Building a Real-Time 2D Lidar Using Deep Learning

Applying deep learning methods, this paper addresses depth prediction problem resulting from single monocular images. A vector of distances is predicted instead of a whole image matrix. A vector-only prediction decreases training overhead and prediction periods and requires less resources (memory, C...

Full description

Saved in:
Bibliographic Details
Main Authors: Nadim Arubai, Omar Hamdoun, Assef Jafar
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Journal of Robotics
Online Access:http://dx.doi.org/10.1155/2021/6652828
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849696306976522240
author Nadim Arubai
Omar Hamdoun
Assef Jafar
author_facet Nadim Arubai
Omar Hamdoun
Assef Jafar
author_sort Nadim Arubai
collection DOAJ
description Applying deep learning methods, this paper addresses depth prediction problem resulting from single monocular images. A vector of distances is predicted instead of a whole image matrix. A vector-only prediction decreases training overhead and prediction periods and requires less resources (memory, CPU). We propose a module which is more time efficient than the state-of-the-art modules ResNet, VGG, FCRN, and DORN. We enhanced the network results by training it on depth vectors from other levels (we get a new level by changing the Lidar tilt angle). The predicted results give a vector of distances around the robot, which is sufficient for the obstacle avoidance problem and many other applications.
format Article
id doaj-art-c81fc56183524c0a9f016f48a52dbd24
institution DOAJ
issn 1687-9600
1687-9619
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Journal of Robotics
spelling doaj-art-c81fc56183524c0a9f016f48a52dbd242025-08-20T03:19:29ZengWileyJournal of Robotics1687-96001687-96192021-01-01202110.1155/2021/66528286652828Building a Real-Time 2D Lidar Using Deep LearningNadim Arubai0Omar Hamdoun1Assef Jafar2Higher Institute for Applied Sciences and Technology, Damascus, SyriaHigher Institute for Applied Sciences and Technology, Damascus, SyriaHigher Institute for Applied Sciences and Technology, Damascus, SyriaApplying deep learning methods, this paper addresses depth prediction problem resulting from single monocular images. A vector of distances is predicted instead of a whole image matrix. A vector-only prediction decreases training overhead and prediction periods and requires less resources (memory, CPU). We propose a module which is more time efficient than the state-of-the-art modules ResNet, VGG, FCRN, and DORN. We enhanced the network results by training it on depth vectors from other levels (we get a new level by changing the Lidar tilt angle). The predicted results give a vector of distances around the robot, which is sufficient for the obstacle avoidance problem and many other applications.http://dx.doi.org/10.1155/2021/6652828
spellingShingle Nadim Arubai
Omar Hamdoun
Assef Jafar
Building a Real-Time 2D Lidar Using Deep Learning
Journal of Robotics
title Building a Real-Time 2D Lidar Using Deep Learning
title_full Building a Real-Time 2D Lidar Using Deep Learning
title_fullStr Building a Real-Time 2D Lidar Using Deep Learning
title_full_unstemmed Building a Real-Time 2D Lidar Using Deep Learning
title_short Building a Real-Time 2D Lidar Using Deep Learning
title_sort building a real time 2d lidar using deep learning
url http://dx.doi.org/10.1155/2021/6652828
work_keys_str_mv AT nadimarubai buildingarealtime2dlidarusingdeeplearning
AT omarhamdoun buildingarealtime2dlidarusingdeeplearning
AT assefjafar buildingarealtime2dlidarusingdeeplearning