Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Enhancing UAV Classification with Synthetic Data: GMM LiDAR Simulator for Aerial Surveillance Applications

  • Aldao Pensado, Enrique
  • Veiga López, Fernando
  • González De Santos, Luis Miguel
  • González Jorge, Higinio
The proliferation of Unmanned Aerial Vehicles (UAVs) has raised safety concerns due to the potential threats resulting from their misuse or malicious intent. Due to their compact size, high-resolution surveillance systems such as LiDAR sensors are necessary to exert effective control over the airspace. Given the large volume of data that these technologies generate, efficient Deep Learning (DL) algorithms are needed to make their real-time implementation feasible. However, the training of DL models requires extense and diverse datasets, which in certain scenarios may not be available. Therefore, this work introduces a novel method based on Gaussian Mixture Models (GMMs) for simulating realistic synthetic point clouds of UAVs. This simulator is calibrated using experimental data and allows to probabilistically replicate the intricacies of sensor ray propagation, thereby addressing the limitations of current Ray Tracing (RT) simulators such as Gazebo or CARLA. In this study, we perform a quantitative analysis of the point cloud quality of the GMM simulator, comparing it with the results obtained using a RT approach. Additionally, we evaluate the effectiveness of both methods in training object classifiers. Results demonstrate the GMM simulator’s potential for creating realistic synthetic databases, Agencia Estatal de Investigación | Ref. PID2021-125060OB-100, Agencia Estatal de Investigación | Ref. TED2021-129757B-C3, Ministerio de Universidades | Ref.FPU21/01176
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Deep learning based target pose estimation using LiDAR measurements in active debris removal operations

  • Aldao Pensado, Enrique
  • González De Santos, Luis Miguel
  • Sanjurjo Rivo, Manuel
  • González Jorge, Higinio
In this work, a study on the use of a commercial global-flash LiDAR sensor in Active Debris Removal operations is presented. This type of activity requires precise knowledge of the position and orientation of the target to be removed. For these missions, relative navigation devices such as cameras or LiDAR sensors are typically regarded. In this study, the mission profile defined in the e.Deorbit System Requirements Review was considered and data acquisition and processing from a commercial ASC GSFL-16KS LiDAR sensor were simulated. As the main novelty of this work, the use of Multi-Layer Perceptron neural networks for the processing of LiDAR depth images is proposed in order to obtain an estimate of the pose of the target. Using the results of the neural networks, an Iterative Closest Point (ICP) algorithm is applied to refine the calculation of the pose. The accuracy and computation time of the system were evaluated, obtaining robust and computationally efficient results in the proposed study cases., Ministerio de Universidades | Ref. FPU21/01176, Universidade de Vigo