ARTS: Automotive Repository of Traffic Signs for the United States

Almutairy, Fayha; Alshaabi, Thayer; Nelson, Jonathan; Wshah, Safwan

doi:10.1109/tits.2019.2958486

Cited by 12 publications

(22 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only a few studies were found which detected a limited number of individual traffic signs according to MUTCD codes (22). A recent study introduced the Automotive Repository of Traffic Signs (ARTS), comprising of an extensive database of U.S. traffic signs and benchmark results (23).…”

Section: Asset Data Processing Methodologiesmentioning

confidence: 99%

Automated Real-Time Roadway Asset Inventory using Artificial Intelligence

Kargah-Ostadi¹,

Waqar²,

Hanif³

2020

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Roadway asset inventory data are essential in making data-driven asset management decisions. Despite significant advances in automated data processing, the current state of the practice is semi-automated. This paper demonstrates integration of the state-of-the-art artificial intelligence technologies within a practical framework for automated real-time identification of traffic signs from roadway images. The framework deploys one of the very latest machine learning algorithms on a cutting-edge plug-and-play device for superior effectiveness, efficiency, and reliability. The proposed platform provides an offline system onboard the survey vehicle, that runs a lightweight and speedy deep neural network on each collected roadway image and identifies traffic signs in real-time. Integration of these advanced technologies minimizes the need for subjective and time-consuming human interventions, thereby enhancing the repeatability and cost-effectiveness of the asset inventory process. The proposed framework is demonstrated using a real-world image dataset. Appropriate pre-processing techniques were employed to alleviate limitations in the training dataset. A deep learning algorithm was trained for detection, classification, and localization of traffic signs from roadway imagery. The success metrics based on this demonstration indicate that the algorithm was effective in identifying traffic signs with high accuracy on a test dataset that was not used for model development. Additionally, the algorithm exhibited this high accuracy consistently among the different considered sign categories. Moreover, the algorithm was repeatable among multiple runs and reproducible across different locations. Above all, the real-time processing capability of the proposed solution reduces the time between data collection and delivery, which enhances the data-driven decision-making process.

show abstract

Section: Asset Data Processing Methodologiesmentioning

confidence: 99%

Automated Real-Time Roadway Asset Inventory using Artificial Intelligence

Kargah-Ostadi¹,

Waqar²,

Hanif³

2020

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Here, we present an expansion to the ARTS dataset [1], providing new metadata to enable future research in this domain. The original ARTS dataset is composed of over 16,000 images spanning 175 different classes.…”

Section: Datasetsmentioning

confidence: 99%

“…To train our system and support future research we constructed the ARTS v2 dataset, which builds on the ARTS dataset [1] to become the largest dataset of geolocalized US traffic signs. ARTS v2 contains US traffic signs with class labels consistent with the Vermont VCI sign catalog [3] and contains 25,544 images, 47,589 annotations, and 199 sign classes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Object Tracking and Geo-localization from Street Images

Wilson¹,

Alshaabi²,

Oort³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ben-Bassat, et al (2019) performed about twenty-seven ergonomics and human factors considered from 10 countries for analyzed the conventional sign relative to their expectation with the conventional sign with the same meaning. For example, diamond-shaped signs indicate a warning, whereas a circular sign with crossing indicates a railroad crossing (Almutairy et al 2019). This is not always case, in the Europe countries warning is indicated by the signs with the triangle shape, and circular signs with white background and red bordure can indicate some limitation (e.g.…”

Section: Introductionmentioning

confidence: 99%

Hazard perception test among young inexperienced drivers and risk analysis while driving through a T-junction

Kabir¹,

Roy²

2023

Decis. Mak. Appl. Manag. Eng.

View full text Add to dashboard Cite

In this article, the hazard-based accident duration model and the reaction time due to various types of distractions are considered. This analysis is mainly considered T-junction or T-junctions like all other forms of roadgeometries which are more prone to accident. The model proposed is constructed by using a electronics devices along with driving simulator, to study the behavior of the yang inexperienced drivers as well as an experienced driver about their reaction by calling their phone from unknown numbers intentionally. The results show that drivers distracted by mobile phones uses the hard breaking due to least available time to respond after identification of an event. Some of the research and theory bearing on decision making and risk perception, driver situation awareness, and possible mediators of risk-taking is also analyzed here.

show abstract

ARTS: Automotive Repository of Traffic Signs for the United States

Cited by 12 publications

References 27 publications

Automated Real-Time Roadway Asset Inventory using Artificial Intelligence

Automated Real-Time Roadway Asset Inventory using Artificial Intelligence

Object Tracking and Geo-localization from Street Images

Hazard perception test among young inexperienced drivers and risk analysis while driving through a T-junction

Contact Info

Product

Resources

About