MYMiguel Yermo

Miguel Yermo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Miguel Yermo has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    ALICE-LRI: A general method for lossless range image generation for spinning LiDAR sensors without calibration metadata

    by Samuel Soutullo, Miguel Yermo, David L. Vilariño, Óscar G. Lorenzo, José C. Cabaleiro, Francisco F. Rivera

  • Open Access

    Efficient Neighbourhood Search in 3D Point Clouds Through Space-Filling Curves and Linear Octrees

    by Pablo D. Viñambres, Miguel Yermo, Silvia R. Alcaraz, Óscar Lorenzo, Francisco Rivera, José Cabaleiro

    This work presents an efficient approach for neighbourhood searching in 3D point clouds by combining spatial reordering leveraging Space-Filling Curves (SFCs), specifically Morton and Hilbert curves, with a linear Octree implementation. We also propose specialised search algorithms for fixed-radius and kNN queries, based on our linear Octree structures. Additionally, we introduce the novel concept of kNN locality histogram, which can be easily computed to characterise locality in data accesses, and we found to be directly related to cache misses and search performance.Our experiments reveal that SFC reordering significantly improves access to spatial data, reducing the number of cache misses from 25% to 75% and runtime by up to 50%. Moreover, we compare our proposal with several widely used Octree and KDTree implementations. Our method achieves a significant reduction in search time, up to 10x faster than existing solutions. Furthermore, we analysed the performance of our neighbourhood searches (parallelised using OpenMP), demonstrating high scalability with the number of cores and the problem size. Notably, we observed a speedup of up to 36x when executing fixed-radius searches in a system with 40 cores. The results obtained indicate that our methods provide a robust and efficient solution for applications that require fast access to large-scale 3D point neighbour sets.

  • Open Access

    ALICE-LRI: A General Method for Lossless Range Image Generation for Spinning LiDAR Sensors without Calibration Metadata

    by Samuel Soutullo, Miguel Yermo, David Vilariño, Óscar Lorenzo, José Cabaleiro, Francisco Rivera

    3D LiDAR sensors are essential for autonomous navigation, environmental monitoring, and precision mapping in remote sensing applications. To efficiently process the massive point clouds generated by these sensors, LiDAR data is often projected into 2D range images that organize points by their angular positions and distances. While these range image representations enable efficient processing, conventional projection methods suffer from fundamental geometric inconsistencies that cause irreversible information loss, compromising high-fidelity applications. We present ALICE-LRI (Automatic LiDAR Intrinsic Calibration Estimation for Lossless Range Images), the first general, sensor-agnostic method that achieves lossless range image generation from spinning LiDAR point clouds without requiring manufacturer metadata or calibration files. Our algorithm automatically reverse-engineers the intrinsic geometry of any spinning LiDAR sensor by inferring critical parameters including laser beam configuration, angular distributions, and per-beam calibration corrections, enabling lossless projection and complete point cloud reconstruction with zero point loss. Comprehensive evaluation across the complete KITTI and DurLAR datasets demonstrates that ALICE-LRI achieves perfect point preservation, with zero points lost across all point clouds. Geometric accuracy is maintained well within sensor precision limits, establishing geometric losslessness with real-time performance. We also present a compression case study that validates substantial downstream benefits, demonstrating significant quality improvements in practical applications. This paradigm shift from approximate to lossless LiDAR projections opens new possibilities for high-precision remote sensing applications requiring complete geometric preservation.

  • Open Access

    Deep Learning for Ultra-Large-Scale Semantic Segmentation of Geographic 3D Point Clouds With Missing Labels

    by Alberto M. Esmorís, Miguel Yermo, Silvia R. Alcaraz, Samuel Soutullo, Francisco F. Rivera

    Semantic segmentation of 3D point clouds is a critical task essential for research and industry in a wide variety of domains. Mostworks until nowuse datasets where the concept of large-scale varies between 1.17 and 9, 261 million points and 0.31 and 250 square kilometers. In this research, we push the limits of 3D deep learning by considering approximately 36, 369 million points and 29, 557 square kilometers in our case study. To the best of our knowledge, it is the largest geographic region ever classified with neural networks for 3D point clouds in scientific works. The main contributions of our research are: 1) The first published results on semantic segmentation of ultra-large-scale and low-resolution airborne laser scanning point clouds, 2) adapted neural networks to work under missing labels and high measurement error conditions, 3) the introduction of class ambiguity as a more robust uncertainty measurement compared to entropy, and 4) an open-source deep learning framework for 3D point clouds that enables the reproducibility of our experiments and further studies.


  • Open Access

    Cheesemap: A High-Performance Point-Indexing Data Structure for Neighbor Search in LiDAR Data

    by Ruben Laso, Miguel Yermo

    Point cloud data, as the representation of three-dimensional spatial information, is a fundamental piece of information in various domains where indexing and querying these point clouds efficiently is crucial for tasks such as object recognition, autonomous navigation, and environmental modeling. In this paper, we present a comprehensive comparative analysis of various data structures combined with neighboring search methods across different types of point clouds. Additionally, we introduce a novel data structure, cheesemap, to handle 3D LiDAR point clouds. Exploring the sparsity and irregularity in the distribution of points, there are three flavors of the cheesemap: dense, sparse, and mixed. Results show that the cheesemap can outperform state-of-the-art data structures in terms of execution time per query, particularly for ALS (Aerial Laser Scanning) point clouds. Memory consumption is also minimal, especially in the sparse and mixed representations, making the cheesemap a suitable choice for applications involving three-dimensional point clouds.

  • Open Access

    Powerline Detection and Characterization in General-Purpose Airborne LiDAR Surveys

    by Miguel Yermo, Ruben Laso, Oscar G. Lorenzo, Tomás F. Pena, José C. Cabaleiro, Francisco F. Rivera, David L. Vilariño

    Powerline inspection and modelization using airborne light detection and ranging (LiDAR) data have been widely studied through the years. However, to the best of our knowledge, the proposed methods rely on intentional flights carried out along the high-voltage powerline. Thus, the state-of-the-art studies focus on detecting and characterizing a single powerline whose presence and location are known beforehand. We propose a method to detect and model powerlines of any voltage from airborne LiDAR point clouds not necessarily acquired for this purpose. Also, the method is suitable to be applied to those point clouds whose density is usually lower than that obtained using specific purpose flights over the powerlines. Our solution starts filtering out most of the points that do not belong to electric conductors. Then, the Hough transform is used to detect straight lines. Its output is then used to cluster the electric conductors. Also, we propose a solution to bypass a common issue regarding the nonmaxima suppression often used in object detection algorithms. Furthermore, a robust method for clustering conductors sharing the same vertical plane is presented, being able to return good results even in the absence of parts of any electrical conductor. The algorithm is tested in several datasets containing high-voltage powerlines and others, comprising mid- and low-voltage electric conductors. Finally, a study of the computational performance shows that the algorithm can efficiently take advantage of manycore systems, which is essential to determine the feasibility of our approach on massive LiDAR point clouds.


  • Open Access

    Virtual LiDAR Simulation as a High Performance Computing Challenge: Toward HPC HELIOS++

    by Alberto M. Esmoris, Miguel Yermo, Hannah Weiser, Lukas Winiwarter, Bernhard Hofle, Francisco F. Rivera

    The software HELIOS++ simulates the laser scanning of a given virtual scene that can be composed of different spatial primitives and 3D meshes with distinct granularity. The high computational cost of this type of simulation software demands efficient computational solutions. Classical solutions based on GPU are not well suited when irregular geometries compose the scene combining different primitives and physics models because they lead to different computation branches. In this paper, we explore the usage of parallelization strategies based on static and dynamic workload balancing and heuristic optimization strategies to speed up the ray tracing process based on a k-dimensional tree (KDT). Using HELIOS++ as our case study, we analyze the performance of our algorithms on different parallel computers, including the CESGA FinisTerrae-II supercomputer. There is a significant performance boost in all cases, with the decrease in computation time ranging from 89.5% to 99.4%. Our results show that the proposed algorithms can boost the performance of any software that relies heavily on a KDT or a similar data structure, as well as those that spend most of the time computing with only a few synchronization barriers. Hence, the algorithms presented in this paper improve performance, whether computed on personal computers or supercomputers.


  • Open Access

    AUTOMATIC DETECTION AND CHARACTERISATION OF POWER LINES AND THEIR SURROUNDINGS USING LIDAR DATA

    by M. Yermo, J. Martínez, O. G. Lorenzo, D. L. Vilariño, J. C. Cabaleiro, T. F. Pena, F. F. Rivera

    Light Detection and Ranging (LiDAR) is nowadays one of the most used tools to obtain geospatial data. In this paper, a method to detect and characterise power lines of both high and low voltage and their surroundings from 3D LiDAR point clouds exclusively is proposed. First, to identify points of the power lines a global search of candidate points is carried out based on the height of each point compared to its neighbours. Then, the Hough Transform (HT) is applied on the set of candidate points to extract the catenaries that belong to each power line, allowing the identification of each conductor individually. Finally, conductors located on the same power line are grouped, their geometric characteristics analysed, and the quantitative features of the surroundings are computed. A very high accuracy of power line classification is reached with these methods, while the computational time is optimised by efficient memory usage and parallel implementation of the code.