Indoor Semantic Segmentation using depth information
Lists
Only you see this
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.
BibTeX
@inproceedings{couprie2013indoor,
author = {Camille Couprie and Clément Farabet and Laurent Najman and Yann LeCun},
title = {{Indoor Semantic Segmentation using depth information}},
booktitle = {International Conference on Learning Representations},
year = {2013},
url = {https://openreview.net/forum?id=ttnAE7vaATtaK},
}Loading related content...