Video search device, data storage method and data storage device

Patent metadata

Field	Value
Publication number	US-2025355933-A1
Application number	US-202519247174-A
Country	US
Kind code	A1
Filing date	Jun 24, 2025
Priority date	Nov 23, 2016
Publication date	Nov 20, 2025
Grant date	—

Abstract

Disclosed herein is a video search device comprising: at least one processor configured to implement an updating unit generating event object information based on feature information on an object detected in a video; and a storage configured to store comparison object information containing feature information on a reference object, wherein the processor is further configured to implement: an object information generating/deleting unit configured to create information on an object having a predetermined degree of similarity between the event object information and the comparison object information as final object information, and storing the final object information in the storage; and a data searching unit searching the final object information for data that satisfies a search criterion entered by a user.

First claim

What is claimed is:

1 . A video search device comprising:
a processor; and a memory for storing program instructions to be executed by the processor, the processor, when executing the instructions, is configured to: generate event object information by extracting feature information of at least one object; generate final object information from the event object information based on the feature information of the at least one object having a predetermined degree of similarity with comparison object information; store the final object information in a storage; and search the final object information stored on the storage for data that satisfies a search criterion entered by a user, wherein the at least one object comprises a first object from a first channel camera and a second object from a second channel camera, and a same identifier is assigned to the first object and the second object in the final object information based on a number of attribute items common to the first object and the second object, the attribute items representing features that are distinguishable between objects through visual observation, and the feature information indicating at least one of a plurality of different values associated with an attribute item of an object, and wherein the processor is configured to search for the data based on objects that have the same identifier.

2 . The device of claim 1 , wherein a number of attribute items included in the final object information is smaller than a number of attribute items included in the event object information.

3 . The device of claim 1 , wherein the processor, when executing the instructions, is further configured to store event object information of an object having a similarity with the comparison object information that is lower than the predetermined degree in the storage as temporary object information.

4 . The device of claim 3 , wherein the processor, when executing the instructions, is further configured to determine whether the temporary object information satisfies a predetermined criterion.

5 . The device of claim 1 , wherein at least one attribute item defined by the feature information on the at least one object is different from an attribute item defined by other information on the at least one object.

6 . The device of claim 4 , wherein, based on determining that the temporary object information satisfies the predetermined criterion, the processor, when executing the instructions, is further configured to:
update the comparison object information based on the temporary object information.

7 . The device of claim 4 , wherein, based on determining that the temporary object information fails to satisfy the predetermined criterion for a predetermined time, the processor, when executing the instructions, is further configured to delete the temporary object information from the storage.

8 . The device of claim 1 , wherein the storage is further configured to store a representative image for a video.

9 . The device of claim 8 , further comprising:
a display configured to display a video derived as search results when the processor searches for the data, wherein the display is configured to display the representative image associated with the video as thumbnails.

10 . A data storage method comprising:
generating event object information including a plurality of entries, each of which comprises a plurality of attribute items of at least one object detected in a video; comparing the event object information with comparison object information including feature information on a reference object; selecting at least one entry, from among the plurality of entries, with attribute items having at least a predetermined degree of similarity with the feature information on the reference object; generating final object information in which at least one attribute item from among the attribute items of the at least one entry is associated with an identifier of the reference object; and establishing a database based on the final object information, wherein the at least one object comprises a first object from a first channel camera and a second object from a second channel camera, and a same identifier is assigned to the first object and the second object in the final object information based on a number of attribute items common to the first object and the second object, the attribute items representing features that are distinguishable between objects through visual observation, and the feature information indicating at least one of a plurality of different values associated with an attribute item of an object, and wherein the at least one entry can be retrieved from the database based on the at least one attribute item and objects that have the same identifier.

11 . The method of claim 10 , wherein a number of the at least one attribute item included in the final object information is smaller than a number of the plurality of attribute items included in the event object information.

12 . The method of claim 10 , further comprising:
generating temporary object information based on another entry, from among the plurality of entries, with attribute items having similarity with the feature information on the reference object that is less than the predetermined degree.

13 . The method of claim 12 , further comprising:
updating the final object information to comprise at least one attribute item of the other entry, based on determining that the temporary object information satisfies a predetermined criterion.

14 . The method of claim 10 , further comprising:
searching the final object information for data if a search criterion is entered.

15 . A video surveillance method comprising:
generating temporary object information by extracting feature information of at least one object, wherein the at least one object comprises a first object from a first channel camera and a second object from a second channel camera and the first object has a first identifier and the second object has a second identifier different from the first identifier; storing the temporary object information in a storage; generating final object information from the temporary object information based on the feature information of the at least one object having a predetermined degree of similarity with comparison object information, wherein a same identifier is assigned to the first object and the second object in the final object information; storing the final object information in the storage; and monitoring the at least one object based on the same identifier, wherein the predetermined degree of similarity is determined based on the number of attribute items common to the first object and the second object, the attribute items representing features that are distinguishable between objects through visual observation, and the feature information indicating at least one of a plurality of different values associated with an attribute item of an object.

16 . The method of claim 15 ,
wherein the generating temporary object information, the storing the temporary object information, the generating final object information and the storing the final object information are performed by a first processor and the monitoring the at least one object is performed by a second processor which communicates with the first processor via a network channel.

17 . The method of claim 15 , wherein a number of attribute items included in the final object information is smaller than a number of attribute items included in the event object informati

Assignees

• Hanwha Vision Co Ltd

Inventors

• Choi Jae Won
• Lee Jeong Hun
• Kim Kye Won
• Kim Ji Man
• Lee Sang Wook
• Lee Jong Hyeok
• Byun Jae Woon
• Lee Ho Jung
• Choi Jin Hyuk
• Cheung Sweung Won
• Kim Yeon Woo
• Yoon Jin

Classifications

• G06V40/103

  Static body considered as a whole, e.g. static pedestrian or occupant recognition · CPC title

• G06V20/40

  in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44) · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06V20/46

  Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames · CPC title