Dual descriptor data for object recognition in low light conditions

US12260610B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-12260610-B2
Application numberUS-202318123439-A
CountryUS
Kind codeB2
Filing dateMar 20, 2023
Priority dateMar 24, 2022
Publication dateMar 25, 2025
Grant dateMar 25, 2025

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using dual descriptor data. One of the methods includes: detecting, using a first set of descriptor features included in dual descriptor data, a first representation within first image data collected by a camera; determining a change to an imaging modality of the camera; detecting, using a second set of features included in the dual descriptor data, a second representation within second image data collected by the camera; classifying the first representation and the second representation as associated with a same object using the dual descriptor data; and in response to classifying the first representation and the second representation as associated with the same object using the dual descriptor data, transmitting operational instructions to one or more appliances connected to the system.

First claim

Opening claim text (preview).

What is claimed is: 1. A system comprising one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising: generating dual descriptor data, which comprises: determining a first bounding box in first image data collected by a camera, determining a second bounding box in second image data collected by the camera, determining an overlapping region between the first bounding box and the second bounding box, and generating the dual descriptor data for an object associated with the overlapping region; detecting, using a first set of descriptor features included in the dual descriptor data, a first representation within first image data collected by the camera with a first imaging modality; determining a change to an imaging modality of the camera from the first imaging modality to a second imaging modality; detecting, using a second, different set of features included in the dual descriptor data, a second representation within second image data collected by the camera with the second imaging modality; classifying the first representation and the second representation as associated with a same object using the dual descriptor data; and in response to classifying the first representation and the second representation as associated with the same object using the dual descriptor data, transmitting operational instructions to one or more appliances connected to the system. 2. The system of claim 1 , wherein the camera comprises an RGB sensor and an IR sensor, the change to the imaging modality of the camera comprises a change in using the IR sensor to the RGB sensor or in using an RGB sensor to an IR sensor. 3. The system of claim 1 , wherein the operations further comprise detecting, by the camera, a change in lighting conditions; and wherein determining the change to the imaging modality of the camera is in response to detecting the change in the lighting conditions. 4. The system of claim 1 , wherein the classifying of the first representation and the second representation as associated with the same object using the dual descriptor data comprises determining that object features of the same object satisfy a threshold for resembling object features used in generating the dual descriptor data. 5. The system of claim 1 , wherein the first representation has a first location in the first image data, and the second representation has a second location in the second image data, and the first and second locations (i) are different and (ii) indicate movement. 6. The system of claim 1 , wherein the classifying of the first representation and the second representation as associated with the same object using the dual descriptor data uses a time period between capturing the first and second image data. 7. The system of claim 1 , wherein the operations further comprise providing, to a user device, a notification asking for confirmation that the first representation and the second representation are associated with the same object. 8. The system of claim 7 , wherein the operations further comprise receiving, from the user device, feedback indicating that the first representation and the second representation are associated with the same object. 9. The system of claim 1 , wherein the detecting, using the second set of features specified in the dual descriptor data, of the second representation within second image data comprises: determining that a descriptor template is not specified for the second image data; in response to determining that a descriptor template is not specified for the second image data, initiate a bounding box registration process, thereby generating a new descriptor template; and updating the dual descriptor data with the new descriptor template. 10. The system of claim 1 , wherein the dual descriptor data for the object comprises object attributes in different imaging modalities with the object. 11. The system of claim 1 , wherein: the operations further comprise determining that the object is unrecognized to the system; and the determining of the first bounding box in the first image data is in response to determining that the object is unrecognized. 12. The system of claim 1 , wherein the operations further comprise providing, to a user device, a notification asking for confirmation that a representation within the first bounding box and a representation within the second bounding box correspond to a same object. 13. The system of claim 12 , wherein the operations further comprise receiving, from the user device, feedback indicating that a representation within the first bounding box and a representation within the second bounding box correspond to a same object. 14. The system of claim 1 , wherein the operations further comprise: determining that the object is recognized to the system; comparing the generated dual descriptor data for the object with a feature template of the dual descriptor data; and updating the feature template of the dual descriptor data with the generated dual descriptor data. 15. A non-transitory computer storage medium encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising: generating dual descriptor data, which comprises: determining a first bounding box in first image data collected by a camera, determining a second bounding box in second image data collected by the camera, determining an overlapping region between the first bounding box and the second bounding box, and generating the dual descriptor data for an object associated with the overlapping region; detecting, using a first set of descriptor features specified in the dual descriptor data, a first representation within first image data collected by the camera with a first imaging modality; determining a change to an operating mode of the camera from the first imaging modality to a second imaging modality; detecting, using a second, different set of features specified in the dual descriptor data, a second representation within second image data collected by the camera with the second imaging modality; classifying the first representation and the second representation as associated with a same object using the dual descriptor data; and in response to classifying the first representation and the second representation as associated with the same object using the dual descriptor data, sending operational instructions to one or more appliances. 16. The computer storage medium of claim 15 , wherein the camera comprises an RGB sensor and an IR sensor, the change to the operating mode of the camera comprises a change in using the IR sensor to the RGB sensor or in using an RGB sensor to an IR sensor. 17. The computer storage medium of claim 16 , wherein the operations further comprise detecting, by the camera, a change in lighting conditions; and wherein determining the change to the operating mode of the camera is in response to detecting the change in the lighting conditions. 18. The computer storage medium of claim 15 , wherein the dual descriptor data for the object comprises object attributes in different imaging modalities with the object. 19. The computer storage medium of claim 15 , wherein the classifying of the first representation and the second representation as associated with the same object using the dual descriptor data comprises determining that object features of the sam

Assignees

Inventors

Classifications

  • Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

  • Surveillance · CPC title

  • Infrared image · CPC title

  • Color image · CPC title

  • involving reference images or patches · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US12260610B2 cover?
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using dual descriptor data. One of the methods includes: detecting, using a first set of descriptor features included in dual descriptor data, a first representation within first image data collected by a camera; determining a change to an imaging modality of the camera; detecting, using a second…
Who is the assignee on this patent?
Objectvideo Labs Llc
What technology area does this patent fall under?
Primary CPC classification H04N23/11. Mapped technology areas include Electricity.
When was this patent published?
Publication date Tue Mar 25 2025 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 12 related publications on this page (citations in our corpus or others sharing the same primary CPC).