Apparatus and method for classifying orientation of a body of a mammal
Inventors
Umer, Muhammad • Ronchi, Andrew James • Ronchi, Daniel Matthew
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10126108-B2
Publication Date
2018-11-13
Expiration Date
Abstract
Apparatus is disclosed for providing classification of body orientation of a mammal. The apparatus includes means (10, 11) for measuring position of said body relative to a frame of reference at one or more points on the body, wherein said means for measuring includes at least one position sensor. The apparatus includes means (12) for providing first data indicative of said position; means (15) for storing said data at least temporarily; and means (13, 14) for processing said data to provide said classification of body orientation. A method for providing classification of body orientation of a mammal is also disclosed.
Core Innovation
The invention provides an apparatus and a method for providing a classification of body orientation of a mammal in static and/or dynamic states. Body position is measured relative to a frame of reference using two position sensors located on an upper body of the mammal, and first data indicative of said body position are stored at least temporarily in a memory device. A processor receives the first data and processes the first data to provide the classification of body orientation in said static and/or dynamic states.
The processor implements a Body Orientation Classification (BOC) algorithm for evaluating said body orientation. The BOC algorithm includes a dynamic classifier configured to identify dynamic movement based on identification of a cyclic pattern in the first data received from the two position sensors. The BOC algorithm also includes a static classifier configured to identify posture based on the first data received from the two position sensors mapping to predetermined values.
A transition classifier is configured to identify a pattern of transition in response to a changing state as identified by the static classifier and based on the first data received from the two position sensors. The transition detection is based on a moving window of position values in real time correlating to predefined statistics from observed data, wherein the correlation serves as a confirmation or refutation of the changing state. The BOC algorithm updates the predefined statistics based on the first data for subsequent classification of subsequent body position data in a feedback loop and outputs a status of the changing state.
Claims Coverage
The partial content identifies two independent claims, apparatus and method, each centered on a Body Orientation Classification (BOC) algorithm with dynamic, static, and transition classification, feedback-loop updating, and output of changing-state status.
BOC algorithm with dynamic cyclic-pattern classification, static posture mapping, and transition confirmation/refutation
The processor or method processor executes a BOC algorithm including a dynamic classifier configured to identify dynamic movement based on a cyclic pattern in the first data; a static classifier configured to identify posture based on the first data mapping to predetermined values; and a transition classifier configured to identify a pattern of transition in response to a changing state as identified by the static classifier and based on a moving window of position values in real time correlating to predefined statistics from observed data, wherein the correlation serves as a confirmation or refutation of the changing state.
Feedback-loop updating of predefined statistics and output of changing-state status
The BOC algorithm updates the predefined statistics based on the first data for subsequent classification of subsequent body position data in a feedback loop, and outputs a status of the changing state.
Two upper-body position sensors measuring body position relative to a frame of reference for static and/or dynamic classification
An apparatus or method includes two position sensors located on an upper body of the mammal to measure body position relative to a frame of reference and provide first data indicative of said body position; a memory device storing said first data at least temporarily; and a processor to receive the first data and process the first data to provide the classification of body orientation in static and/or dynamic states.
Across the independent claims, the core claim coverage is body orientation classification of a mammal in static and/or dynamic states from two upper-body position sensors using a BOC algorithm with dynamic cyclic-pattern detection, static posture mapping, and transition detection via a real-time moving window correlated to predefined statistics, with feedback-loop updates and output of changing-state status.
Stated Advantages
Provides classification of body orientation of a mammal in static and/or dynamic states.
Provides confirmation or refutation of a changing state via correlation to predefined statistics.
Updates predefined statistics in a feedback loop for subsequent classification.
Outputs a status of the changing state.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?