idTracker: tracking individuals in a group by automatic identification of unmarked animals

The transformation of individual animal images acquired from videos into unique reference fingerprints allows for robust tracking of individuals in groups and reidentification of individuals between sightings and across different videos. Animals in groups touch each other, move in paths that cross, and interact in complex ways. Current video tracking methods sometimes switch identities of unmarked individuals during these interactions. These errors propagate and result in random assignments after a few minutes unless manually corrected. We present idTracker, a multitracking algorithm that extracts a characteristic fingerprint from each animal in a video recording of a group. It then uses these fingerprints to identify every individual throughout the video. Tracking by identification prevents propagation of errors, and the correct identities can be maintained indefinitely. idTracker distinguishes animals even when humans cannot, such as for size-matched siblings, and reidentifies animals after they temporarily disappear from view or across different videos. It is robust, easy to use and general. We tested it on fish ( Danio rerio and Oryzias latipes ), flies ( Drosophila melanogaster ), ants ( Messor structor ) and mice ( Mus musculus ).