FLIR European Regional Thermal Dataset for Algorithm Training

The FLIR Enhanced European Thermal Dataset is available for sale to automotive developers. It enables developers to start training convolutional neural networks (CNN), empowering the automotive community to create the next generation of safer and more efficient ADAS and driverless vehicle systems using cost-effective thermal cameras from FLIR.

The dataset was acquired via a thermal camera mounted on a vehicle. It contains a total of 14,353 annotated thermal images with 3,554 images sampled from short videos and 10,799 images from a continuous 360-second video. Videos were taken at a variety of locations, light conditions, and weather conditions (see "extra_info" in the images section of the annotations json).

The videos were captured at the following locations London (England); Paris (France);  Madrid, Toledo, Granada, Malaga (Spain)

Paris-Arc-1.jpg

London-Buckingham.jpg

London-Tunnel.jpg

Why Use FLIR Thermal Sensing for ADAS?

The ability to sense thermal infrared radiation, or heat, within the ADAS context provides both complementary and distinct advantages to existing sensor technologies such as visible cameras, Lidar and radar systems:

  • With over 15 years of experience working with Veoneer to make the only automotive-qualified thermal camera, FLIR’s thermal sensors are deployed in over 600,000 cars today for driver warning systems.
  • The FLIR thermal cameras can be used to detect and classify objects in challenging conditions including total darkness, fog, smoke, inclement weather and glare, providing a supplemental dataset beyond LiDAR, radar and visible cameras. 
  • When combined with visible-light data and distance scanning data from LiDAR and radar, thermal data paired with machine learning creates a more comprehensive detection and classification system.

Dataset Details & Specifications

Content

Synced annotated thermal imagery and annotated RGB imagery for reference. Camera centerlines approximately 2 inches apart and collimated to minimize parallax.

Images

Frames were sampled from 191 different videos:
3,554 frames
51,823 annotations

Frame Annotation Labels

Bike: 542
Bus: 1,047
Car: 19,701 
Hydrant: 2
Light: 4,695
Motorcycle: 1,202 
Person: 14,797
Sign: 9,101 
Truck: 654
Other Vehicle: 82
Total: 51,823

Weather

Clear
Overcast
Partly cloudy
Rainy
Unknown

Scene

City Street: 2,050
Gas Station: 2
Highway: 869
Residential: 358
Parking Lot: 15
Tunnel: 85
Other: 52
Unknown: 11
Total: 3,442

Time of Day

Day: 57%
Night: 25%
Dawn/Dusk: 4%
Unknown: 14%
Total: 100%

Sample Results

Accuracy (mAP)
Value Overall: 0.475
Person: 0.547
Car: 0.701
Bus: 0.602
Motorcycle: 0.724
Bike: 0.415 

Image Capture Refresh Rate

Recorded at 30Hz. Dataset sequences sampled at 2 frames/sec or 1 frame/ second. Video annotations were performed at 30 frames/sec recording.

Location

The videos were captured in London ( England ); Paris ( France ); Madrid, Toledo, Granada, Malaga ( Spain )

Capture Camera Specifications

IR Tau2 640x512, 13mm f/1.0 (HFOV 45°, VFOV 37°) FLIR BlackFly (BFS-U3-51S5C-C) 1280x1024, 4-8mm f/1.4-16 megapixel lens (FOV set to match Tau2)

Dataset File Format

1. Thermal - 14-bit TIFF (no AGC)
2. Thermal 8-bit JPEG (AGC applied) w/o bounding boxes embedded in images
3. Thermal 8-bit JPEG (AGC applied) with bounding boxes embedded in images for viewing purposes
4. RGB - 8-bit JPEG
5. Annotations: JSON (MSCOCO format)
6. No temporal filter applied

   

FLIR ADK Training and Development Settings

Use the FLIR ADK with default settings to begin data collection

 

 


Have questions or want a larger dataset?

Please contact the FLIR ADAS team at ADAS-Support@flir.com for assistance.

 

Related Products

PathFindIR™ II
PathFindIR™ II

Driver Vision Enhancement System

FLIR ADK™
FLIR ADK™

Thermal Vision Automotive Development Kit (ADK)