We want the WWF site to be comfortable and interesting for you. We work with web analytics to become better. Cookies are used to collect analytical data. All information is completely confidential and is never passed on to third parties. Confirm your agreement with the policy regarding cookies or learn more about the technology.
Accept
What we do
Regions
Премия рунета 2017

Neural network used to calculate the population of Saiga antelope in Southern Russia

03 october 2019
WWF-Russia has joined forces with SPH Engineering to develop an automated system of calculating populations of Saiga antelope Saiga tatarica using data obtained with UAVs.
An example of aerial photography of the antelopes and the result of a neural network analysis of an aggregation of Saiga antelopes
SPH Engineering

In 2018-2019 WWF researched methods of counting Saiga antelopes with the help of UAVs. In June 2019, an aerial photoshoot of the animals was performed in Chornye Zemli, Mekletinskii, and Stepnoi nature reserves. 

An analysis of the pictures taken during the photoshoot performed by wildlife experts revealed several seasonal aggregations and their composition by sex and age. This kind of manual analysis of aerial photography is a labor-intensive process that requires the involvement of highly-qualified professionals. In order to optimize the process of analyzing such images, WWF called in the specialists from SPH Engineering - one of the leaders in the field of UAV software development and digital analysis of photographs. They developed and trained neural network algorithms that could recognize all antelopes on a given image and identify their age and sex.

 

Evgenii Polonsky

 At the moment, experts are comparing the results of the manual and automated analyses of the images to determine whether any changes in the neural network’s detection strategy or learning conditions are needed.

 “It is always a pleasure to see modern technologies assisting in the preservation of wildlife, rather than causing it harm,” says Alexei Yankelevich, the R&D director at SPH Engineering. “We are happy that our neural network algorithm allowed the specialists from WWF to do their work much more efficiently. The task turned out to be more challenging than anticipated. The photoshoot was carried out at a high altitude in order not to scare the animals with the sound of drone engines. Therefore, there were very few dots per animal on a picture. This compelled us to be extremely careful with creation of the learning dataset and the processing pipeline, so the quality of detection and classification of the animals would be appropriate.”

-----------------------

 About SPH Engineering

SPH Engineering has been developing software for UAV control and data processing since 2013. The company is located in Riga, Latvia. The flagship product of the company is Universal ground Control Software (UgCS), which is used by thousands of professionals worldwide for planning and performing missions with UAVs in complex environments, as well as data processing.
For additional information please contact
Traffic programme Coordinator