Namibia – all about Tracks
Yes, you are reading correctly. Namibia it was again! This time with a team made up of Drone Adventures, Skydio, Cyril Gliner an aerospace engineering student from London (Imperial College), and the team at Kuzikus Wildlife Reserve where we all met to undertake a research project for WildTrack and Kuzikus.
With great advancements in technology in the last two years the bar was set high: collect data that will be used to map-process-train AI to detect tracks not only of different animal species, but also between different individuals within the same species.
As a small side project, the entire 100sqkm of the reserve was mapped at 4cm resolution!
Here are some key mission numbers:
Project performed in: October/November 2020
Duration: 4 weeks
Total number of flights: 77
Flights per flying day: 5-6
Average flight time per flight: 55min
UAVs: 1 eBee X with cameras senseFly Aeria X and senseFly Duet T, 1 Anafi, 1 Skydio
Location and Conditions:
The Kuzikus Wildlife reserve is located on the western edge of the Kalahari Desert; hence the terrain is of type semi-arid Savanna. With the mission taking place mid-October into November, it was the end of the dry season and rain was expected soon.
Temperatures up to 35°C midday, strong winds carrying sand/dust and dry exposed sandy soil were a challenge for all the tech equipment.
Daily “blowouts” of laptops and drones with compressed air were a must to keep going. Working the latest senseFly fixed-wing eBee X that features an easily exchangeable pitot tube was a blessing.
Despite all material taking a good beating, everything lasted for the four weeks. Compliments to those companies senseFly, Parrot and Skydio for having such robust systems!
Mapping the Kuzikus Wildlife Reserve
Mapping 100sqkm at 4cm with a limited number of flight hours per day due to heat, and the need for shadows and wind, was a challenge, but feasible within the timeframe available. The processing of the data was done on site at Kuzikus using Pix4Ds React software.
The orthomosaics were then loaded into a QGIS project and tweaked for faster rendering when working with the data.
This dataset helps with the wildlife reserve management, to quantify different ground covers, classify vegetation, or even count plant species.
Other ideas like virtual tourism or printouts for self-organized exploring by Kuzikus visitors and more emerged of course as well.
The Tracking project
Identifying animal tracks gives information about the type of species, sometimes the health of the animal, the number of animals, and their behavioral patterns. This is nothing new to Namibian bushmen who would use their tracking skills to source food back in the old times.
Now the challenge of the project is to replicate the bushmen skills using drone imaging or videoing and AI.
We knew that training these AI algorithms requires a lot of data, but after one eBee flight collecting 800 images, no complaints were raised anymore concerning the data problem and the teams got to train the algorithm!
The focus was on identifying black rhino tracks. Black rhino live in the reserve as part of the Namibian black rhino custodian program. These rhinos are being monitored for health issues. …..
Therefore, the daily drill was: up early and check where a rhino was active during the night, a tricky task in a 100 sqkm reserve. Once tracks were found the drones would go into action and map the tracks to acquire training data. Then back to the farm, process or use the data directly to label and train the algorithm. Some promising results are emerging already, but more about these in a 2nd Part.
Many thanks to our project partner WildTrack!
This mission has been made possible with the generous support of our technology partners:
This mission is also part of the SAVMAP project, that had started in 2014. The project aims to find solutions using new technologies for sustainable land-use management and rare species conservation in semi-arid Savanna. The wildlife reserve Kuzikus is the research terrain used since the project start.
Author: Andrea Blindenbacher