Indoor Semantic Segmentation using depth information

Camille Couprie 1 Clément Farabet 2, 3 Laurent Najman 3 Yann Lecun 2
1 Direction Technologie, Informatique et Mathématiques appliquées
2 CIMS - Courant Institute of Mathematical Sciences [New York]
3 LIGM - Laboratoire d'Informatique Gaspard-Monge
Abstract : This work addresses multi-class segmentation of indoor scenes with RGB-D inputs. While this area of research has gained much attention recently, most works still rely on hand-crafted features. In contrast, we apply a multiscale convolutional network to learn features directly from the images and the depth information. We obtain state-of-the-art on the NYU-v2 depth dataset with an accuracy of 64.5%. We illustrate the labeling of indoor scenes in videos sequences that could be processed in real-time using appropriate hardware such as an FPGA.
Document type :
Conference papers
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-00805105
Contributor : Laurent Najman <>
Submitted on : Wednesday, March 27, 2013 - 9:33:18 AM
Last modification on : Tuesday, January 22, 2019 - 3:51:42 PM

Links full text

arxiv

Identifiers

  • HAL Id : hal-00805105, version 1
  • ARXIV : 1301.3572

Collections

IFP | LIGM_A3SI | LIGM | ENPC | PARISTECH | UNIV-MLV | UPEC-UPEM | ESIEE-PARIS

Citation

Camille Couprie, Clément Farabet, Laurent Najman, Yann Lecun. Indoor Semantic Segmentation using depth information. First International Conference on Learning Representations (ICLR 2013), May 2013, Scottsdale, AZ, United States. pp.1-8. ⟨hal-00805105⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

905

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD