Real-time traffic sign recognition using spatially weighted HOG trees

Traffic sign recognition is one of the main components of a Driver Assistance System (DAS). This paper presents a real-time traffic sign recognition system. It consists of three stages: 1) an image segmentation using red color enhancement to reduce the search space, 2) a HOG-based Support Vector Mac...

Full description

Saved in:
Bibliographic Details
Main Authors: Zaklouta, F., Stanciulescu, B.
Format: Conference Proceeding
Language:English
Subjects:
Image color analysis
Image segmentation
Lighting
Real time systems
Support vector machines
Training
Vegetation
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 66
container_issue
container_start_page 61
container_title
container_volume
creator Zaklouta, F.
Stanciulescu, B.
description Traffic sign recognition is one of the main components of a Driver Assistance System (DAS). This paper presents a real-time traffic sign recognition system. It consists of three stages: 1) an image segmentation using red color enhancement to reduce the search space, 2) a HOG-based Support Vector Machine (SVM) detection to extract the traffic signs, and 3) a tree classifier (K-d tree or Random Forests) to identify the signs found. This methodology is tested on images under bad weather conditions and poor illumination. The tree classifiers achieve high classification rates for the German Traffic Sign Recognition Benchmark and the ETH 80 dataset. The K-d tree classification is improved by introducing a Gaussian spatial weighting to favor the interior blocks of the HOG descriptors.
doi_str_mv 10.1109/ICAR.2011.6088571
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6088571</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6088571</ieee_id><sourcerecordid>6088571</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-a407055f1bb905b80c2c2851bdeb3cc6dff2a94f35ca0edb59729db324b379593</originalsourceid><addsrcrecordid>eNo1j8FKAzEYhCNSUOs-gHjJC-z6J9lskqOU2gqFQum9JNk_28h2WzYR6du7YJ3LMIdvmCHkhUHFGJi3z8X7ruLAWNWA1lKxO1IYpVktlWJMKn5Pnv6DFg-kSOkLJjVcKc0fyXKHti9zPCHNow0heppiN9AR_bkbYo7ngX6nOHQ0XWyOtu-v9Adjd8zY0vV2NVGI6ZnMgu0TFjefk_3Hcr9Yl5vtalq4KaOBXNoaFEgZmHMGpNPguedaMteiE943bQjcmjoI6S1g66RR3LRO8NoJZaQRc_L6VxsR8XAZ48mO18PtuPgFSgFMTw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Real-time traffic sign recognition using spatially weighted HOG trees</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Zaklouta, F. ; Stanciulescu, B.</creator><creatorcontrib>Zaklouta, F. ; Stanciulescu, B.</creatorcontrib><description>Traffic sign recognition is one of the main components of a Driver Assistance System (DAS). This paper presents a real-time traffic sign recognition system. It consists of three stages: 1) an image segmentation using red color enhancement to reduce the search space, 2) a HOG-based Support Vector Machine (SVM) detection to extract the traffic signs, and 3) a tree classifier (K-d tree or Random Forests) to identify the signs found. This methodology is tested on images under bad weather conditions and poor illumination. The tree classifiers achieve high classification rates for the German Traffic Sign Recognition Benchmark and the ETH 80 dataset. The K-d tree classification is improved by introducing a Gaussian spatial weighting to favor the interior blocks of the HOG descriptors.</description><identifier>ISBN: 1457711583</identifier><identifier>ISBN: 9781457711589</identifier><identifier>EISBN: 9781457711572</identifier><identifier>EISBN: 1457711591</identifier><identifier>EISBN: 9781457711596</identifier><identifier>EISBN: 1457711575</identifier><identifier>DOI: 10.1109/ICAR.2011.6088571</identifier><language>eng</language><publisher>IEEE</publisher><subject>Image color analysis ; Image segmentation ; Lighting ; Real time systems ; Support vector machines ; Training ; Vegetation</subject><ispartof>2011 15th International Conference on Advanced Robotics (ICAR), 2011, p.61-66</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/6088571$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2057,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6088571$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zaklouta, F.</creatorcontrib><creatorcontrib>Stanciulescu, B.</creatorcontrib><title>Real-time traffic sign recognition using spatially weighted HOG trees</title><title>2011 15th International Conference on Advanced Robotics (ICAR)</title><addtitle>ICAR</addtitle><description>Traffic sign recognition is one of the main components of a Driver Assistance System (DAS). This paper presents a real-time traffic sign recognition system. It consists of three stages: 1) an image segmentation using red color enhancement to reduce the search space, 2) a HOG-based Support Vector Machine (SVM) detection to extract the traffic signs, and 3) a tree classifier (K-d tree or Random Forests) to identify the signs found. This methodology is tested on images under bad weather conditions and poor illumination. The tree classifiers achieve high classification rates for the German Traffic Sign Recognition Benchmark and the ETH 80 dataset. The K-d tree classification is improved by introducing a Gaussian spatial weighting to favor the interior blocks of the HOG descriptors.</description><subject>Image color analysis</subject><subject>Image segmentation</subject><subject>Lighting</subject><subject>Real time systems</subject><subject>Support vector machines</subject><subject>Training</subject><subject>Vegetation</subject><isbn>1457711583</isbn><isbn>9781457711589</isbn><isbn>9781457711572</isbn><isbn>1457711591</isbn><isbn>9781457711596</isbn><isbn>1457711575</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1j8FKAzEYhCNSUOs-gHjJC-z6J9lskqOU2gqFQum9JNk_28h2WzYR6du7YJ3LMIdvmCHkhUHFGJi3z8X7ruLAWNWA1lKxO1IYpVktlWJMKn5Pnv6DFg-kSOkLJjVcKc0fyXKHti9zPCHNow0heppiN9AR_bkbYo7ngX6nOHQ0XWyOtu-v9Adjd8zY0vV2NVGI6ZnMgu0TFjefk_3Hcr9Yl5vtalq4KaOBXNoaFEgZmHMGpNPguedaMteiE943bQjcmjoI6S1g66RR3LRO8NoJZaQRc_L6VxsR8XAZ48mO18PtuPgFSgFMTw</recordid><startdate>201106</startdate><enddate>201106</enddate><creator>Zaklouta, F.</creator><creator>Stanciulescu, B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201106</creationdate><title>Real-time traffic sign recognition using spatially weighted HOG trees</title><author>Zaklouta, F. ; Stanciulescu, B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-a407055f1bb905b80c2c2851bdeb3cc6dff2a94f35ca0edb59729db324b379593</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Image color analysis</topic><topic>Image segmentation</topic><topic>Lighting</topic><topic>Real time systems</topic><topic>Support vector machines</topic><topic>Training</topic><topic>Vegetation</topic><toplevel>online_resources</toplevel><creatorcontrib>Zaklouta, F.</creatorcontrib><creatorcontrib>Stanciulescu, B.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL) - Journals and E-Books</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zaklouta, F.</au><au>Stanciulescu, B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Real-time traffic sign recognition using spatially weighted HOG trees</atitle><btitle>2011 15th International Conference on Advanced Robotics (ICAR)</btitle><stitle>ICAR</stitle><date>2011-06</date><risdate>2011</risdate><spage>61</spage><epage>66</epage><pages>61-66</pages><isbn>1457711583</isbn><isbn>9781457711589</isbn><eisbn>9781457711572</eisbn><eisbn>1457711591</eisbn><eisbn>9781457711596</eisbn><eisbn>1457711575</eisbn><abstract>Traffic sign recognition is one of the main components of a Driver Assistance System (DAS). This paper presents a real-time traffic sign recognition system. It consists of three stages: 1) an image segmentation using red color enhancement to reduce the search space, 2) a HOG-based Support Vector Machine (SVM) detection to extract the traffic signs, and 3) a tree classifier (K-d tree or Random Forests) to identify the signs found. This methodology is tested on images under bad weather conditions and poor illumination. The tree classifiers achieve high classification rates for the German Traffic Sign Recognition Benchmark and the ETH 80 dataset. The K-d tree classification is improved by introducing a Gaussian spatial weighting to favor the interior blocks of the HOG descriptors.</abstract><pub>IEEE</pub><doi>10.1109/ICAR.2011.6088571</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 1457711583
ispartof 2011 15th International Conference on Advanced Robotics (ICAR), 2011, p.61-66
issn
language eng
recordid cdi_ieee_primary_6088571
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Image color analysis
Image segmentation
Lighting
Real time systems
Support vector machines
Training
Vegetation
title Real-time traffic sign recognition using spatially weighted HOG trees
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T18%3A56%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Real-time%20traffic%20sign%20recognition%20using%20spatially%20weighted%20HOG%20trees&rft.btitle=2011%2015th%20International%20Conference%20on%20Advanced%20Robotics%20(ICAR)&rft.au=Zaklouta,%20F.&rft.date=2011-06&rft.spage=61&rft.epage=66&rft.pages=61-66&rft.isbn=1457711583&rft.isbn_list=9781457711589&rft_id=info:doi/10.1109/ICAR.2011.6088571&rft.eisbn=9781457711572&rft.eisbn_list=1457711591&rft.eisbn_list=9781457711596&rft.eisbn_list=1457711575&rft_dat=%3Cieee_6IE%3E6088571%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-a407055f1bb905b80c2c2851bdeb3cc6dff2a94f35ca0edb59729db324b379593%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=6088571&rfr_iscdi=true