Learning apparatus, estimation apparatus, learning method, and non-transitory storage medium
US-2024428667-A1 · Dec 26, 2024 · US
US9432639B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9432639-B2 |
| Application number | US-95009510-A |
| Country | US |
| Kind code | B2 |
| Filing date | Nov 19, 2010 |
| Priority date | Nov 19, 2010 |
| Publication date | Aug 30, 2016 |
| Grant date | Aug 30, 2016 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method and apparatus for operating a security system are provided. The method includes the steps of the security system monitoring a secured area, a video camera obtaining images of the secured area, detecting at least one person within the obtained images and identifying a predetermined context associated with the identified at least one person within the obtained images.
Opening claim text (preview).
The invention claimed is: 1. A method comprising: a security system monitoring a secured area; a video camera obtaining images of the secured area; detecting at least one authorized person and at least one other person within the obtained images; analyzing video frames of the obtained images for specific contexts involving the detected at least one authorized person or at least one other person that require further action, wherein the analyzing does not operate by detecting locomotion or movement of humans across one of the obtained images and, instead, the analyzing operates to detect specific acts performed by or a specific condition of the detected at least one authorized person or at least one other person; and identifying a predetermined context associated with the detected at least one authorized person or at least one other person within the analyzed video frames requiring further action of the obtained images. 2. The method as in claim 1 wherein the step of identifying the predetermined context further comprises detecting a hand gesture. 3. The method as in claim 1 wherein the step of identifying the predetermined context further comprises detecting a predetermined interaction between the detected at least one authorized person and at least one other person within the obtained images. 4. The method as in claim 3 further comprising defining the predetermined interaction as a display of a weapon by one of the detected at least one authorized person and at least one other person. 5. The method as in claim 3 further comprising defining the predetermined interaction as a fight between the detected at least one authorized person and at least one other person. 6. The method as in claim 1 wherein the step of identifying the predefined context further comprises measuring a biometric parameter of the detected at least one authorized person. 7. The method as in claim 6 wherein the biometric parameter further comprises a heat signature of the identified-detected at least one authorized person. 8. The method as in claim 1 further comprising triggering a silent alarm of the security system upon identifying the predetermined context. 9. The method as in claim 1 further comprising providing an audio status report of the security system to the detected at least one authorized person upon identifying the predetermined context. 10. An apparatus comprising: means for monitoring a secured area; means for obtaining a sequence of images of the secured area; means for identifying at least one authorized person and at least one other person within the obtained sequence of images; a context detection processor that analyzes video frames of the obtained sequence of images for specific contexts involving the identified at least one authorized person or at least one other person that require, further action, wherein the context detection processor does not operate by detecting locomotion or movement of humans across one of the obtained sequence of images and, instead, the context detection processor operates to detect specific acts performed by or a specific condition of the identified at least one authorized person or at least one other person; and means for detecting a predetermined action performed by or associated with the identified at least one authorized person or at least one other person within the analyzed video frames requiring further action of the obtained sequence of images. 11. The apparatus as in claim 10 wherein the predetermined action further comprises a display of a weapon by one of the identified at least one authorized person and at least one other person. 12. The apparatus as in claim 10 wherein the predetermined action further comprises a fight between the identified at least one authorized person and at least one other person. 13. The apparatus as in claim 10 wherein the predetermined action further comprises a measured biometric parameter of the identified at least one authorized person. 14. The apparatus as in claim 13 wherein the biometric parameter further comprises a heat signature of the identified at least one authorized person. 15. An apparatus comprising: a security system that monitors a secured area; a video camera that obtains images proximate the secured area; a programmed processor that identifies at least one authorized person and at least one other person within the obtained images; a context detection processor that analyzes video frames of the obtained images for specific contexts involving the identified at least one authorized person or at least one other person that require further action, wherein the context detection processor does not operate by detecting locomotion or movement of humans across one of the obtained images and, instead, the context detection processor operates to detect specific acts performed by or a specific condition of the identified at least one authorized person or at least one other person; a programmed processor that detects a predetermined context associated with the identified at least one authorized person or at least one other person within the analyzed video frames requiring further action of the obtained images; and a programmed processor that performs a predefined action in response to the detected predetermined context. 16. The apparatus as in claim 15 wherein the predetermined context further comprises a hand gesture. 17. The apparatus as in claim 16 further comprising a programmed processor that sends an alarm message to a central monitoring station in response to the predetermined context. 18. The apparatus as in claim 15 further comprising a programmed processor that provides an audio status report of the security system to the identified at least one authorized person upon detecting the predetermined context.
Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion · CPC title
Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position (signal generation from motion picture films H04N5/253) · CPC title
Recognition of static hand signs · CPC title
Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title
Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.