supervised deep learning framework for optical signature discovery based on inexact and incomplete supervision. The framework consists of a multiple instance learning-based classifier for the identification of regions of interest in coarsely labeled images and model interpretation techniques for optical signature discovery. We applied this framework to investigate human breast cancer-related optical signatures based on virtual histopathology enabled by simultaneous label-free autofluorescence multiharmonic microscopy (SLAM), with the goal of exploring unconventional cancer-related optical signatures from normal-appearing breast tissues. The framework has achieved an average area under the curve (AUC) of 0.975 on the cancer diagnosis task. In addition to well-known cancer biomarkers, non-obvious cancer-related patterns were revealed by the framework, including NAD(P)H-rich extracellular vesicles observed in normal-appearing breast cancer tissue, which facilitate new insights into the tumor microenvironment and field cancerization. This framework can be further extended to diverse imaging modalities and optical signature discovery tasks.

PHOTOREALISTIC AND SYNTHETIC STEREO-DATASET GENERATION METHOD FOR VISUAL ODOMETRY AND DEPTH ESTIMATION

Computer vision is a rapidly developing field in modern computer science that deals with various challenging problems. Both mono and stereo imagery data are widely used for tasks such as depth estimation, visual odometry, and SLAM (Simultaneous Localization and Mapping). To ensure the clean verification and robust performance of the resulting software solutions, datasets should contain precise ground truth data. However, creating a real-world stereo dataset is a costly task as it requires stereo cameras and precise hardware for ground truth measurements (such as lidars, lasers, barometers, accelerometers, etc.). The¬se types of hardware are often expensive and not accessible to intermediate users. An alternative approach is to use synthetic datasets, which are collections of computer-gener¬a¬te¬d data designed to mimic real-world data. Synthetic datasets are used to train AI models wh¬e¬n real-world data is not available, or to test the performance of models in simulated environ¬m¬ents. Our method suggests combining real-world data collection with synthetic data gene¬rat¬ion methods to maintain photorealism while gaining the advantages of synthetic data generation flow.

Performance metrics of AI-enhanced single lead EKG maintained after entry of organised clustered data

Abstract Background Our experience in creating innovative Artificial Intelligence-guided single lead EKG methodologies for ST-Elevation Myocardial Infarction (STEMI) detection within complex EKG records has been previously validated. Purpose By expanding the intricate variables of our previously tested algorithm input, we seek to further improve our STEMI detecting tool. Methods 11,567 12-lead EKG records (10-s length, 500 Hz sample frequency) derived from the Latin America Telemedicine Infarct Network database from April 2014 to December 2019. From these records, we included the following balanced classes: angiographically confirmed and unconfirmed STEMI (divided by wall affected), branch blocks, non-specific ST-T changes, normal, and abnormal (Remaining 200+ CPT codes). Cardiologist annotations ensured precision (Ground truth). Determined classes were “STEMI” and “Not-STEMI”. A 1-D Convolutional Neural Network model was trained and tested for each lead with dataset proportions of 90/10, respectively. The last dense layer outputs a probability for each record being STEMI/Not-STEMI. The analysis also included performance metrics and false-negative reports. Results Overall, the most promising Single lead for STEMI detection was V2 (91.2% Accuracy, 89.6% Sensitivity, and 92.9% Specificity). 55% of false negatives were inferior wall STEMI (Table 1). Conclusion Appreciable progress of our new methodology compared to our previous experiences in AI-guided Single Lead for STEMI detection, especially for lead V2. By performing a thorough analysis of false-negative reports, we aspire to identify potential areas of STEMI detection weakness which will become the focus of future ventures. Funding Acknowledgement Type of funding sources: None.

Performance metrics of AI-enhanced single lead EKG maintained after entry of organised clustered data

Abstract Background Our experience in creating innovative Artificial Intelligence-guided single lead EKG methodologies for ST-Elevation Myocardial Infarction (STEMI) detection within complex EKG records has been previously validated. Purpose By expanding the intricate variables of our previously tested algorithm input, we seek to further improve our STEMI detecting tool. Methods 11,567 12-lead EKG records (10-s length, 500 Hz sample frequency) derived from the Latin America Telemedicine Infarct Network database from April 2014 to December 2019. From these records, we included the following balanced classes: angiographically confirmed and unconfirmed STEMI (divided by wall affected), branch blocks, non-specific ST-T changes, normal, and abnormal (Remaining 200+ CPT codes). Cardiologist annotations ensured precision (Ground truth). Determined classes were “STEMI” and “Not-STEMI”. A 1-D Convolutional Neural Network model was trained and tested for each lead with dataset proportions of 90/10, respectively. The last dense layer outputs a probability for each record being STEMI/Not-STEMI. The analysis also included performance metrics and false-negative reports. Results Overall, the most promising Single lead for STEMI detection was V2 (91.2% Accuracy, 89.6% Sensitivity, and 92.9% Specificity). 55% of false negatives were inferior wall STEMI (Table 1). Conclusion Appreciable progress of our new methodology compared to our previous experiences in AI-guided Single Lead for STEMI detection, especially for lead V2. By performing a thorough analysis of false-negative reports, we aspire to identify potential areas of STEMI detection weakness which will become the focus of future ventures. Funding Acknowledgement Type of funding sources: None.

Single image depth estimation based on sculpture strategy

Supervised deep learning approaches have achieved state-of-the-art performance in single image depth estimation. However, the procedure to train the network is not intervened, due to the black box character of deep learning. To enhance the generalization ability of trained models, we employ a learned prior that is inspired by the process of sculpturing, to guide the model’s learning. From the view of sculpturing, the depth estimation can be divided into two consecutive steps: the initial contour estimation and the detail refinement. The contour of scene can be introduced as the intermediate supervision which enables the network to learn true knowledge and accelerate training. In addition, the edges of the scene contain much semantic information. To better use this structured knowledge, we use an attention mechanism to integrate the edges of the scene to guide training. We also create a more precise ground truth by using self-adaptive Gaussian interpolation. Compared to other datasets, our dataset is denser, and the details of small objects and the ordinal relation in the depths of different objects is preserved. Additionally, the distribution of depth values does not change. The experimental results on the KITTI, Make3D and NYU Depth V2 datasets show that the method achieved better performance with respect to other state-of-the-art depth estimation approaches. Code is available at https://github.com/XTU-PR-LAB/HG-Net.

Systematic analysis of volumetric ultrasound parameters for markerless 4D motion tracking

ObjectivesMotion compensation is an interesting approach to improve treatments of moving structures. For example, target motion can substantially affect dose delivery in radiation therapy, where methods to detect and mitigate the motion are widely used. Recent advances in fast, volumetric ultrasound have rekindled the interest in ultrasound for motion tracking. We present a setup to evaluate ultrasound based motion tracking and we study the effect of imaging rate and motion artifacts on its performance.MethodsWe describe an experimental setup to acquire markerless 4D ultrasound data with precise ground truth from a robot and evaluate different real-world trajectories and system settings toward accurate motion estimation. We analyze motion artifacts in continuously acquired data by comparing to data recorded in a step-and-shoot fashion. Furthermore, we investigate the trade-off between the imaging frequency and resolution.ResultsThe mean tracking errors show that continuously acquired data leads to similar results as data acquired in a step-and-shoot fashion. We report mean tracking errors up to 2.01 mm and 1.36 mm on the continuous data for the lower and higher resolution, respectively, while step-and-shoot data leads to mean tracking errors of 2.52 mm and 0.98 mm.ConclusionsWe perform a quantitative analysis of different system settings for motion tracking with 4D ultrasound. We can show that precise tracking is feasible and additional motion in continuously acquired data does not impair the tracking. Moreover, the analysis of the frequency resolution trade-off shows that a high imaging resolution is beneficial in ultrasound tracking.

TOWARDS ROBUST INDOOR VISUAL SLAM AND DENSE RECONSTRUCTION FOR MOBILE ROBOTS

Abstract. Mobile robots are being increasingly employed in various indoor scenarios. The fundamental prerequisite is that the robot can reconstruct an accurate and complete map of the observed environment and estimate the track of its movements in this map. Current visual SLAM methods can perform this task reasonably well, but mostly in small spaces, such as a single room, and often tested in well-textured environments. In real-world applications of large indoor scenes, they lack robustness and fail to build a globally consistent map. To this end, we propose a novel system that can robustly solve the problem encountered by existing visual SLAM methods, such as weak texture and long-term drift. By combining information from a wheel odometer, the robot poses can be predicted smoothly in the absence of texture. The geometric cues are leveraged by aligning Truncated Signed Distance Function (TSDF) based submaps to minimize the long-term drift. To reconstruct a more complete and accurate dense map, we refine the sensor depth maps by taking advantage of color information and the optimization result of global bundle adjustment. As a result, the system can provide precise trajectory estimation and a globally consistent map for the downstream tasks. We validate the accuracy and robustness of the proposed method on both public and self-collected datasets and show the complementary nature of each module. Evaluation results based on high precision ground-truth show an improvement in the mean Absolute Trajectory Error (ATE) from 21 cm to 2 cm for the trajectory estimation, and the reconstructed map has a mean accuracy of 8 cm.

ColoRadar: The direct 3D millimeter wave radar dataset

This work presents two different forms of dense, high-resolution radar data from two frequency modulated continuous wave radar sensors, along sparse radar pointclouds produced by one of the radar sensors. In addition, all datasets include 3D lidar and inertial measurements, and a lidar-based simultaneous localization and mapping pose estimation. Over 2 h of 6D pose data was generated across 52 datasets collected in highly diverse 3D environments including lab spaces, outside and inside large buildings, urban walkways, and a mine. One dataset, from the ASPEN Lab, also includes precision groundtruth generated from a motion capture system. Intrinsic radar calibration and measured extrinsic sensor position calibrations are also provided along with python based development tools to interact with the various datasets. This data is designed to assist with generating radar based localization algorithms and calibrations between radar and other sensors.

Independent assessment of a deep learning system for lymph node metastasis detection on the Augmented Reality Microscope

Several machine learning algorithms have demonstrated high predictive capability in the identification of cancer within digitized pathology slides. The Augmented Reality Microscope (ARM) has allowed these algorithms to be seamlessly integrated within the pathology workflow by overlaying their inferences onto its microscopic field of view in real time. We present an independent assessment of the LYmph Node Assistant (LYNA) models, state-of-the-art algorithms for the identification of breast cancer metastases in lymph node biopsies, optimized for usage on the ARM. We assessed the models on 40 whole slide images at the commonly used objective magnifications of 10×, 20×, and 40×. We analyzed their performance across clinically relevant subclasses of tissue, including breast cancer, lymphocytes, histiocytes, blood, and fat. Each model obtained overall AUC values of approximately 0.98, accuracy values of approximately 0.94, and sensitivity values above 0.88 at classifying small regions of a field of view as benign or cancerous. Across tissue subclasses, the models performed most accurately on fat and blood, and least accurately on histiocytes, germinal centers, and sinus. The models also struggled with the identification of isolated tumor cells, especially at lower magnifications. After testing, we reviewed the discrepancies between model predictions and ground truth to understand the causes of error. We introduce a distinction between proper and improper ground truth for analysis in cases of uncertain annotations. Taken together, these methods comprise a novel approach for exploratory model analysis over complex anatomic pathology data in which precise ground truth is difficult to establish.

Real-Time Music Following in Score Sheet Images via Multi-Resolution Prediction

The task of real-time alignment between a music performance and the corresponding score (sheet music), also known as score following, poses a challenging multi-modal machine learning problem. Training a system that can solve this task robustly with live audio and real sheet music (i.e., scans or score images) requires precise ground truth alignments between audio and note-coordinate positions in the score sheet images. However, these kinds of annotations are difficult and costly to obtain, which is why research in this area mainly utilizes synthetic audio and sheet images to train and evaluate score following systems. In this work, we propose a method that does not solely rely on note alignments but is additionally capable of leveraging data with annotations of lower granularity, such as bar or score system alignments. This allows us to use a large collection of real-world piano performance recordings coarsely aligned to scanned score sheet images and, as a consequence, improve over current state-of-the-art approaches.

Visibility estimation via deep label distribution learning in cloud environment

The visibility estimation of the environment has great research and application value in the fields of production. To estimate the visibility, we can utilize the camera to obtain some images as evidence. However, the camera only solves the image acquisition problem, and the analysis of image visibility requires strong computational power. To realize effective and efficient visibility estimation, we employ the cloud computing technique to realize high-through image analysis. Our method combines cloud computing and image-based visibility estimation into a powerful and efficient monitoring framework. To train an accurate model for visibility estimation, it is important to obtain the precise ground truth for every image. However, the ground-truth visibility is difficult to be labeled due to its high ambiguity. To solve this problem, we associate a label distribution to each image. The label distribution contains all the possible visibilities with their probabilities. To learn from such annotation, we employ a CNN-RNN model for visibility-aware feature extraction and a conditional probability neural network for distribution prediction. The estimation result can be improved by fusing the predicting results of multiple images from different views. Our experiment shows that labeling the image with visibility distribution can boost the learning performance, and our method can obtain the visibility from the image efficiently.

Defect detection in CT scans of cast aluminum parts: A machine vision perspective

One of the many applications of X-ray computed tomography (CT) in industry is the detection of pores, cavities and other flaws in cast metal parts. Because of its improvement on part safety and saving of expenses, CT inspection is moving from a random sample inspection towards a full in-line inspection. With the increasing amount of produced data, however, comes the need for an automated processing. Due to tight time constraints the resulting CT scans are very artifact afflicted, which impedes automated inspection. In recent years, deep learning methods—convolutional neural networks in particular—have been used with great success to tackle even complex segmentation tasks in cluttered scenes. As we show, these methods are also applicable to the domain of industrial CT data: they are able to cope with noise, beam hardening, scatter and other artifacts which we encounter here. However, these methods need a vast amount of precisely labeled training data to work properly. Gathering the necessary data is not only cumbersome due to the need of annotating three-dimensional data but also expensive as it requires the knowledge of domain experts. Therefore, we present a new approach: We train our models on realistically simulated CT data only. Here, a precise per-voxel ground truth can simply be computed. In order to show that the simulated data is sufficient to train a segmentation network, we turn to its prediction performance on real CT data. We compare the prediction performance of traditional algorithms as well as the trained segmentation network on simulated and real validation data and demonstrate that they behave similarly. The ground truth for the real validation data is hand-labeled using high-quality CT scans, while the actual validation set consists of CT scans of lower quality of the exact same parts. For a comprehensive evaluation, we evaluate the probability of detection as well as the intersection over union. The first tells us how likely a flaw of given size can be found with a given confidence, which is of special interest to domain experts. The latter gives us a per-voxel information of how precise the overall segmentation is. Moreover, our synthetic data enables us to examine the influence of different artifact types on the detection rate. Besides these quantitative analyses we show some qualitative results of real-world applications. To the best of our knowledge, we describe the first approach for defect detection in three-dimensional CT data, which is solely trained with simulated data.

Accuracy Evaluation of Selected Mobile Inspection Robot Localization Techniques in a GNSS-Denied Environment.

Locating an inspection robot is an essential task for inspection missions and spatial data acquisition. Giving a spatial reference to measurements, especially those concerning environmental parameters, e.g., gas concentrations may make them more valuable by enabling more insightful analyses. Thus, an accurate estimation of sensor position and orientation is a significant topic in mobile measurement systems used in robotics, remote sensing, or autonomous vehicles. Those systems often work in urban or underground conditions, which are lowering or disabling the possibility of using Global Navigation Satellite Systems (GNSS) for this purpose. Alternative solutions vary significantly in sensor configuration requirements, positioning accuracy, and computational complexity. The selection of the optimal solution is difficult. The focus here is put on the assessment, using the criterion of the positioning accuracy of the mobile robot with no use of GNSS signals. Automated geodetic surveying equipment is utilized for acquiring precise ground truth data of the robot’s movement. The results obtained, with the use of several methods, compared: Wheel odometry, inertial measurement-based dead-reckoning, visual odometry, and trilateration of ultra-wideband signals. The suitability, pros, and cons of each method are discussed in the context of their application in autonomous robotic systems, operating in an underground mine environment.