It feels like something straight out of “Minority Report” the movie – a computer searches the planet for ‘ grey elephants in green forest’ – and returns a positive result – ‘there’s a herd scattered at ### , ### coordinates’ . Yet it’s very real – and it’s helping to highlight the plight of these magnificent beasts, spread as they are the vast plains of Africa.
“Satellites allow large‐scale surveys to be conducted in short time periods with repeat surveys possible at intervals of <24 h. Very‐high‐resolution satellite imagery has been successfully used to detect and count a number of wildlife species in open, homogeneous landscapes and seascapes where target animals have a strong contrast with their environment. “ The study applied a Convolution Neural Network (CNN) model to automatically detect and count African elephants in a woodland savanna ecosystem in South Africa. Using WorldView‐3 and 4 satellite data –the highest resolution satellite imagery commercially available – performance accuracy of the CNN against human accuracy, had very high positive results.
*** Is the ideal next step – using this technology to locate ‘would-be poachers’ ?
Would that be a good thing , or creating a ‘Big Brother ‘ scenario where peoples privacy is more important than the lives of animals?
The research was conducted by ZSL – the Zoological Society.
“ Our results demonstrate, for the first time, that it is possible to automate detection of African elephants in very‐high‐resolution satellite imagery in both heterogeneous and homogeneous backgrounds using deep learning. We have automated the detection of elephants with as high accuracy as human detection capabilities. For a number of species remote sensing via satellite imagery is already a viable monitoring technique. However, the resolution required to identify individuals is not yet available for the vast majority of species … “
Previous studies have largely focused on marine species due both to their inaccessibility via other monitoring techniques and the high contrast of their bodies against mainly homogenous backgrounds
Why satellites? ..
“ The advantages of using satellite imagery are numerous. Large areas can be covered in one pass, reducing the risk of double counting and eliminating the need for repeat surveys at short intervals. Satellite monitoring is an unobtrusive technique requiring no ground presence, and thus eliminating the risk of disturbing species, or of concern for human safety during data collection. Previously inaccessible areas are rendered accessible, and cross‐border areas – often crucial to conservation planning ‐ can be surveyed without the often time‐consuming and bureaucratically problematic requirements of terrestrial permits. “
One challenge with satellite monitoring is the high cost of commercial satellite imagery. Worldview‐3 costs $17.50 per km2 for archive imagery and tasking new imagery costs $27.50 per km2, with a minimum order of 100 km2(2020 pricing). Another key challenge is processing the large quantity of imagery generated. However, expediting identification of species by automating detection can allow for large‐scale application of satellite‐based wildlife surveying (LaRue et al., 2015; Torney et al., 2019). A detection process that would formally have taken weeks can thus be completed in a matter of hours.
All of this bodes well for the study of elephants and their conservation – BBC featured the technology here