LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks
Artikel i vetenskaplig tidskrift, 2019
To further highlight the benefits of using a multimodal system for road detection, a data set consisting of visually challenging scenes was extracted from driving sequences of the KITTI raw data set. It was then demonstrated that, as expected, a purely camera-based FCN severely underperforms on this data set. A multimodal system, on the other hand, is still able to provide high accuracy. Finally, the proposed cross fusion FCN was evaluated on the KITTI road benchmark where it achieved excellent performance, with a MaxF score of 96.03%, ranking it among the top-performing approaches.
fully convolutional neural network
autonomous driving
Författare
Luca Caltagirone
Chalmers, Mekanik och maritima vetenskaper, Fordonsteknik och autonoma system
Mauro Bellone
Chalmers, Mekanik och maritima vetenskaper, Fordonsteknik och autonoma system
Lennart Svensson
Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik
Mattias Wahde
Chalmers, Mekanik och maritima vetenskaper, Fordonsteknik och autonoma system
Robotics and Autonomous Systems
0921-8890 (ISSN)
Vol. 111 125-131Ämneskategorier
Annan data- och informationsvetenskap
Mediateknik
Datorseende och robotik (autonoma system)
Styrkeområden
Transport
DOI
10.1016/j.robot.2018.11.002
Relaterade dataset
Lidar-Camera Fusion For Road Detection Using Fully Convolutional Neural Network [dataset]
DOI: 10.5281/zenodo.1411432