ThermalTracker Software Identifies Offshore Animals in Thermal Video

Thermal imaging is being used to automatically track and categorize birds and bats, helping to protect wildlife near offshore wind turbines and supporting responsible wind farm siting and operations.

Pacific Northwest National Laboratory’s ThermalTracker software analyzes thermal video to help birds and bats near offshore wind farms. PNNL engineer Shari Matzner is shown here with a thermal video camera she’s using for this research. Courtesy of Pacific Northwest National Laboratory.

ThermalTracker, an open source software package developed by the Pacific Northwest National Laboratory (PNNL), extracts flight tracks of birds and bats from thermal video recordings and characterizes flight tracks in quantified terms, giving researchers a more complete picture of the animals that live in offshore locations. ThermalTracker plug-and-play software can be used with any standard desktop computer, thermal camera and statistical software.

While thermal cameras see general animal shapes when visibility is low, they don't provide clear images or color, which can make identifying animals difficult.

Three birds are seen flying offshore in this screenshot of the thermal video that PNNL’s software analyzes. Courtesy of Pacific Northwest National Laboratory.

PNNL's solution uses algorithms that can identify birds and bats based on their flight behaviors. The ThermalTracker software specifically evaluates two characteristics: the shape of the path that birds or bats take to fly from point A to B, and how frequently their wings beat up and down. The software evaluates thermal video for these behaviors and then determines whether the observed animals are bats or belong to bird families such as gulls, terns or swallows.

Today, most wind power sites are evaluated for birds and bats through field observations. For offshore wind power sites, scientists board a boat, but can only observe in daylight and when the weather cooperates. Remote sensing technologies could enable longer-term bird and bat monitoring that is also less expensive and labor-intensive.

An early version of ThermalTracker was able to detect 81 percent of all animals recorded in thermal video and correctly classify 82 percent of those animals. It took humans an average of five times longer to arrive at the same conclusions as the software.

Now, PNNL researchers are improving the software. They’ve updated its algorithms so it can detect animals as video is being recorded, instead of processing video after the fact. Live data processing means the software only saves video when a bird or bat is detected. With less data to store, the system can be used for long-term observation.

The team is also creating a system that offers “stereo vision,” i.e. 3D video, by using two thermal cameras instead of one. Three-dimensional video provides depth perception, which helps determine if birds are flying at the heights where turbines spin and if birds are avoiding existing turbines. This technology will also reveal how far a bird is from a camera, which can determine bird size, contributing to more accurate identification.

Field researchers are now testing the new stereo camera system to determine how well it identifies birds compared to their field observations. ThermalTracker’s developers will use the field biologists’ notes to refine the software.

ThermalTracker's original source code — without real-time processing and using video from just one camera — is open source and can be downloaded for free from GitHub. The more advanced code is still being developed.

Research on the early version of Thermal Tracker was published in Ecological Informatics (doi: 10.1016/j.ecoinf.2015.09.001).

ThermalTracker’s original source code can be downloaded for free here.

Researchers can now collect the data they need to better understand the potential effects of offshore wind turbines on bird and bat populations. This plug and play software can be used with any standard desktop computer, thermal camera, and statistical software to identify species and behaviors of animals in offshore locations.