3D-MiniNet: Learning a 2D Representation From Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation

• Published in: IEEE robotics and automation letters Vol. 5; no. 4; pp. 5432 - 5439
• Main Authors: Alonso, Inigo, Riazuelo, Luis, Montesano, Luis, Murillo, Ana C.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.10.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Ablation; Artificial neural networks; Computer architecture; deep learning for visual perception; Feature extraction; Laser radar; Learning; Lidar; LiDAR point clouds; Modules; Post-production processing; Representations; Robotics; Semantic scene understanding; Semantic segmentation; Semantics; Task analysis; Three dimensional models; Three-dimensional displays; Two dimensional displays

LIDAR semantic segmentation is an essential task that provides 3D semantic information about the environment to robots. Fast and efficient semantic segmentation methods are needed to match the strong computational and temporal restrictions of many real-world robotic applications. This work presents...