IFR: Indoor Fire Rescue Dataset with 27,000 Frames of LiDAR, Camera, and Radar Data

27,000 synchronized frames of 16-layer LiDAR, RGB camera, and 4D radar data were collected across multiple buildings at the University of British Columbia. The Indoor FireRescue Rada (IFR) dataset includes raw ADC data, point clouds, and 3D bounding box annotations for objects like doors, chairs, and fire hydrants. This dataset was created by author yysd123 and last updated on Hugging Face in October 2025.

Use Cases

• Train 3D object detection models based on annotated bounding boxes for doors, waste containers, and fire hydrants.
• Develop sensor fusion algorithms based on synchronized LiDAR, camera, and 4D radar data.
• Benchmark indoor scene understanding systems for fire rescue robotics based on multi-building data.
• Generate synthetic or augmented training data for indoor environments based on calibrated point clouds.

Strengths

• Contains 27,000 frames of synchronized multi-sensor data.
• Includes 3D bounding box annotations for specific building layout objects.
• Data is calibrated and collected from multiple real-world buildings.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset's license is unspecified, which could restrict usage.

Provenance

Source

yysd123 on Hugging Face.

Collection Method

Acquired using synchronized and calibrated 16-layer LiDAR, RGB camera, and 4D radar.

Time Range

null

Freshness

Last updated 2025-10-13 22:28:32; freshness should be verified.

Geography

Multiple buildings at the University of British Columbia (UBC).