Researchers from the Spanish National Research Council have developed the software to better track animals on videos.
It is easy to follow the route traced by an animal by using video recordings of the animal. The problem arises when the behaviour of two or more individuals is studied, as animals often cross or interact with other members of the group and wrong assignments of identity for each animal occur.

These faults make virtually impossible to identify an individual after several minutes of video, researchers said.

The new software, called idTracker, is based on the discovery of some algorithms that enable the identification of each individual, therefore allowing their tracking within the group.
The image of the individual, with its unique features, becomes the particular "footprint" of each animal, which allows tracking it although the human visual system cannot.

Even if they hide or temporarily disappear from the scene, these are recognized by the programme when they enter the scene again.
"From now on, we will be able to quantitatively determine the rules of animal behaviour in groups taking into account the individuality of each animal," said Gonzalo G de Polavieja, CSIC researcher and head of the study.

The software identification system first performs a search of the specimens when they are separated and can be differentiated. Since then, the programme identifies and recognizes its image in every frame of the video.
The identification is automatically done by extracting the 'footprint' of each animal. Thus, the routes that each of them took can be determined.

"Furthermore, it is possible to study the same individual in several videos because its 'footprint' is always the same. This enables a better understanding of their behaviour," Polavieja said.
Researchers claim that id Tracker is a very easy to use software that can be used with a variety of different species.

"We have done tests with fish (Danio rerio and Oryzias latipes), flies (Drosophila melanogaster), ants (Messor
structor) and mice (Mus musculus), but it can be applied to other animals," researchers said.

Among the applications of this software, Alfonso Perez Escudero, CSIC researcher noted that "in the short term, this will be used in science, but in the longer term, the method we have developed can be applied to recognize people in large crowds, vehicles or parts in a factory, for instance."
The study was published in the journal Nature Methods.


Latest News from Lifestyle News Desk