Next Article in Journal
A Computer Vision-Based Roadside Occupation Surveillance System for Intelligent Transport in Smart Cities
Next Article in Special Issue
Spatio–Temporal Image Representation of 3D Skeletal Movements for View-Invariant Action Recognition with Deep Convolutional Neural Networks
Previous Article in Journal
Nanopipette/Nanorod-Combined Quartz Tuning Fork–Atomic Force Microscope
Previous Article in Special Issue
VisNet: Deep Convolutional Neural Networks for Forecasting Atmospheric Visibility
Open AccessArticle

Depth Estimation and Semantic Segmentation from a Single RGB Image Using a Hybrid Convolutional Neural Network

1
Visual Interactions and Communication Technologies (Vicomtech), 20009 Donostia/San Sebastián, Spain
2
Image Processing Group, TSC Department, Technical University of Catalonia (UPC), 08034 Barcelona, Spain
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(8), 1795; https://doi.org/10.3390/s19081795
Received: 6 March 2019 / Revised: 9 April 2019 / Accepted: 12 April 2019 / Published: 15 April 2019
(This article belongs to the Special Issue Deep Learning-Based Image Sensors)
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 single RGB input image under a unified convolutional neural network. We analyze two different architectures to evaluate which features are more relevant when shared by the two tasks and which features should be kept separated to achieve a mutual improvement. Likewise, our approaches are evaluated under two different scenarios designed to review our results versus single-task and multi-task methods. Qualitative and quantitative experiments demonstrate that the performance of our methodology outperforms the state of the art on single-task approaches, while obtaining competitive results compared with other multi-task methods. View Full-Text
Keywords: depth estimation; semantic segmentation; convolutional neural networks; hybrid architecture depth estimation; semantic segmentation; convolutional neural networks; hybrid architecture
Show Figures

Figure 1

MDPI and ACS Style

Lin, X.; Sánchez-Escobedo, D.; Casas, J.R.; Pardàs, M. Depth Estimation and Semantic Segmentation from a Single RGB Image Using a Hybrid Convolutional Neural Network. Sensors 2019, 19, 1795.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop