Surveillance system and method for predicting patient falls using motion feature patterns
First Claim
1. A surveillance system for detecting a fall risk condition, the system comprising:
- a storage device that stores motion feature patterns that are extracted from video recordings of patient activities, the motion feature patterns each being representative of motion associated with a risk event or a non-risk event based on a centroid of motion corresponding to movement proximate to a fall risk area; and
at least one server comprising;
a classifier component that generates a fall alert by analyzing a plurality of frames generated by a surveillance camera, andan alarm verifier thatdetermines a centroid of motion of one or more frames from the plurality of frames that correspond to the fall alert,compares the centroid of motion of the one or more frames with the motion feature patterns, anddetermines whether to confirm the fall alert based on the comparison.
0 Assignments
0 Petitions
Accused Products
Abstract
A method and system for detecting a fall risk condition, the system comprising a surveillance camera configured to generate a plurality of frames showing an area in which a patient at risk of falling is being monitored, and a computer system comprising memory and logic circuitry configured to store motion feature patterns that are extracted from video recordings, the motion feature patterns are representative of motion associated with real alarm cases and false-alarm cases of fall events, receive a fall alert from a classifier, determine motion features of one or more frames from the plurality of frames that correspond to the fall alert; compare the motion features of the one or more frames with the motion feature patterns, and determine whether to confirm the fall alert based on the comparison.
-
Citations
20 Claims
-
1. A surveillance system for detecting a fall risk condition, the system comprising:
-
a storage device that stores motion feature patterns that are extracted from video recordings of patient activities, the motion feature patterns each being representative of motion associated with a risk event or a non-risk event based on a centroid of motion corresponding to movement proximate to a fall risk area; and at least one server comprising; a classifier component that generates a fall alert by analyzing a plurality of frames generated by a surveillance camera, and an alarm verifier that determines a centroid of motion of one or more frames from the plurality of frames that correspond to the fall alert, compares the centroid of motion of the one or more frames with the motion feature patterns, and determines whether to confirm the fall alert based on the comparison. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A method for predicting a condition of elevated risk of a fall with a computer system comprising:
-
storing motion feature patterns that are extracted from video recordings of patient activities, the motion feature patterns each being representative of motion associated with a risk event or a non-risk event based on a centroid of motion corresponding to movement proximate to a fall risk area; generating a fall alert by analyzing a plurality of frames generated by surveillance camera; determining centroid of motion of one or more frames from the plurality of frames that correspond to the fall alert; comparing the centroid of motion of the one or more frames with the motion feature patterns; and determining whether to confirm the fall alert based on the comparison. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19, 20)
-
Specification