FLIR Systems is enabling the acceleration of being able to test thermal sensors on autonomous vehicles with the release of its open-source thermal dataset, which features more than 10,000 annotated thermal images of day and nighttime scenarios.
The company has over a decade of experience within the automotive industry. More than 500,000 FLIR thermal sensors are installed in driver warning systems from various automakers including General Motors, Volkswagen, Audi, BMW, and Mercedes-Benz, according to the company.
This dataset will enable developers to evaluate thermal sensors on next-generation algorithms. By combining this data with visible light cameras, LiDAR, and RADAR, developers will be able to build a more comprehensive and redundant system for identifying objects on the road.
According to the company, its thermal cameras have seen success in reliably classifying pedestrians, bicycles, and vehicles in challenging lighting conditions, such as total darkness, fog, smoke, shadows, inclement weather, and sun glare at four times the distance of normal headlights.
“This free, open-source dataset is a subset of what FLIR has to offer, and it provides a critical opportunity for the automotive community to expand the data set to make ADAS and self-driving cars more capable in various conditions,”said Frank Pennisi, president of the industrial business at FLIR. “Furthermore, recent high-profile autonomous-driving related accidents show a clear need for affordable,intelligent thermal sensors. With the potential for millions of autonomous-enabled vehicles, FLIR thermal sensor costs will decrease significantly, which will encourage wide-scale adoption and ultimately enable safer autonomous vehicles.”