SLEAP: A deep learning system for multi-animal pose tracking.

Pereira TD, Tabris N, Matsliah A, Turner DM, Li J, Ravindranath S, Papadoyannis ES, Normand E, Deutsch DS, Wang ZY, McKenzie-Smith GC, Mitelut CC, Castro MD, D'Uva J, Kislin M, Sanes DH, Kocher SD, Wang SS, Falkner AL, Shaevitz JW, Murthy M. · 2022

Read SLEAP: A deep learning system for multi-animal pose tracking. by Pereira TD, Tabris N, Matsliah A, Turner DM, Li J, Ravindranath S, Papadoyannis ES, Normand E, Deutsch DS, Wang ZY, McKenzie-Smith GC, Mitelut CC, Castro MD, D'Uva J, Kislin M, Sanes DH, Kocher SD, Wang SS, Falkner AL, Shaevitz JW, Murthy M. (2022) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc9007740.txt.

Description

Pereira and co-authors present SLEAP, a deep learning system that tracks poses of many animals at once. Social behavior science needs exact motion records. Single-animal tools fail when animals interact. SLEAP covers the full work path. It helps users label training frames. It trains models and runs them on new video. A friendly screen interface fronts the system. A standard data model sits under it. More than 30 model designs are built in.

Two ways to group body parts are offered. Two ways to track identity join them. The team tested SLEAP on seven datasets. Flies, bees, mice, and gerbils all featured. Accuracy beat rival systems in their tests. Speed topped 800 frames per second. Delay stayed low enough for live use. The authors prove that with a closed-loop demo. One animal's behavior was steered by tracking its partner. The system is open for labs to adopt.

Catalog record

CREATORPereira TD, Tabris N, Matsliah A, Turner DM, Li J, Ravindranath S, Papadoyannis ES, Normand E, Deutsch DS, Wang ZY, McKenzie-Smith GC, Mitelut CC, Castro MD, D'Uva J, Kislin M, Sanes DH, Kocher SD, Wang SS, Falkner AL, Shaevitz JW, Murthy M.
YEAR2022
COLLECTIONPAPERS
FORMATTXT
FILE SIZE117 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC9007740

Browse the full library · About the Tower of Babel