Digital twins to alleviate the need for real field data in vision-based vehicle speed detection systems
Accurate vision-based speed estimation is much more cost-effective than traditional methods based on radar or LiDAR. However, it is also challenging due to the limitations of perspective projection on a discrete sensor, as well as the high sensitivity to calibration, lighting and weather conditions....
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Martínez, Antonio Hernández Daza, Iván García López, Carlos Fernández Llorca, David Fernández |
description | Accurate vision-based speed estimation is much more cost-effective than
traditional methods based on radar or LiDAR. However, it is also challenging
due to the limitations of perspective projection on a discrete sensor, as well
as the high sensitivity to calibration, lighting and weather conditions.
Interestingly, deep learning approaches (which dominate the field of computer
vision) are very limited in this context due to the lack of available data.
Indeed, obtaining video sequences of real road traffic with accurate speed
values associated with each vehicle is very complex and costly, and the number
of available datasets is very limited. Recently, some approaches are focusing
on the use of synthetic data. However, it is still unclear how models trained
on synthetic data can be effectively applied to real world conditions. In this
work, we propose the use of digital-twins using CARLA simulator to generate a
large dataset representative of a specific real-world camera. The synthetic
dataset contains a large variability of vehicle types, colours, speeds,
lighting and weather conditions. A 3D CNN model is trained on the digital twin
and tested on the real sequences. Unlike previous approaches that generate
multi-camera sequences, we found that the gap between the the real and the
virtual conditions is a key factor in obtaining low speed estimation errors.
Even with a preliminary approach, the mean absolute error obtained remains
below 3km/h. |
doi_str_mv | 10.48550/arxiv.2407.08380 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2407_08380</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2407_08380</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2407_083803</originalsourceid><addsrcrecordid>eNqFjj0OgkAQRrexMOoBrJwLgKtApPcnHsCejDLAJMtCdier3F4g9lZf8b2XPKW2Bx2neZbpPboPh_iY6lOs8yTXS1VfuGZBA_Jm60E6QGMoMAqBNASWqISqc-BohComU0KJgsAWAnvubPREPzKBGn4ZAt9PRklCLxlf8IMXav1aLSo0nja_Xand7fo436M5qegdt-iGYkor5rTkP_EFZqFFMQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Digital twins to alleviate the need for real field data in vision-based vehicle speed detection systems</title><source>arXiv.org</source><creator>Martínez, Antonio Hernández ; Daza, Iván García ; López, Carlos Fernández ; Llorca, David Fernández</creator><creatorcontrib>Martínez, Antonio Hernández ; Daza, Iván García ; López, Carlos Fernández ; Llorca, David Fernández</creatorcontrib><description>Accurate vision-based speed estimation is much more cost-effective than
traditional methods based on radar or LiDAR. However, it is also challenging
due to the limitations of perspective projection on a discrete sensor, as well
as the high sensitivity to calibration, lighting and weather conditions.
Interestingly, deep learning approaches (which dominate the field of computer
vision) are very limited in this context due to the lack of available data.
Indeed, obtaining video sequences of real road traffic with accurate speed
values associated with each vehicle is very complex and costly, and the number
of available datasets is very limited. Recently, some approaches are focusing
on the use of synthetic data. However, it is still unclear how models trained
on synthetic data can be effectively applied to real world conditions. In this
work, we propose the use of digital-twins using CARLA simulator to generate a
large dataset representative of a specific real-world camera. The synthetic
dataset contains a large variability of vehicle types, colours, speeds,
lighting and weather conditions. A 3D CNN model is trained on the digital twin
and tested on the real sequences. Unlike previous approaches that generate
multi-camera sequences, we found that the gap between the the real and the
virtual conditions is a key factor in obtaining low speed estimation errors.
Even with a preliminary approach, the mean absolute error obtained remains
below 3km/h.</description><identifier>DOI: 10.48550/arxiv.2407.08380</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2024-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2407.08380$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2407.08380$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Martínez, Antonio Hernández</creatorcontrib><creatorcontrib>Daza, Iván García</creatorcontrib><creatorcontrib>López, Carlos Fernández</creatorcontrib><creatorcontrib>Llorca, David Fernández</creatorcontrib><title>Digital twins to alleviate the need for real field data in vision-based vehicle speed detection systems</title><description>Accurate vision-based speed estimation is much more cost-effective than
traditional methods based on radar or LiDAR. However, it is also challenging
due to the limitations of perspective projection on a discrete sensor, as well
as the high sensitivity to calibration, lighting and weather conditions.
Interestingly, deep learning approaches (which dominate the field of computer
vision) are very limited in this context due to the lack of available data.
Indeed, obtaining video sequences of real road traffic with accurate speed
values associated with each vehicle is very complex and costly, and the number
of available datasets is very limited. Recently, some approaches are focusing
on the use of synthetic data. However, it is still unclear how models trained
on synthetic data can be effectively applied to real world conditions. In this
work, we propose the use of digital-twins using CARLA simulator to generate a
large dataset representative of a specific real-world camera. The synthetic
dataset contains a large variability of vehicle types, colours, speeds,
lighting and weather conditions. A 3D CNN model is trained on the digital twin
and tested on the real sequences. Unlike previous approaches that generate
multi-camera sequences, we found that the gap between the the real and the
virtual conditions is a key factor in obtaining low speed estimation errors.
Even with a preliminary approach, the mean absolute error obtained remains
below 3km/h.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjj0OgkAQRrexMOoBrJwLgKtApPcnHsCejDLAJMtCdier3F4g9lZf8b2XPKW2Bx2neZbpPboPh_iY6lOs8yTXS1VfuGZBA_Jm60E6QGMoMAqBNASWqISqc-BohComU0KJgsAWAnvubPREPzKBGn4ZAt9PRklCLxlf8IMXav1aLSo0nja_Xand7fo436M5qegdt-iGYkor5rTkP_EFZqFFMQ</recordid><startdate>20240711</startdate><enddate>20240711</enddate><creator>Martínez, Antonio Hernández</creator><creator>Daza, Iván García</creator><creator>López, Carlos Fernández</creator><creator>Llorca, David Fernández</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240711</creationdate><title>Digital twins to alleviate the need for real field data in vision-based vehicle speed detection systems</title><author>Martínez, Antonio Hernández ; Daza, Iván García ; López, Carlos Fernández ; Llorca, David Fernández</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2407_083803</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Martínez, Antonio Hernández</creatorcontrib><creatorcontrib>Daza, Iván García</creatorcontrib><creatorcontrib>López, Carlos Fernández</creatorcontrib><creatorcontrib>Llorca, David Fernández</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Martínez, Antonio Hernández</au><au>Daza, Iván García</au><au>López, Carlos Fernández</au><au>Llorca, David Fernández</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Digital twins to alleviate the need for real field data in vision-based vehicle speed detection systems</atitle><date>2024-07-11</date><risdate>2024</risdate><abstract>Accurate vision-based speed estimation is much more cost-effective than
traditional methods based on radar or LiDAR. However, it is also challenging
due to the limitations of perspective projection on a discrete sensor, as well
as the high sensitivity to calibration, lighting and weather conditions.
Interestingly, deep learning approaches (which dominate the field of computer
vision) are very limited in this context due to the lack of available data.
Indeed, obtaining video sequences of real road traffic with accurate speed
values associated with each vehicle is very complex and costly, and the number
of available datasets is very limited. Recently, some approaches are focusing
on the use of synthetic data. However, it is still unclear how models trained
on synthetic data can be effectively applied to real world conditions. In this
work, we propose the use of digital-twins using CARLA simulator to generate a
large dataset representative of a specific real-world camera. The synthetic
dataset contains a large variability of vehicle types, colours, speeds,
lighting and weather conditions. A 3D CNN model is trained on the digital twin
and tested on the real sequences. Unlike previous approaches that generate
multi-camera sequences, we found that the gap between the the real and the
virtual conditions is a key factor in obtaining low speed estimation errors.
Even with a preliminary approach, the mean absolute error obtained remains
below 3km/h.</abstract><doi>10.48550/arxiv.2407.08380</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2407.08380 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2407_08380 |
source | arXiv.org |
subjects | Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition |
title | Digital twins to alleviate the need for real field data in vision-based vehicle speed detection systems |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T15%3A32%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Digital%20twins%20to%20alleviate%20the%20need%20for%20real%20field%20data%20in%20vision-based%20vehicle%20speed%20detection%20systems&rft.au=Mart%C3%ADnez,%20Antonio%20Hern%C3%A1ndez&rft.date=2024-07-11&rft_id=info:doi/10.48550/arxiv.2407.08380&rft_dat=%3Carxiv_GOX%3E2407_08380%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |