Cargando…

Deep Learning Method on Target Echo Signal Recognition for Obscurant Penetrating Lidar Detection in Degraded Visual Environments

With the rapid development of autonomous vehicles and mobile robotics, the desire to advance robust light detection and ranging (Lidar) detection methods for real world applications is increasing. However, this task still suffers in degraded visual environments (DVE), including smoke, dust, fog, and...

Descripción completa

Detalles Bibliográficos
Autores principales: Liang, Xujia, Huang, Zhonghua, Lu, Liping, Tao, Zhigang, Yang, Bing, Li, Yinlin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7349105/
https://www.ncbi.nlm.nih.gov/pubmed/32560504
http://dx.doi.org/10.3390/s20123424
_version_ 1783556985912819712
author Liang, Xujia
Huang, Zhonghua
Lu, Liping
Tao, Zhigang
Yang, Bing
Li, Yinlin
author_facet Liang, Xujia
Huang, Zhonghua
Lu, Liping
Tao, Zhigang
Yang, Bing
Li, Yinlin
author_sort Liang, Xujia
collection PubMed
description With the rapid development of autonomous vehicles and mobile robotics, the desire to advance robust light detection and ranging (Lidar) detection methods for real world applications is increasing. However, this task still suffers in degraded visual environments (DVE), including smoke, dust, fog, and rain, as the aerosols lead to false alarm and dysfunction. Therefore, a novel Lidar target echo signal recognition method, based on a multi-distance measurement and deep learning algorithm is presented in this paper; neither the backscatter suppression nor the denoise functions are required. The 2-D spectrogram images are constructed by using the frequency-distance relation derived from the 1-D echo signals of the Lidar sensor individual cell in the course of approaching target. The characteristics of the target echo signal and noise in the spectrogram images are analyzed and determined; thus, the target recognition criterion is established accordingly. A customized deep learning algorithm is subsequently developed to perform the recognition. The simulation and experimental results demonstrate that the proposed method can significantly improve the Lidar detection performance in DVE.
format Online
Article
Text
id pubmed-7349105
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-73491052020-07-22 Deep Learning Method on Target Echo Signal Recognition for Obscurant Penetrating Lidar Detection in Degraded Visual Environments Liang, Xujia Huang, Zhonghua Lu, Liping Tao, Zhigang Yang, Bing Li, Yinlin Sensors (Basel) Article With the rapid development of autonomous vehicles and mobile robotics, the desire to advance robust light detection and ranging (Lidar) detection methods for real world applications is increasing. However, this task still suffers in degraded visual environments (DVE), including smoke, dust, fog, and rain, as the aerosols lead to false alarm and dysfunction. Therefore, a novel Lidar target echo signal recognition method, based on a multi-distance measurement and deep learning algorithm is presented in this paper; neither the backscatter suppression nor the denoise functions are required. The 2-D spectrogram images are constructed by using the frequency-distance relation derived from the 1-D echo signals of the Lidar sensor individual cell in the course of approaching target. The characteristics of the target echo signal and noise in the spectrogram images are analyzed and determined; thus, the target recognition criterion is established accordingly. A customized deep learning algorithm is subsequently developed to perform the recognition. The simulation and experimental results demonstrate that the proposed method can significantly improve the Lidar detection performance in DVE. MDPI 2020-06-17 /pmc/articles/PMC7349105/ /pubmed/32560504 http://dx.doi.org/10.3390/s20123424 Text en © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Liang, Xujia
Huang, Zhonghua
Lu, Liping
Tao, Zhigang
Yang, Bing
Li, Yinlin
Deep Learning Method on Target Echo Signal Recognition for Obscurant Penetrating Lidar Detection in Degraded Visual Environments
title Deep Learning Method on Target Echo Signal Recognition for Obscurant Penetrating Lidar Detection in Degraded Visual Environments
title_full Deep Learning Method on Target Echo Signal Recognition for Obscurant Penetrating Lidar Detection in Degraded Visual Environments
title_fullStr Deep Learning Method on Target Echo Signal Recognition for Obscurant Penetrating Lidar Detection in Degraded Visual Environments
title_full_unstemmed Deep Learning Method on Target Echo Signal Recognition for Obscurant Penetrating Lidar Detection in Degraded Visual Environments
title_short Deep Learning Method on Target Echo Signal Recognition for Obscurant Penetrating Lidar Detection in Degraded Visual Environments
title_sort deep learning method on target echo signal recognition for obscurant penetrating lidar detection in degraded visual environments
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7349105/
https://www.ncbi.nlm.nih.gov/pubmed/32560504
http://dx.doi.org/10.3390/s20123424
work_keys_str_mv AT liangxujia deeplearningmethodontargetechosignalrecognitionforobscurantpenetratinglidardetectionindegradedvisualenvironments
AT huangzhonghua deeplearningmethodontargetechosignalrecognitionforobscurantpenetratinglidardetectionindegradedvisualenvironments
AT luliping deeplearningmethodontargetechosignalrecognitionforobscurantpenetratinglidardetectionindegradedvisualenvironments
AT taozhigang deeplearningmethodontargetechosignalrecognitionforobscurantpenetratinglidardetectionindegradedvisualenvironments
AT yangbing deeplearningmethodontargetechosignalrecognitionforobscurantpenetratinglidardetectionindegradedvisualenvironments
AT liyinlin deeplearningmethodontargetechosignalrecognitionforobscurantpenetratinglidardetectionindegradedvisualenvironments