Segmentation of Vehicles and Roads by a Low-Channel Lidar

An effective method to segment vehicles and roads is proposed for autonomous vehicles using low-channel 3D lidar. The distance-view transformation is newly proposed to overcome the low density of top-view data of lidar. In addition, a dilated convolution structure is proposed to expand the receptive...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on intelligent transportation systems 2019-11, Vol.20 (11), p.4251-4256
Hauptverfasser:	Lee, Jae-Seol, Jo, Jun-Hyeong, Park, Tae-Hyoung
Format:	Artikel
Sprache:	eng
Schlagworte:	3D lidar Artificial neural networks Autonomous vehicle Autonomous vehicles Convolution convolution neural network Image segmentation Laser radar Lidar receptive field Roads Segmentation spherical coordinate Three-dimensional displays Two dimensional displays Vehicles
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!