Night Fog Pedestrian Detection: Synthetic Kia Ray POV Imagery

JTSGRIT generated this synthetic image dataset in March 2026 using Unity Perception to model pedestrian detection in night fog. It provides fewer than 1,000 images at 1101 x 514 resolution captured from a Kia Ray vehicle's point-of-view at a height of 1.4 meters.

Use Cases

• Training YOLOv8 models to identify the 'Pedestrian' class in low-visibility night fog
• Evaluating detection accuracy using the 1101 x 514 resolution images
• Simulating Kia Ray blackbox sensor data for autonomous driving perception tests

Strengths

• Unity Perception generated synthetic data
• Specific 1.4m POV height for Kia Ray simulation
• YOLOv8 ready format

Limitations

• Small sample size of fewer than 1,000 images
• Single-class label set restricted to pedestrians
• Synthetic domain gap compared to real-world sensor noise

Provenance

Source

JTSGRIT

Collection Method

synthetic

Freshness

Last updated March 2026.