Unsupervised Learning for Subterranean Junction Recognition Based on 2D Point Cloud
| Autor: | Farhad Pourkamali-Anaraki, Sina Sharif Mansouri, George Nikolakopoulos, Miguel Castano, Joel W. Burdick, Ali-akbar Agha-mohammadi |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
0301 basic medicine Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Point cloud computer.software_genre Spectral clustering Matrix decomposition Computer Science - Robotics 03 medical and health sciences 030104 developmental biology 0302 clinical medicine Data point Unsupervised learning Embedding Robot Pairwise comparison Data mining Robotics (cs.RO) computer 030217 neurology & neurosurgery |
| Zdroj: | MED |
| DOI: | 10.1109/med48518.2020.9183337 |
| Popis: | This article proposes a novel unsupervised learning framework for detecting the number of tunnel junctions in subterranean environments based on acquired 2D point clouds. The implementation of the framework provides valuable information for high level mission planners to navigate an aerial platform in unknown areas or robot homing missions. The framework utilizes spectral clustering, which is capable of uncovering hidden structures from connected data points lying on non-linear manifolds. The spectral clustering algorithm computes a spectral embedding of the original 2D point cloud by utilizing the eigen decomposition of a matrix that is derived from the pairwise similarities of these points. We validate the developed framework using multiple data-sets, collected from multiple realistic simulations, as well as from real flights in underground environments, demonstrating the performance and merits of the proposed methodology. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|