Improved System For Recognition Of Human Actions
- Technology Benefits
- Observations are not limited to an environment that has been instrumented with cameras and other sensors --this enables continuous monitoring in natural environments (i.e. homes)Readily scalable approach thereby enabling the monitoring of increasingly smaller body movementsPower consumption is lower than comparable alternativesClassification of human actions are more robust and flexible
- Technology Application
- Medical care, for example quantitative study of treatment of Duchenne Muscular DystrophyAssisted living care, for example remote monitoring of elderly peopleAthletic training and fitness programs
- Detailed Technology Description
- None
- Supplementary Information
- Patent Number: US20100176952A1
Application Number: US2009631714A
Inventor: Bajcsy, Ruzena | Yang, Allen Y. | Sastry, S. Shankar | Jafari, Roozbeh
Priority Date: 4 Dec 2008
Priority Number: US20100176952A1
Application Date: 4 Dec 2009
Publication Date: 15 Jul 2010
IPC Current: G08B002300
US Class: 3405731
Assignee Applicant: The Regents of the University of California
Title: SYSTEM FOR DETECTION OF BODY MOTION
Usefulness: SYSTEM FOR DETECTION OF BODY MOTION
Summary: Method for obtaining data in a distributed sensor system that is used with a cell phone e.g. Apple iPhone (RTM: Internet-enabled multimedia mobile phone), Google gPhone (RTM: flagship smartphone), Nokia N800/900 (RTM: mobile computer with smartphone functions), personal digital assistant (PDA) and personal navigation device, for detecting action of a human body. Uses include but are not limited to monitor activities of elderly people, disabled people and chronically ill people in nursing homes and hospitals, hospital emergency room monitoring for nursing coverage, diagnosis of diseases e.g. Parkinson's disease, monitoring prisoners or solders, athletic training, monitoring patients in clinical drug studies, monitoring animal activities and machine monitoring.
Novelty: Data obtaining method for distributed sensor system for use with e.g. flagship smartphone for detecting human body action for e.g. diagnosis of Parkinson's disease, involves using local process to perform portion of data classification
- Industry
- Electronics
- Sub Category
- 3C/Gadgets
- Application No.
- 9060714
- Others
-
Tech ID/UC Case
17943/2008-082-0
Related Cases
2008-082-0
- *Abstract
-
Computer-based recognition of human physical actions is gaining attention in fields such as medical care, tele-immersion and athletic training. Most conventional approaches to computer-based recognition of human actions are based on computer vision systems along with model-based or appearance-based vision algorithms. However, these conventional approaches have limitations including the requirement for human subjects to be observed in a finite environment that is instrumented with cameras and other sensors -- and those instruments can't analyze very small body movements.
To address this problem, researchers at UC Berkeley have developed a distributed recognition framework to segment and classify human actions that was inspired by emerging compression sensing theory.
- *IP Issue Date
- Jun 23, 2015
- *Principal Investigator
-
Name: Ruzena Bajcsy
Department:
Name: Roozbeh Jafari
Department:
Name: Sosale Sastry
Department:
Name: Allen Yang
Department:
- Country/Region
- USA
