TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems Article Swipe

PDF

Y. P. Lu , Dong Wang , Kaifeng Huang , Bihuan Chen , Xin Peng ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.05932

Autonomous vehicle technology has been developed in the last decades with recent advances in sensing and computing technology. There is an urgent need to ensure the reliability and robustness of autonomous driving systems (ADSs). Despite the recent achievements in testing various ADS modules, little attention has been paid on the automated testing of traffic light detection models in ADSs. A common practice is to manually collect and label traffic light data. However, it is labor-intensive, and even impossible to collect diverse data under different driving environments. To address these problems, we propose and implement TigAug to automatically augment labeled traffic light images for testing traffic light detection models in ADSs. We construct two families of metamorphic relations and three families of transformations based on a systematic understanding of weather environments, camera properties, and traffic light properties. We use augmented images to detect erroneous behaviors of traffic light detection models by transformation-specific metamorphic relations, and to improve the performance of traffic light detection models by retraining. Large-scale experiments with four state-of-the-art traffic light detection models and two traffic light datasets have demonstrated that i) TigAug is effective in testing traffic light detection models, ii) TigAug is efficient in synthesizing traffic light images, and iii) TigAug generates traffic light images with acceptable naturalness.

Related Topics

Utah Data Center

General Data Protection Regulation

Data And Information Visualization

Data Recovery

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2507.05932
PDF: https://arxiv.org/pdf/2507.05932
OA Status: green
OpenAlex ID: https://openalex.org/W4416061673

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416061673

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2507.05932

Digital Object Identifier
Title: TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-07-08

Full publication date if available
Authors: Y. P. Lu, Dong Wang, Kaifeng Huang, Bihuan Chen, Xin Peng

List of authors in order
Landing page: https://arxiv.org/abs/2507.05932

Publisher landing page
PDF URL: https://arxiv.org/pdf/2507.05932

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2507.05932

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416061673
doi	https://doi.org/10.48550/arxiv.2507.05932
ids.doi	https://doi.org/10.48550/arxiv.2507.05932
ids.openalex	https://openalex.org/W4416061673
fwci
type	preprint
title	TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2507.05932
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2507.05932
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2507.05932
locations[1].id	doi:10.48550/arxiv.2507.05932
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2507.05932
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5021146040
authorships[0].author.orcid	https://orcid.org/0009-0009-8946-9596
authorships[0].author.display_name	Y. P. Lu
authorships[0].author_position	first
authorships[0].raw_author_name	Lu, You
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100665334
authorships[1].author.orcid	https://orcid.org/0000-0002-7446-4604
authorships[1].author.display_name	Dong Wang
authorships[1].author_position	middle
authorships[1].raw_author_name	Wang, Dingji
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5120322493
authorships[2].author.orcid
authorships[2].author.display_name	Kaifeng Huang
authorships[2].author_position	middle
authorships[2].raw_author_name	Huang, Kaifeng
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5059253116
authorships[3].author.orcid	https://orcid.org/0000-0001-7238-7492
authorships[3].author.display_name	Bihuan Chen
authorships[3].author_position	middle
authorships[3].raw_author_name	Chen, Bihuan
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5101854992
authorships[4].author.orcid	https://orcid.org/0000-0003-3376-2581
authorships[4].author.display_name	Xin Peng
authorships[4].author_position	last
authorships[4].raw_author_name	Peng, Xin
authorships[4].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2507.05932
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T10:25:21.940643
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2507.05932
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2507.05932
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2507.05932
primary_location.id	pmh:oai:arXiv.org:2507.05932
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2507.05932
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2507.05932
publication_date	2025-07-08
publication_year	2025
referenced_works_count	0
abstract_inverted_index.A	59
abstract_inverted_index.a	124
abstract_inverted_index.To	86
abstract_inverted_index.We	110, 136
abstract_inverted_index.an	20
abstract_inverted_index.by	149, 163
abstract_inverted_index.i)	182
abstract_inverted_index.in	6, 13, 38, 57, 108, 186, 196
abstract_inverted_index.is	19, 62, 73, 184, 194
abstract_inverted_index.it	72
abstract_inverted_index.of	29, 52, 114, 120, 127, 144, 158
abstract_inverted_index.on	48, 123
abstract_inverted_index.to	23, 63, 78, 95, 140, 154
abstract_inverted_index.we	90
abstract_inverted_index.ADS	41
abstract_inverted_index.and	15, 27, 66, 75, 92, 117, 132, 153, 174, 201
abstract_inverted_index.for	102
abstract_inverted_index.has	3, 45
abstract_inverted_index.ii)	192
abstract_inverted_index.the	7, 25, 35, 49, 156
abstract_inverted_index.two	112, 175
abstract_inverted_index.use	137
abstract_inverted_index.been	4, 46
abstract_inverted_index.data	81
abstract_inverted_index.even	76
abstract_inverted_index.four	168
abstract_inverted_index.have	179
abstract_inverted_index.iii)	202
abstract_inverted_index.last	8
abstract_inverted_index.need	22
abstract_inverted_index.paid	47
abstract_inverted_index.that	181
abstract_inverted_index.with	10, 167, 208
abstract_inverted_index.ADSs.	58, 109
abstract_inverted_index.There	18
abstract_inverted_index.based	122
abstract_inverted_index.data.	70
abstract_inverted_index.label	67
abstract_inverted_index.light	54, 69, 100, 105, 134, 146, 160, 171, 177, 189, 199, 206
abstract_inverted_index.these	88
abstract_inverted_index.three	118
abstract_inverted_index.under	82
abstract_inverted_index.TigAug	94, 183, 193, 203
abstract_inverted_index.camera	130
abstract_inverted_index.common	60
abstract_inverted_index.detect	141
abstract_inverted_index.ensure	24
abstract_inverted_index.images	101, 139, 207
abstract_inverted_index.little	43
abstract_inverted_index.models	56, 107, 148, 162, 173
abstract_inverted_index.recent	11, 36
abstract_inverted_index.urgent	21
abstract_inverted_index.(ADSs).	33
abstract_inverted_index.Despite	34
abstract_inverted_index.address	87
abstract_inverted_index.augment	97
abstract_inverted_index.collect	65, 79
abstract_inverted_index.decades	9
abstract_inverted_index.diverse	80
abstract_inverted_index.driving	31, 84
abstract_inverted_index.images,	200
abstract_inverted_index.improve	155
abstract_inverted_index.labeled	98
abstract_inverted_index.models,	191
abstract_inverted_index.propose	91
abstract_inverted_index.sensing	14
abstract_inverted_index.systems	32
abstract_inverted_index.testing	39, 51, 103, 187
abstract_inverted_index.traffic	53, 68, 99, 104, 133, 145, 159, 170, 176, 188, 198, 205
abstract_inverted_index.various	40
abstract_inverted_index.vehicle	1
abstract_inverted_index.weather	128
abstract_inverted_index.However,	71
abstract_inverted_index.advances	12
abstract_inverted_index.datasets	178
abstract_inverted_index.families	113, 119
abstract_inverted_index.manually	64
abstract_inverted_index.modules,	42
abstract_inverted_index.practice	61
abstract_inverted_index.attention	44
abstract_inverted_index.augmented	138
abstract_inverted_index.automated	50
abstract_inverted_index.behaviors	143
abstract_inverted_index.computing	16
abstract_inverted_index.construct	111
abstract_inverted_index.detection	55, 106, 147, 161, 172, 190
abstract_inverted_index.developed	5
abstract_inverted_index.different	83
abstract_inverted_index.effective	185
abstract_inverted_index.efficient	195
abstract_inverted_index.erroneous	142
abstract_inverted_index.generates	204
abstract_inverted_index.implement	93
abstract_inverted_index.problems,	89
abstract_inverted_index.relations	116
abstract_inverted_index.Autonomous	0
abstract_inverted_index.acceptable	209
abstract_inverted_index.autonomous	30
abstract_inverted_index.impossible	77
abstract_inverted_index.relations,	152
abstract_inverted_index.robustness	28
abstract_inverted_index.systematic	125
abstract_inverted_index.technology	2
abstract_inverted_index.Large-scale	165
abstract_inverted_index.experiments	166
abstract_inverted_index.metamorphic	115, 151
abstract_inverted_index.performance	157
abstract_inverted_index.properties,	131
abstract_inverted_index.properties.	135
abstract_inverted_index.reliability	26
abstract_inverted_index.retraining.	164
abstract_inverted_index.technology.	17
abstract_inverted_index.achievements	37
abstract_inverted_index.demonstrated	180
abstract_inverted_index.naturalness.	210
abstract_inverted_index.synthesizing	197
abstract_inverted_index.automatically	96
abstract_inverted_index.environments,	129
abstract_inverted_index.environments.	85
abstract_inverted_index.understanding	126
abstract_inverted_index.transformations	121
abstract_inverted_index.labor-intensive,	74
abstract_inverted_index.state-of-the-art	169
abstract_inverted_index.transformation-specific	150
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile