Why anti-poaching drones haven't worked well

As an industry, we had high hopes for the use of drones in anti-poaching efforts. But in hot climates everything looks hot to airborne thermal cameras and fleet logistics are crippling. Dogs work much better. Here's a sobering report from the field:

I spent 2 years flying anti-poaching drones in the Kruger National Park and other reserves, clocking up hundreds of hours and Robert is right, everything is a trade-off unfortunately. And that’s only the start, there are so many difficulties in the actual operation, very few people have even the slightest idea of what it entails.

The design and building is really the easy part. So if that is hard then one is going to have a hell of a struggle on-site in the bush in 39°C heat (and that’s at 11pm at night!) not counting all the other challenges.

From my experience I believe, that even with the best intentions and best technology, drones will never have more than a negligible effect on poaching. To put it in context, the Canine teams in the KNP’s best haul was 18 poachers apprehended in one week. Our drone team saw less than 8 poachers in TWO years of night flying, with not one apprehension. So if the drone is not CATCHING an average of 2-5 poachers a WEEK then it’s of no use. And note that poachers get around deterrents easily.

In 1014, I did a stint in Honduras for anti poaching where similar heat at night was observed. The night time wind served no comfort at all! However the use of a Thermal camera acquired from China and mounted to a petrol powered Mugin 3m platform worked well but not exactly as intended! The task was for surveillance of SHRIMP farms where a estimated $6M of losses can be attributed to poaching. Some was done by trespassing and netting, other times by opening up the river side slues gates and netting them downstream. Then they would be sold at the local market. The shrimp farm operators know this because the shrimp are GM and have a tell tale signature but they couldn't prosecute. People were shot on occasion and retaliations etc ensued. Apart from the obvious hardships of temperatures, maintenance and threat to personal safety, the Mugin flew well with the APM 2.4! Initially we were spotting the odd security guard doing his patrols over the 4000ha even with the warm water contrast. But after a few days of showing our security detail what we looked like on the screen and letting them disseminate that info to the public (most probably relatives) , none of the GM shrimp from the farm made it to market. Apparently the Mugin 3 was still effective when we were just practicing with no payload. Whenever we weren't flying, occurrences of the GM shrimp made it to the market the next day. The project was a proof of concept and was finalized a month later. With todays sensors and color night vision capable cameras, i'm sure would be more effective in other areas of anti poaching, albeit as a deterrent.

You need to be a member of diydrones to add comments!

Join diydrones

Comments

Choppy January 30, 2023 at 11:09pm

In 1014, I did a stint in Honduras for anti poaching where similar heat at night was observed. The night time wind served no comfort at all! However the use of a Thermal camera acquired from China and mounted to a petrol powered Mugin 3m platform worked well but not exactly as intended! The task was for surveillance of SHRIMP farms where a estimated $6M of losses can be attributed to poaching. Some was done by trespassing and netting, other times by opening up the river side slues gates and netting them downstream. Then they would be sold at the local market. The shrimp farm operators know this because the shrimp are GM and have a tell tale signature but they couldn't prosecute. People were shot on occasion and retaliations etc ensued. Apart from the obvious hardships of temperatures, maintenance and threat to personal safety, the Mugin flew well with the APM 2.4! Initially we were spotting the odd security guard doing his patrols over the 4000ha even with the warm water contrast. But after a few days of showing our security detail what we looked like on the screen and letting them disseminate that info to the public (most probably relatives) , none of the GM shrimp from the farm made it to market. Apparently the Mugin 3 was still effective when we were just practicing with no payload. Whenever we weren't flying, occurrences of the GM shrimp made it to the market the next day. The project was a proof of concept and was finalized a month later. With todays sensors and color night vision capable cameras, i'm sure would be more effective in other areas of anti poaching, albeit as a deterrent.
Pascal Fust April 6, 2019 at 1:17am

Somehow correct. Hyperspectral technology provides many advantages, though it is prone to challenges when it comes to wavelengths in the visual range due to colour variations.
Developer

John Arne Birkeland April 5, 2019 at 3:03pm

My first thought was maybe some variation of a hyperspectral camera?
Pascal Fust March 29, 2019 at 1:22am

Hi Chris, thanks for raising attention to the project.

As I'm currently working on comparable topics (detecting diurnal mammals instead of humans) in the same climatic environment, I am most interested in any investigation of the applicability and reliability of UAV-based remote sensing technology.

As I've stated in my blog entry of the project mentioned above, I am puzzled about the "stubbornness" of researchers/developers to rely on thermal imagery in tropical climate. As John already indicated will further development of imagery sensors based on emitted temperature barely be able to enhance detectibility, due to the lack of contrast. Therefore, our research investigates the application of alternative features of light and vision in biodiversity conservation.
Developer

John Arne Birkeland March 24, 2019 at 11:48am

1. When the human body and the ambient temperature are almost the same, a better TI camera with better sensitivity/resolution will only help marginally. The increased sensitivity will also lead to more false positives.

2. When/if a drone is able to detect a poacher 10 Km away in the jungle, it's not really all that helpful. Most likely he will be long gone by the time you are able to reach the location. And tracking the poacher until you catch up with him, would require many hours of flight time and not loosing the target either on foot or in a vehicle.
Ravi March 17, 2019 at 7:03am

One should not give up so easily. eventually better TI cameras will appear in market.

Remember drones can go 10Km in the jungle. Imagine travelling 10km in jungle over foot or by a SUV.

electric drones are easy to operate and have very low maintenances. much lower than a 4WD SUV.

operating cost is minimal because of less mechanical parts.

anything that can FLY autonomously has to have a special use. it's just our imagination which is blocked.

audible level is very low for electric drones.

TI cameras will evolve eventually.
Mateusz Sadowski March 12, 2019 at 3:53am

Thanks for the great insights Chris! Although the forum is not the format I would usually link to at WeeklyRobotics the discussion is so eye opening that I'll most probably make an exception.
3D Robotics

Chris Anderson March 9, 2019 at 7:24pm

Thanks for the catch. Link fixed
Rana March 9, 2019 at 4:56pm

Hello Mr. Anderson !

The Link is not working.

This reply was deleted.