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

Özgür Erkent 1 Christian Wolf 2, 1 Christian Laugier 3, 1, 4
1 CHROMA - Robots coopératifs et adaptés à la présence humaine en environnements dynamiques
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
2 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
3 SHARP - Automatic Programming and Decisional Systems in Robotics
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes
4 E-MOTION - Geometry and Probability for Motion and Action
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes
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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [36 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02302533
Contributor : Christian Wolf <>
Submitted on : Wednesday, October 9, 2019 - 10:47:21 AM
Last modification on : Wednesday, October 9, 2019 - 2:24:07 PM

File

unmanned_systems_2019.pdf
Explicit agreement for this submission

Identifiers

Citation

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

Share

Metrics

Record views

21

Files downloads

6