MobileXNet: An Efficient Convolutional Neural Network for Monocular Depth Estimation

Depth estimation from a single RGB image has attracted great interest in autonomous driving and robotics. State-of-the-art methods are usually designed on top of complex and extremely deep network architectures, which require more computational resources. Moreover, the inherent characteristic of the...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on intelligent transportation systems 2022-11, Vol.23 (11), p.20134-20147
Main Authors: Dong, Xingshuai, Garratt, Matthew A., Anavatti, Sreenatha G., Abbass, Hussein A.
Format: Article
Language:English
Subjects:
Artificial neural networks
autonomous vehicles
Coders
Computer architecture
Convolution
Convolutional neural networks
Decoding
depth prediction
encoder-decoder
Encoders-Decoders
Estimation
Feature maps
Monocular depth estimation
Robotics
Semantics
Spatial data
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Depth estimation from a single RGB image has attracted great interest in autonomous driving and robotics. State-of-the-art methods are usually designed on top of complex and extremely deep network architectures, which require more computational resources. Moreover, the inherent characteristic of the backbone used by the existing approaches results in severe spatial information loss in the produced feature maps, which impairs the accuracy of depth estimation on small sized images. In this study, we aimed to design a novel and efficient Convolutional Neural Network (CNN) to address these problems. Specifically, we stacked two shallow encoder-decoder style subnetworks successively in a unified network. Extensive experiments have been conducted on the NYU depth v2, KITTI, Make3D and Unreal data sets. Experimental results show that the proposed network achieves comparable accuracy to state-of-the-art methods that have extremely deep architectures but runs at a much faster speed on a single, less powerful GPU.
ISSN:1524-9050
1558-0016
DOI:10.1109/TITS.2022.3179365