Indoor Semantic Segmentation using depth information
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Causal graph-based video segmentation2013
- Learning Hierarchical Features for Scene LabelingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998