New Paper on Poacher Detection with Drones

Leonard Hambrecht led a new paper on detecting poachers with drones carrying a thermal imaging camera.

The paper titled “Detecting ‘poachers’ with drones: Factors influencing the probability of detection with TIR and RGB imaging in miombo woodlands, Tanzania” can be dowloaded until April 21st 2019 from here: Drones detecting Poachers April 2019.

Here’s the abstract:

Conservation biologists increasingly employ drones to reduce poaching of animals.

However, there are no published studies on the probability of detecting poachers and the factors influencing detection. In an experimental setting with voluntary subjects, we evaluated the influence of various factors on poacher detection probability: camera (visual spectrum: RGB and thermal infrared: TIR), density of canopy cover, subject distance from the image centreline, subject contrast against the background, altitude of the drone and image analyst. We manually analysed the footage and marked all recorded subject detections. A multilevel model was used to analyse the TIR image data and a general linear model approach was used for the RGB image data.

We found that the TIR camera had a higher detection probability than the RGB camera. Detection probability in TIR images was significantly influenced by canopy density, subject distance from the centreline and the analyst. Detection probability in RGB images was significantly influenced by canopy density, subject contrast against the background, altitude and the analyst. Overall, our findings indicate that TIR cameras improve human detection, particularly at cooler times of the day, but this is significantly hampered by thick vegetation cover. The effects of diminished detection with increased distance from the image centreline can be improved by increasing the overlap between images although this requires more flights over a specific area. Analyst experience also contributed to increased detection probability, but this might cease being a problem following the development of automated detection using machine learning.