Database comparison operation to identify an object

Patent metadata

Field	Value
Publication number	US-10956493-B2
Application number	US-201515570878-A
Country	US
Kind code	B2
Filing date	May 19, 2015
Priority date	May 19, 2015
Publication date	Mar 23, 2021
Grant date	Mar 23, 2021

Abstract

Examples disclosed herein relate to a database comparison operation to identify an object. For example, a processor may enroll a set of object templates in a storage based on objects within input content and enroll a target object template in the storage based on a target object in target content. The processor may identify an object within the input content associated with the target object based on a database comparison operation of the stored set of object templates to the stored target object template. The processor may output object recognition information related to the identified object.

First claim

The invention claimed is:

1. A database system, comprising:
a hardware processor, a memory, and a database,
wherein the memory stores instructions that when executed cause the hardware processor to:
create sets of first object template information based on at least one of image information and video information;
store the sets of first object template information in the database;
create target object template information associated with a target object in at least one of an input image and an input video;
store the target object template information in the database;
respond to a query corresponding to a database comparison operation to identify a second object associated with the target object, wherein the database comparison operation corresponds to parallel search capabilities of the database to cause the hardware processor to simultaneously compare the sets of first object template information to the target object template information to identify the second object, and wherein the sets of first object template information comprise a first set of first object template information containing data representing features of a first person and a second set of first object template information containing data representing features of a second person other than the first person; and
output object recognition information related to the second object.

2. The database system of claim 1 , wherein the sets of first object template information comprise at least one of a file name, tracker number, video frame number, object bounding box coordinates, face bounding box coordinates, and object feature template information.

3. The database system of claim 1 , wherein the database stores information linking a given set of first object template information of the sets of first object template information to additional information related to the second object.

4. The database system of claim 3 , wherein the additional information is related to information associated with the at least one of the image information and the video information.

5. The database system of claim 1 , wherein the database comprises a relational database.

6. The database system of claim 1 , wherein the hardware processor executes multiple user defined database functions in parallel to perform the simultaneous comparison.

7. The database system of claim 1 , wherein the hardware processor executes a user defined database function corresponding to multiple parallel searches to perform the simultaneous comparison.

8. A method, comprising:
storing a set of first object templates in a database based on a plurality of objects within an input content, wherein the set of first object templates comprises a first object template containing data representing features of a first person and a second object template containing data representing features of a second person different from the first person;
storing a target object template in the database based on a target object in a target content;
responding to a query corresponding to a database comparison operation to identify a second object associated with the target object, wherein the database comparison operation corresponds to parallel search capabilities of the database to simultaneously compare the set of first object templates to the target object template to identify the second object in the input content; and
outputting object recognition information related to the second object in the input content.

9. The method of claim 8 , further comprising comparing a subset of first object templates of the set of first object templates to other object templates during an enrollment process.

10. The method of claim 8 , wherein the input content includes a video content and wherein a first object template of the set of first object templates is associated with a set of adjacent video frames including an object appearing in all video frames of the set of adjacent video frames.

11. The method of claim 8 , wherein the simultaneous comparison comprises executing multiple user defined database functions in parallel.

12. The method of claim 8 , wherein the simultaneous comparison comprises executing a user defined database function associated with parallel database searching.

13. A machine-readable non-transitory storage medium storing instructions that, when executed by a processor, cause the processor to:
store a set of first object templates in a database based on a plurality of objects within an input content;
storing a target object template in the database based on a target object in a target content;
respond to a query corresponding to a database comparison operation to identify a second object associated with the target object, wherein the database comparison operation corresponds to parallel search capabilities of the database to cause the database to simultaneously compare the set of first object templates to the target object template to identify the second object in the input content, wherein the set of first object templates comprise a first stored object template containing data representing features of a first person and a second stored object template containing data representing features of a second person other than the first person; and
output information related to the second object based on a result of the query.

14. The machine-readable non-transitory storage medium of claim 13 , wherein the set of first object templates comprises stored feature information related to both images and videos.

15. The machine-readable non-transitory storage medium of claim 13 , wherein the output information is associated with a surveillance application for person identification.

16. The machine-readable non-transitory storage medium of claim 13 , wherein the database comprises a relational database.

17. The machine-readable non-transitory storage medium of claim 13 , wherein the query invokes a user defined function to cause the database to perform parallel searching.

18. The machine-readable non-transitory storage medium of claim 13 , wherein the query invokes a parallel execution by the database of multiple user defined functions to cause the database to perform the simultaneous comparison.

Assignees

• Entit Software Llc
• Micro Focus Llc

Inventors

• Lin Qian
• Hsu Meichun
• Chen Qiming

Classifications

• G06F16/5854 Primary

  using shape and object relationship · CPC title

• G06F16/783

  using metadata automatically derived from the content · CPC title

• G06F16/7867

  using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings · CPC title

• G06F16/71

  Indexing; Data structures therefor; Storage structures · CPC title

• G06F16/738

  Presentation of query results · CPC title