TY - GEN
T1 - LAPTNet-FPN
T2 - 2023 IEEE International Conference on Robotics and Automation, ICRA 2023
AU - Diaz-Zapata, Manuel
AU - Sierra-Gonzalez, David
AU - Erkent, Ozgur
AU - Laugier, Christian
AU - Dibangoye, Jilles
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85168676166
U2 - 10.1109/ICRA48891.2023.10160757
DO - 10.1109/ICRA48891.2023.10160757
M3 - Conference contribution
AN - SCOPUS:85168676166
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 712
EP - 718
BT - Proceedings - ICRA 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 29 May 2023 through 2 June 2023
ER -