Traffic Accident Risk Forecasting using Contextual Vision Transformers with Static Map Generation and Coarse-Fine-Coarse Transformers

We propose an enhancement to our previously proposed novel model called Contextual Vision Transformer (ViT) to address the problem of traffic accident risk forecasting. This framework combines spatial and temporal information using a data-driven approach. By treating the problem as a computer vision...

Full description

Saved in:
Bibliographic Details
Main Authors: Grigorev, Artur, Saleh, Khaled, Mihaita, Adriana-Simona
Format: Conference Proceeding
Language:English
Subjects:
Accidents
Context modeling
deep learning
Forecasting
Predictive models
risk prediction
Task analysis
traffic accident risk
Transformers
vision transformers
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 4769
container_issue
container_start_page 4762
container_title
container_volume
creator Grigorev, Artur
Saleh, Khaled
Mihaita, Adriana-Simona
description We propose an enhancement to our previously proposed novel model called Contextual Vision Transformer (ViT) to address the problem of traffic accident risk forecasting. This framework combines spatial and temporal information using a data-driven approach. By treating the problem as a computer vision task, we can predict traffic accident risk as the next frame in a video sequence. Specificaly, we extend the ViT network with a Static Map generation (named XViT) for even better results on the Chicago dataset. Furthermore, we propose a Coarse-Fine-Coarse transformer architecture as an alternative approach to enhance traffic accident risk prediction.
doi_str_mv 10.1109/ITSC57777.2023.10421915
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10421915</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10421915</ieee_id><sourcerecordid>10421915</sourcerecordid><originalsourceid>FETCH-LOGICAL-i204t-50d5b6127d0c3797a0f355783b03db090b1d8810c45f36e4dde545f5305f47ea3</originalsourceid><addsrcrecordid>eNpVkNFKAzEQRaMgWGr_QDA_sHWSbDabx7LYWqgItvpasptZjbZpSVLUD_C_jVQfvA8zd2DOfbiEXDEYMwb6er5aNlJljTlwMWZQcqaZPCEjrXQtJAity4qfkgFnUhQATJ2TUYyvkCV4XQkYkK9VMH3vOjrpOmfRJ_rg4hud7gJ2Jibnn-kh_sxm5xN-pIPZ0CcX3c7TTPrY78IWQ6TvLr3QZTIpR92ZPZ2hx5Cv_Ge8zbQJEYup81gc_T_8gpz1ZhNx9LuH5HF6s2pui8X9bN5MFoXjUKZCgpVtxbiy0AmllYFeSKlq0YKwLWhoma1rBl0pe1FhaS3KbKUA2ZcKjRiSy2OuQ8T1PritCZ_rv-bEN5c1ZKw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Traffic Accident Risk Forecasting using Contextual Vision Transformers with Static Map Generation and Coarse-Fine-Coarse Transformers</title><source>IEEE Xplore All Conference Series</source><creator>Grigorev, Artur ; Saleh, Khaled ; Mihaita, Adriana-Simona</creator><creatorcontrib>Grigorev, Artur ; Saleh, Khaled ; Mihaita, Adriana-Simona</creatorcontrib><description>We propose an enhancement to our previously proposed novel model called Contextual Vision Transformer (ViT) to address the problem of traffic accident risk forecasting. This framework combines spatial and temporal information using a data-driven approach. By treating the problem as a computer vision task, we can predict traffic accident risk as the next frame in a video sequence. Specificaly, we extend the ViT network with a Static Map generation (named XViT) for even better results on the Chicago dataset. Furthermore, we propose a Coarse-Fine-Coarse transformer architecture as an alternative approach to enhance traffic accident risk prediction.</description><identifier>EISSN: 2153-0017</identifier><identifier>EISBN: 9798350399462</identifier><identifier>DOI: 10.1109/ITSC57777.2023.10421915</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accidents ; Context modeling ; deep learning ; Forecasting ; Predictive models ; risk prediction ; Task analysis ; traffic accident risk ; Transformers ; vision transformers ; Visualization</subject><ispartof>2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), 2023, p.4762-4769</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10421915$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,27906,54536,54913</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10421915$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Grigorev, Artur</creatorcontrib><creatorcontrib>Saleh, Khaled</creatorcontrib><creatorcontrib>Mihaita, Adriana-Simona</creatorcontrib><title>Traffic Accident Risk Forecasting using Contextual Vision Transformers with Static Map Generation and Coarse-Fine-Coarse Transformers</title><title>2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)</title><addtitle>ITSC</addtitle><description>We propose an enhancement to our previously proposed novel model called Contextual Vision Transformer (ViT) to address the problem of traffic accident risk forecasting. This framework combines spatial and temporal information using a data-driven approach. By treating the problem as a computer vision task, we can predict traffic accident risk as the next frame in a video sequence. Specificaly, we extend the ViT network with a Static Map generation (named XViT) for even better results on the Chicago dataset. Furthermore, we propose a Coarse-Fine-Coarse transformer architecture as an alternative approach to enhance traffic accident risk prediction.</description><subject>Accidents</subject><subject>Context modeling</subject><subject>deep learning</subject><subject>Forecasting</subject><subject>Predictive models</subject><subject>risk prediction</subject><subject>Task analysis</subject><subject>traffic accident risk</subject><subject>Transformers</subject><subject>vision transformers</subject><subject>Visualization</subject><issn>2153-0017</issn><isbn>9798350399462</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2023</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpVkNFKAzEQRaMgWGr_QDA_sHWSbDabx7LYWqgItvpasptZjbZpSVLUD_C_jVQfvA8zd2DOfbiEXDEYMwb6er5aNlJljTlwMWZQcqaZPCEjrXQtJAity4qfkgFnUhQATJ2TUYyvkCV4XQkYkK9VMH3vOjrpOmfRJ_rg4hud7gJ2Jibnn-kh_sxm5xN-pIPZ0CcX3c7TTPrY78IWQ6TvLr3QZTIpR92ZPZ2hx5Cv_Ge8zbQJEYup81gc_T_8gpz1ZhNx9LuH5HF6s2pui8X9bN5MFoXjUKZCgpVtxbiy0AmllYFeSKlq0YKwLWhoma1rBl0pe1FhaS3KbKUA2ZcKjRiSy2OuQ8T1PritCZ_rv-bEN5c1ZKw</recordid><startdate>20230924</startdate><enddate>20230924</enddate><creator>Grigorev, Artur</creator><creator>Saleh, Khaled</creator><creator>Mihaita, Adriana-Simona</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20230924</creationdate><title>Traffic Accident Risk Forecasting using Contextual Vision Transformers with Static Map Generation and Coarse-Fine-Coarse Transformers</title><author>Grigorev, Artur ; Saleh, Khaled ; Mihaita, Adriana-Simona</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i204t-50d5b6127d0c3797a0f355783b03db090b1d8810c45f36e4dde545f5305f47ea3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accidents</topic><topic>Context modeling</topic><topic>deep learning</topic><topic>Forecasting</topic><topic>Predictive models</topic><topic>risk prediction</topic><topic>Task analysis</topic><topic>traffic accident risk</topic><topic>Transformers</topic><topic>vision transformers</topic><topic>Visualization</topic><toplevel>online_resources</toplevel><creatorcontrib>Grigorev, Artur</creatorcontrib><creatorcontrib>Saleh, Khaled</creatorcontrib><creatorcontrib>Mihaita, Adriana-Simona</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Grigorev, Artur</au><au>Saleh, Khaled</au><au>Mihaita, Adriana-Simona</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Traffic Accident Risk Forecasting using Contextual Vision Transformers with Static Map Generation and Coarse-Fine-Coarse Transformers</atitle><btitle>2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)</btitle><stitle>ITSC</stitle><date>2023-09-24</date><risdate>2023</risdate><spage>4762</spage><epage>4769</epage><pages>4762-4769</pages><eissn>2153-0017</eissn><eisbn>9798350399462</eisbn><abstract>We propose an enhancement to our previously proposed novel model called Contextual Vision Transformer (ViT) to address the problem of traffic accident risk forecasting. This framework combines spatial and temporal information using a data-driven approach. By treating the problem as a computer vision task, we can predict traffic accident risk as the next frame in a video sequence. Specificaly, we extend the ViT network with a Static Map generation (named XViT) for even better results on the Chicago dataset. Furthermore, we propose a Coarse-Fine-Coarse transformer architecture as an alternative approach to enhance traffic accident risk prediction.</abstract><pub>IEEE</pub><doi>10.1109/ITSC57777.2023.10421915</doi><tpages>8</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2153-0017
ispartof 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), 2023, p.4762-4769
issn 2153-0017
language eng
recordid cdi_ieee_primary_10421915
source IEEE Xplore All Conference Series
subjects Accidents
Context modeling
deep learning
Forecasting
Predictive models
risk prediction
Task analysis
traffic accident risk
Transformers
vision transformers
Visualization
title Traffic Accident Risk Forecasting using Contextual Vision Transformers with Static Map Generation and Coarse-Fine-Coarse Transformers
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T20%3A21%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Traffic%20Accident%20Risk%20Forecasting%20using%20Contextual%20Vision%20Transformers%20with%20Static%20Map%20Generation%20and%20Coarse-Fine-Coarse%20Transformers&rft.btitle=2023%20IEEE%2026th%20International%20Conference%20on%20Intelligent%20Transportation%20Systems%20(ITSC)&rft.au=Grigorev,%20Artur&rft.date=2023-09-24&rft.spage=4762&rft.epage=4769&rft.pages=4762-4769&rft.eissn=2153-0017&rft_id=info:doi/10.1109/ITSC57777.2023.10421915&rft.eisbn=9798350399462&rft_dat=%3Cieee_CHZPO%3E10421915%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i204t-50d5b6127d0c3797a0f355783b03db090b1d8810c45f36e4dde545f5305f47ea3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10421915&rfr_iscdi=true