The common crane (Grus grus) is a large flocking crane which can cause extensive agricultural damage, as found in Israel, with population increase from few hundreds in the 1980s to about 50,000 in 2019. To reduce such conflict, a diversionary feeding and hazing program was created, but to determine how much to feed and to monitor the projects over time, the cranes must be counted. An advanced and accurate method for automatically calculating the number of cranes, using thermal cameras at night and visible light cameras during the day onboard unmanned aerial vehicles (UAVs), based on computer vision and machine learning was developed. The cranes congregate at night in a large communal roost, making it possible to count the birds while they are relatively static. A dedicated algorithm was developed that aimed to identify the cranes based on their spectral characteristics (typical temperature, shape, size) and to effectively separate the cranes from the typical background. The automatic segmentation and counting of roosting common cranes using UAV nighttime thermal images had an Overall Accuracy (OA) of 91.47%, User’s Accuracy (UA) of 99.68%, and Producer’s Accuracy (PA) of 91.74%. The computer vision and machine learning algorithm based on the YOLO v3 platform of daytime RGB UAV images of common cranes at the feeding station yielded OA of 94.51%, UA of 99.91%, PA of 94.59%. These results are highly encouraging, and although the algorithms were developed for the purpose of counting cranes, they could be adapted for other counting purposes for wildlife management.

Dr. Assaf Chen
Automatic Segmentation and Counting of Roosting Common Cranes (Grus grus) using UAV Thermal Images, Computer Vision, and Machine Learning in the Hula Valley, Israel
MIGAL Galilee Research Institute, Israel