Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.

Detalhes bibliográficos
Autor(a) principal: Alessandro Moreira Fonseca
Data de Publicação: 2005
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Biblioteca Digital de Teses e Dissertações do ITA
Texto Completo: http://www.bd.bibl.ita.br/tde_busca/arquivo.php?codArquivo=328
Resumo: This work proposes and compares three algorithms for vehicle detection, composed of two main stages, preprocess and process. The first will proceed with the selection of the region of interest (ROI) and the background learning phase. The ROI is a narrow and transversal-to-lane rectangular area wherein detection is achieved, its dimensions provides low processing workload. The learning, named as progressive background training (PBT), is compounded of three consecutive and nonoverlapping steps that will produce the necessary parameters for the next stage. PBT is accomplished fully automatically, expect for requiring the manual specification of the three subset of training images, one for each training step. These steps relate to find, respectively, the gray-level lane limits (GLLL), the intensity edge threshold (IET) and the normalized chromaticity distortion threshold (NCDT). The first supposes that, in normal traffic conditions, most of the input images are of lane and uses this to select the first subset of sample-frames and build two intensity histograms; a statistical operator is used for the automatic threshold selection (ATS) and further lane intensity interval definition. The second step uses GLLL interval to fulfill the automatic sample selection (ASSEL) of the second input of images subset and build a bi-modal histogram of gradient magnitude wherein two unsupervised, non-parametric and non-context automatic threshold selection (ATS) methods are used to find the intensity edge threshold. One maximizes a cost function related to conditional entropy and the other maximizes the between-classes variance. The last step, NCDT, uses the former step threshold output to perform edge detection and use it as ASSEL and select the frames to model the statistics of the background and construct the histogram of the normalized chroma distortion. An ATS carries out a search into this histogram until find a predefined detection rate and find the NCDT. The second stage, named foreground detection (FD), has two main steps and uses all the thresholds and background statistical parameters computed in the previous stage. The first step relates to the generation of the ROI masks. These masks are binary and maps the state of each ROIs pixels features, as gray-level region position, edge-pixel and normalized chroma distortion. This amount of data is used in the next step of FD to perform the decision process and yield the desired vehicle detection output. A Fathy and Siyal (F&S) approach was taken as the groundwork to the three following resulting developments of this thesis: the MF&S is a modified version of F&S specially regarding to the learning phase, it is robust to lighting changes and shadow, but not to the interface of lane and shadow; the gradient magnitude aiding (GMA) approach is a special case of the previous yielding the same performance of MF&S when it is with its best tuning; and chroma and gradient magnitude aiding (CGMA) approach, fuses the former with gray-level and color information resulting on shadow and lane interface robustness. It is also shown how vehicle detection outputs can be used to compute basic traffic parameters such as vehicle count, traffic flow, occupancy and link travel time. Performance is verified by two further defined indexes, the detection and false alarm rates. Both optimal values respectively relate to the low probability to misclassify a vehicle and incorrectly classify lane as vehicle. Results show that CGMA reduce false alarms while maintaining the detection rate in comparison with GMA and MF&S algorithms.
id ITA_1d2d77831031b94f96ffb722bace4105
oai_identifier_str oai:agregador.ibict.br.BDTD_ITA:oai:ita.br:328
network_acronym_str ITA
network_name_str Biblioteca Digital de Teses e Dissertações do ITA
spelling Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.Processamento de imagensVisão por computadoresDetecçãoVeículosIdentificação de parâmetrosControle de trajetóriaVigilânciaControle automáticoEngenharia eletrônicaThis work proposes and compares three algorithms for vehicle detection, composed of two main stages, preprocess and process. The first will proceed with the selection of the region of interest (ROI) and the background learning phase. The ROI is a narrow and transversal-to-lane rectangular area wherein detection is achieved, its dimensions provides low processing workload. The learning, named as progressive background training (PBT), is compounded of three consecutive and nonoverlapping steps that will produce the necessary parameters for the next stage. PBT is accomplished fully automatically, expect for requiring the manual specification of the three subset of training images, one for each training step. These steps relate to find, respectively, the gray-level lane limits (GLLL), the intensity edge threshold (IET) and the normalized chromaticity distortion threshold (NCDT). The first supposes that, in normal traffic conditions, most of the input images are of lane and uses this to select the first subset of sample-frames and build two intensity histograms; a statistical operator is used for the automatic threshold selection (ATS) and further lane intensity interval definition. The second step uses GLLL interval to fulfill the automatic sample selection (ASSEL) of the second input of images subset and build a bi-modal histogram of gradient magnitude wherein two unsupervised, non-parametric and non-context automatic threshold selection (ATS) methods are used to find the intensity edge threshold. One maximizes a cost function related to conditional entropy and the other maximizes the between-classes variance. The last step, NCDT, uses the former step threshold output to perform edge detection and use it as ASSEL and select the frames to model the statistics of the background and construct the histogram of the normalized chroma distortion. An ATS carries out a search into this histogram until find a predefined detection rate and find the NCDT. The second stage, named foreground detection (FD), has two main steps and uses all the thresholds and background statistical parameters computed in the previous stage. The first step relates to the generation of the ROI masks. These masks are binary and maps the state of each ROIs pixels features, as gray-level region position, edge-pixel and normalized chroma distortion. This amount of data is used in the next step of FD to perform the decision process and yield the desired vehicle detection output. A Fathy and Siyal (F&S) approach was taken as the groundwork to the three following resulting developments of this thesis: the MF&S is a modified version of F&S specially regarding to the learning phase, it is robust to lighting changes and shadow, but not to the interface of lane and shadow; the gradient magnitude aiding (GMA) approach is a special case of the previous yielding the same performance of MF&S when it is with its best tuning; and chroma and gradient magnitude aiding (CGMA) approach, fuses the former with gray-level and color information resulting on shadow and lane interface robustness. It is also shown how vehicle detection outputs can be used to compute basic traffic parameters such as vehicle count, traffic flow, occupancy and link travel time. Performance is verified by two further defined indexes, the detection and false alarm rates. Both optimal values respectively relate to the low probability to misclassify a vehicle and incorrectly classify lane as vehicle. Results show that CGMA reduce false alarms while maintaining the detection rate in comparison with GMA and MF&S algorithms.Instituto Tecnológico de AeronáuticaJacques WaldmannAlessandro Moreira Fonseca2005-10-06info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesishttp://www.bd.bibl.ita.br/tde_busca/arquivo.php?codArquivo=328reponame:Biblioteca Digital de Teses e Dissertações do ITAinstname:Instituto Tecnológico de Aeronáuticainstacron:ITAenginfo:eu-repo/semantics/openAccessapplication/pdf2019-02-02T14:01:45Zoai:agregador.ibict.br.BDTD_ITA:oai:ita.br:328http://oai.bdtd.ibict.br/requestopendoar:null2020-05-28 19:32:57.473Biblioteca Digital de Teses e Dissertações do ITA - Instituto Tecnológico de Aeronáuticatrue
dc.title.none.fl_str_mv Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.
title Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.
spellingShingle Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.
Alessandro Moreira Fonseca
Processamento de imagens
Visão por computadores
Detecção
Veículos
Identificação de parâmetros
Controle de trajetória
Vigilância
Controle automático
Engenharia eletrônica
title_short Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.
title_full Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.
title_fullStr Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.
title_full_unstemmed Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.
title_sort Self-tuned vehicle parameters detection and estimation from vídeo sequences for traffic incident management.
author Alessandro Moreira Fonseca
author_facet Alessandro Moreira Fonseca
author_role author
dc.contributor.none.fl_str_mv Jacques Waldmann
dc.contributor.author.fl_str_mv Alessandro Moreira Fonseca
dc.subject.por.fl_str_mv Processamento de imagens
Visão por computadores
Detecção
Veículos
Identificação de parâmetros
Controle de trajetória
Vigilância
Controle automático
Engenharia eletrônica
topic Processamento de imagens
Visão por computadores
Detecção
Veículos
Identificação de parâmetros
Controle de trajetória
Vigilância
Controle automático
Engenharia eletrônica
dc.description.none.fl_txt_mv This work proposes and compares three algorithms for vehicle detection, composed of two main stages, preprocess and process. The first will proceed with the selection of the region of interest (ROI) and the background learning phase. The ROI is a narrow and transversal-to-lane rectangular area wherein detection is achieved, its dimensions provides low processing workload. The learning, named as progressive background training (PBT), is compounded of three consecutive and nonoverlapping steps that will produce the necessary parameters for the next stage. PBT is accomplished fully automatically, expect for requiring the manual specification of the three subset of training images, one for each training step. These steps relate to find, respectively, the gray-level lane limits (GLLL), the intensity edge threshold (IET) and the normalized chromaticity distortion threshold (NCDT). The first supposes that, in normal traffic conditions, most of the input images are of lane and uses this to select the first subset of sample-frames and build two intensity histograms; a statistical operator is used for the automatic threshold selection (ATS) and further lane intensity interval definition. The second step uses GLLL interval to fulfill the automatic sample selection (ASSEL) of the second input of images subset and build a bi-modal histogram of gradient magnitude wherein two unsupervised, non-parametric and non-context automatic threshold selection (ATS) methods are used to find the intensity edge threshold. One maximizes a cost function related to conditional entropy and the other maximizes the between-classes variance. The last step, NCDT, uses the former step threshold output to perform edge detection and use it as ASSEL and select the frames to model the statistics of the background and construct the histogram of the normalized chroma distortion. An ATS carries out a search into this histogram until find a predefined detection rate and find the NCDT. The second stage, named foreground detection (FD), has two main steps and uses all the thresholds and background statistical parameters computed in the previous stage. The first step relates to the generation of the ROI masks. These masks are binary and maps the state of each ROIs pixels features, as gray-level region position, edge-pixel and normalized chroma distortion. This amount of data is used in the next step of FD to perform the decision process and yield the desired vehicle detection output. A Fathy and Siyal (F&S) approach was taken as the groundwork to the three following resulting developments of this thesis: the MF&S is a modified version of F&S specially regarding to the learning phase, it is robust to lighting changes and shadow, but not to the interface of lane and shadow; the gradient magnitude aiding (GMA) approach is a special case of the previous yielding the same performance of MF&S when it is with its best tuning; and chroma and gradient magnitude aiding (CGMA) approach, fuses the former with gray-level and color information resulting on shadow and lane interface robustness. It is also shown how vehicle detection outputs can be used to compute basic traffic parameters such as vehicle count, traffic flow, occupancy and link travel time. Performance is verified by two further defined indexes, the detection and false alarm rates. Both optimal values respectively relate to the low probability to misclassify a vehicle and incorrectly classify lane as vehicle. Results show that CGMA reduce false alarms while maintaining the detection rate in comparison with GMA and MF&S algorithms.
description This work proposes and compares three algorithms for vehicle detection, composed of two main stages, preprocess and process. The first will proceed with the selection of the region of interest (ROI) and the background learning phase. The ROI is a narrow and transversal-to-lane rectangular area wherein detection is achieved, its dimensions provides low processing workload. The learning, named as progressive background training (PBT), is compounded of three consecutive and nonoverlapping steps that will produce the necessary parameters for the next stage. PBT is accomplished fully automatically, expect for requiring the manual specification of the three subset of training images, one for each training step. These steps relate to find, respectively, the gray-level lane limits (GLLL), the intensity edge threshold (IET) and the normalized chromaticity distortion threshold (NCDT). The first supposes that, in normal traffic conditions, most of the input images are of lane and uses this to select the first subset of sample-frames and build two intensity histograms; a statistical operator is used for the automatic threshold selection (ATS) and further lane intensity interval definition. The second step uses GLLL interval to fulfill the automatic sample selection (ASSEL) of the second input of images subset and build a bi-modal histogram of gradient magnitude wherein two unsupervised, non-parametric and non-context automatic threshold selection (ATS) methods are used to find the intensity edge threshold. One maximizes a cost function related to conditional entropy and the other maximizes the between-classes variance. The last step, NCDT, uses the former step threshold output to perform edge detection and use it as ASSEL and select the frames to model the statistics of the background and construct the histogram of the normalized chroma distortion. An ATS carries out a search into this histogram until find a predefined detection rate and find the NCDT. The second stage, named foreground detection (FD), has two main steps and uses all the thresholds and background statistical parameters computed in the previous stage. The first step relates to the generation of the ROI masks. These masks are binary and maps the state of each ROIs pixels features, as gray-level region position, edge-pixel and normalized chroma distortion. This amount of data is used in the next step of FD to perform the decision process and yield the desired vehicle detection output. A Fathy and Siyal (F&S) approach was taken as the groundwork to the three following resulting developments of this thesis: the MF&S is a modified version of F&S specially regarding to the learning phase, it is robust to lighting changes and shadow, but not to the interface of lane and shadow; the gradient magnitude aiding (GMA) approach is a special case of the previous yielding the same performance of MF&S when it is with its best tuning; and chroma and gradient magnitude aiding (CGMA) approach, fuses the former with gray-level and color information resulting on shadow and lane interface robustness. It is also shown how vehicle detection outputs can be used to compute basic traffic parameters such as vehicle count, traffic flow, occupancy and link travel time. Performance is verified by two further defined indexes, the detection and false alarm rates. Both optimal values respectively relate to the low probability to misclassify a vehicle and incorrectly classify lane as vehicle. Results show that CGMA reduce false alarms while maintaining the detection rate in comparison with GMA and MF&S algorithms.
publishDate 2005
dc.date.none.fl_str_mv 2005-10-06
dc.type.driver.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/masterThesis
status_str publishedVersion
format masterThesis
dc.identifier.uri.fl_str_mv http://www.bd.bibl.ita.br/tde_busca/arquivo.php?codArquivo=328
url http://www.bd.bibl.ita.br/tde_busca/arquivo.php?codArquivo=328
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Instituto Tecnológico de Aeronáutica
publisher.none.fl_str_mv Instituto Tecnológico de Aeronáutica
dc.source.none.fl_str_mv reponame:Biblioteca Digital de Teses e Dissertações do ITA
instname:Instituto Tecnológico de Aeronáutica
instacron:ITA
reponame_str Biblioteca Digital de Teses e Dissertações do ITA
collection Biblioteca Digital de Teses e Dissertações do ITA
instname_str Instituto Tecnológico de Aeronáutica
instacron_str ITA
institution ITA
repository.name.fl_str_mv Biblioteca Digital de Teses e Dissertações do ITA - Instituto Tecnológico de Aeronáutica
repository.mail.fl_str_mv
subject_por_txtF_mv Processamento de imagens
Visão por computadores
Detecção
Veículos
Identificação de parâmetros
Controle de trajetória
Vigilância
Controle automático
Engenharia eletrônica
_version_ 1706809256679833600