Title
Methods for Recognizing Pose and Action of Articulated Objects with Collection of Planes in Motion
Abstract
The invention comprises an improved system, method, and computer-readable instructions for recognizing pose and action of articulated objects with collection of planes in motion. The method starts with a video sequence and a database of reference sequences corresponding to different known actions. The method identifies the sequence from the reference sequences such that the subject in performs the closest action to that observed. The method compares actions by comparing pose transitions. The cross-homography invariant may be used for view-invariant recognition of human body pose transition and actions.
Document Type
Patent
Patent Number
US 8,755,569
Application Serial Number
12/790,083
Issue Date
6-17-2014
Current Assignee
UCFRF
Assignee at Issuance
UCFRF
College
College of Engineering and Computer Science (CECS)
Department
Electrical Engineering & Computer Science - CS Division
Allowance Date
2-5-2014
Filing Date
5-28-2010
Assignee at Filing
UCFRF
Filing Type
Nonprovisional Application Record
Donated
no
Recommended Citation
Foroosh, Hassan and Shen, Yuping, "Methods for Recognizing Pose and Action of Articulated Objects with Collection of Planes in Motion" (2014). UCF Patents. 377.
https://stars.library.ucf.edu/patents/377