Method and apparatus for detecting stereotyped behavior to support diagnosis of Autism Spectrum Disorder
AssigneeElectronics and Telecommunications Research Insitute
InventorsCheol-Hwan Yoo, Moon-Ki Back, Jang-Hee Yoo, Byung-Ok Han
Life of this patent
Estimating the term…
Abstract
Disclosed herein is a method for stereotyped behavior detection for supporting diagnosis of Autism Spectrum Disorder (ASD). The method includes detecting a target object to be assessed in an input video, detecting a section in which a periodic behavior occurs using an image sequence of the target object, and classifying a stereotyped behavior in the section in which the periodic behavior occurs.
Claims16
A method for stereotyped behavior detection for supporting diagnosis of Autism Spectrum Disorder (ASD), comprising:
- detecting a target object to be assessed in an input video;
- detecting a section in which a periodic behavior occurs using an image sequence of the target object;
- and
- classifying a stereotyped behavior in the section in which the periodic behavior occurs,
- wherein detecting the section in which the periodic behavior occurs includes:
- detecting a periodic behavior based on first dense sampling for the input video;
- and
- detecting a periodic behavior based on second dense sampling having a sampling stride that differs from that of the first dense sampling.
An apparatus for stereotyped behavior detection for supporting diagnosis of Autism Spectrum Disorder (ASD), comprising:
- a memory storing instructions;
- and
- one or more processors configured to execute the instructions to:
- detect a target object to be assessed in an input video;
- detect a section in which a periodic behavior occurs using an image sequence of the target object;
- and
- classify a stereotyped behavior in the section in which the periodic behavior occurs,
- wherein the one or more processors are configured to detect a periodic behavior based on first dense sampling for the input video and detect a periodic behavior based on second dense sampling having a sampling stride that differs from that of the first dense sampling.
Dependencies are inferred from the claim text.