US 11,944,429 B2
Automatically classifying animal behavior
Sandeep Robert Datta, Cambridge, MA (US); Alexander B. Wiltschko, Cambridge, MA (US); and Matthew J. Johnson, Cambridge, MA (US)
Assigned to President and Fellows of Harvard College, Cambridge, MA (US)
Filed by President and Fellows of Harvard College, Cambridge, MA (US)
Filed on Mar. 8, 2023, as Appl. No. 18/180,677.
Application 18/180,677 is a continuation of application No. 17/241,863, filed on Apr. 27, 2021, granted, now 11,622,702.
Application 17/241,863 is a continuation of application No. 15/767,544, granted, now 11,020,025, previously published as PCT/US2016/056471, filed on Oct. 11, 2016.
Claims priority of provisional application 62/241,627, filed on Oct. 14, 2015.
Prior Publication US 2023/0225636 A1, Jul. 20, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 5/11 (2006.01); A61B 5/00 (2006.01); G06F 18/20 (2023.01); G06F 18/2135 (2023.01); G06T 7/20 (2017.01); G06V 10/147 (2022.01); G06V 10/77 (2022.01); G06V 10/84 (2022.01); G06V 40/20 (2022.01)
CPC A61B 5/1128 (2013.01) [A61B 5/00 (2013.01); A61B 5/1123 (2013.01); A61B 5/7267 (2013.01); G06F 18/2135 (2023.01); G06F 18/295 (2023.01); G06V 10/7715 (2022.01); G06V 10/85 (2022.01); G06V 40/20 (2022.01); A61B 2503/40 (2013.01); A61B 2503/42 (2013.01); A61B 2576/00 (2013.01); G06T 7/20 (2013.01); G06V 10/147 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for analyzing motion of a subject, the method comprising:
processing three-dimensional video image data frames representing the motion of the subject using a model-free algorithm to output a first and a second set of modules, wherein each module in the first set of modules exhibits pose dynamics for 200-900 milliseconds, and each module in the second set of modules exhibits pose dynamics for 200-900 milliseconds; and
identifying repeated modules of the subject's behavior using a template matching procedure for matching motifs of the subject's motion.