Communications of the ACM
How Footprint Recognition Software May Help Zoology
Key elements uniquely identifying a footprint are marked on an image, as shown here with an Amur tiger print, prior to algorithmic classification.
Credit: Jiayin Gu
WildTrack provides a low-cost and noninvasive way to track animals. The organization has developed image-processing software that detects physical footprint characteristics that are hard for an untrained eye to recognize.
The method, called footprint identification technique (FIT), relies on professional trackers to photograph footprints with a ruler for scale, and add global positioning system coordinates. The footprints are loaded into software that enables WildTrack to match them to a large number of known footprints from captive animals of the same species. Algorithms are then used to compare elements of the photographed footprint against those in a database of animals whose age and gender are known.
FIT has a 90-percent accuracy rate in correctly determining the sex, age, and species, but it does not work well with all animals and remains in an experimental stage.
WildTrack has been developing the software over the past decade, and it is being used to track tigers in Russia, tapirs in South America, and polar bears in Canada.
From Technology Review
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found