Loading...
Loading...

Go to the content (press return)

Depth estimation and semantic segmentation from a single RGB image using a hybrid convolutional neural network

Author
Lin, X.; Sánchez, D.; Casas, J.; Pardas, M.
Type of activity
Journal article
Journal
Sensors
Date of publication
2019-04-15
Volume
19
Number
1795
First page
1
Last page
20
DOI
10.3390/s19081795
Project funding
Multimodal Signal Processing and Machine Learning on Graphs
Repository
http://hdl.handle.net/2117/132168 Open in new window
URL
https://www.mdpi.com/1424-8220/19/8/1795 Open in new window
Abstract
Semantic segmentation and depth estimation are two important tasks in computer vision, and many methods have been developed to tackle them. Commonly these two tasks are addressed independently, but recently the idea of merging these two problems into a sole framework has been studied under the assumption that integrating two highly correlated tasks may benefit each other to improve the estimation accuracy. In this paper, depth estimation and semantic segmentation are jointly addressed using a si...
Keywords
convolutional neural networks, depth estimation, hybrid architecture, semantic segmentation
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants