Challenges

Advanced driver-assistance systems (ADAS) and automated driving (AD) rely on perception models to accurately detect and classify traffic signs. Training these perception models requires significant amounts of diverse, accurately labeled data. Collecting this data can be challenging, as traffic sign appearance, illumination, weather, and occlusion vary extensively between operational design domains (ODDs) and individual drives.

Why Traffic Sign Datasets?

Applied Intuition Traffic Sign Datasets empower perception and validation teams to efficiently develop ML models for traffic sign detection and classification. Improve performance on rare classes, vastly reduce deployment time and cost, and ensure compliance with ISA regulations.

Benefits

Reduce real data collection

Train a high-performance ML model with synthetic data to reduce real data collection and labeling.

Expand coverage

Utilize synthetic images to address edge cases, target data sparsity issues, and expand coverage to new countries and regions.

Iterate faster

Immediately obtain new training datasets when failures occur in testing or production, rather than waiting for collection and labeling.

Key components

Sensor models

Physically accurate synthetic data generated with validated, hardware-specific sensor models.

Ground truth labels

Error-free ground truth labels in industry-standard formats.

Domain gap coverage

Proprietary, state-of-the-art techniques to reduce and mitigate the simulation-to-real domain gap.

Variants

Thousands of sign faces and posts with procedurally generated variants.

Diversity

Different environments and weather to maximize diversity and ensure model robustness.

Global coverage

Regions include the U.S., Canada, Europe, Japan, China, South Korea, and more.

Reduce real-world data requirements by 90%

Applied Intuition’s perception team conducted a study to examine how synthetic data helps improve traffic sign classification performance.
Read the case study

Meet regulatory requirements

Intelligent speed assistance (ISA) is mandated by the European Union (EU) General Safety Regulation (GSR). Applied Intuition’s Synthetic Datasets, including Traffic Sign Datasets, help accelerate the development of ISA systems with accurate traffic sign detection and recognition abilities, reducing reliance on real labeled data.

Get started with Traffic Sign Datasets

Request a data sample and learn how Traffic Sign Datasets can accelerate your ML training for ADAS and AD.