End-to-End Learning of Semantic Grid Estimation Deep Neural Network with Occupancy Grids - Université de Lyon Access content directly
Journal Articles Unmanned systems Year : 2019

End-to-End Learning of Semantic Grid Estimation Deep Neural Network with Occupancy Grids

Abstract

We propose semantic grid, a spatial 2D map of the environment around an autonomous vehicle consisting of cells which represent the semantic information of the corresponding region such as car, road, vegetation, bikes, etc. It consists of an integration of an occupancy grid, which computes the grid states with a Bayesian filter approach, and semantic segmentation information from monocular RGB images, which is obtained with a deep neural network. The network fuses the information and can be trained in an end-to-end manner. The output of the neural network is refined with a conditional random field. The proposed method is tested in various datasets (KITTI dataset, Inria-Chroma dataset and SYNTHIA) and different deep neural network architectures are compared.
Fichier principal
Vignette du fichier
unmanned_systems_2019.pdf (6.63 Mo) Télécharger le fichier
Origin : Explicit agreement for this submission
Loading...

Dates and versions

hal-02302533 , version 1 (09-10-2019)

Identifiers

Cite

Özgür Erkent, Christian Wolf, Christian Laugier. End-to-End Learning of Semantic Grid Estimation Deep Neural Network with Occupancy Grids. Unmanned systems, 2019, 7 (3), pp.171-181. ⟨10.1142/S2301385019410036⟩. ⟨hal-02302533⟩
307 View
309 Download

Altmetric

Share

Gmail Facebook X LinkedIn More