LAPTNet-FPN: Multi-scale LiDAR-aided Projective Transform Network for Real Time Semantic Grid Prediction - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

LAPTNet-FPN: Multi-scale LiDAR-aided Projective Transform Network for Real Time Semantic Grid Prediction

Abstract

Semantic grids can be useful representations of the scene around an autonomous system. By having information about the layout of the space around itself, a robot can leverage this type of representation for crucial tasks such as navigation or tracking. By fusing information from multiple sensors, robustness can be increased and the computational load for the task can be lowered, achieving real time performance. Our multi-scale LiDAR-Aided Perspective Transform network uses information available in point clouds to guide the projection of image features to a top-view representation, resulting in a relative improvement in the state of the art for semantic grid generation for human (+8.67%) and movable object (+49.07%) classes in the nuScenes dataset, as well as achieving results close to the state of the art for the vehicle, drivable area and walkway classes, while performing inference at 25 FPS.
Fichier principal
Vignette du fichier
manuel_ICRA_2023_HAL.pdf (2.57 Mo) Télécharger le fichier
manuel_ICRA_2023_HAL_v1.1.zip (2.45 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03980399 , version 1 (09-02-2023)
hal-03980399 , version 2 (09-03-2023)

Licence

Copyright

Identifiers

Cite

Manuel Alejandro Diaz-Zapata, David Sierra González, Özgür Erkent, Jilles Dibangoye, Christian Laugier. LAPTNet-FPN: Multi-scale LiDAR-aided Projective Transform Network for Real Time Semantic Grid Prediction. ICRA 2023 - IEEE International Conference on Robotics and Automation, IEEE Robotics and Automation Society, May 2023, Londres, United Kingdom. pp.1-6. ⟨hal-03980399v2⟩
56 View
100 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More