Drones, automatic counting tools, and artificial neural networks in wildlife population censusing

Abstract

The use of a drone to count the flock sizes of 33 species of waterbirds during the breeding and non-breeding periods was investigated. In 96% of 343 cases, drone counting was successful. 18.8% of non-breeding birds and 3.6% of breeding birds exhibited adverse reactions: the former birds were flushed, whereas the latter attempted to attack the drone. The automatic counting of birds was best done with ImageJ/Fiji microbiology software – the average counting rate was 100 birds in 64 s. Machine learning using neural network algorithms proved to be an effective and quick way of counting birds – 100 birds in 7 s. However, the preparation of images and machine learning time is time-consuming, so this method is recommended only for large data sets and large bird assemblages. The responsible study of wildlife using a drone should only be carried out by persons experienced in the biology and behavior of the target animals.