FLIR releases starter thermal imaging dataset for machine learning for advanced driver-assistance development
FLIR Systems announced the availability of its open-source machine learning thermal dataset for advanced driver-assistance systems (ADAS) and self-driving vehicle researchers, developers, and auto manufacturers. The dataset features a compilation of more than 10,000 annotated thermal images of day and nighttime scenarios.
FLIR says the starter thermal dataset is the first of its kind to include annotations for cars, other vehicles, people, bicycles, and dogs, and it is intended to enable developers to begin testing and evolving convolutional neural networks (CNN) with the FLIR Automotive Development Kit (ADK). The ADK’s IP67-rated 12-μm thermal sensor is small, installation is plug-and-play, and driving with the system is designed to be simple. The ADK’s thermal data ports directly into analytics over the standard USB connection, or through an optional NVIDIA DRIVE PX 2 connection.
The dataset allows the automotive community to quickly evaluate thermal sensors on next-generation algorithms. When combined with visible light cameras, LiDAR, and radar, thermal sensor data paired with machine learning helps create a more comprehensive and redundant system for identifying and classifying roadway objects, especially pedestrians and other living things.
“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 dataset 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.”
The dataset will be available in July 2018. Register to receive information about the dataset at www.flir.com/adasdataset.