APPARATUS, METHODS AND COMPUTER PRODUCTS FOR VIDEO ANALYTICS

• US 20180293442A1
• Filed: 04/06/2017
• Published: 10/11/2018
• Est. Priority Date: 04/06/2017
• Status: Active Grant

• Current Assignee: KAMI Vision Incorporated
• Original Assignee: ANTS TECHNOLOGY (HK) LIMITED
• Inventors: FRIDENTAL, Ron, BLAYVAS, Ilya
• Granted Patent: US 10,229,322 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 16/7837 using objects detected or recognised in the video content
• CPC Class Codes: G06F 18/217 Validation; Performance evaluation; Active pattern learning techniques
• CPC Class Codes: G06V 10/776 Validation; Performance evaluation
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

A computerized method for providing no-configuration object recognition video analytics, the method comprising generating a database stored in computer memory and including labelled images of recognized objects imaged at an initial set of sites including at least one site; using the database as a training set to train a pattern recognition engine; uploading images of additional site/s including at least one additional site which is not a member in the initial set of sites; providing object recognition results for the additional site/s by using the pattern recognition engine on the images as uploaded; verifying the object recognition results; and using a processor for operating the pattern recognition engine on images generated at each the additional site/s including modifying the pattern recognition engine according to and when indicated by the verifying, thereby to provide no-configuration object recognition video analytics at the additional site/s.

Claims

1. A computerized method for providing no-configuration object recognition video analytics, the method comprising:

generating a database stored in computer memory and including labelled images of recognized objects imaged at an initial set of sites including at least one site;

using the database as a training set to train a pattern recognition engine;

uploading images of additional site/s including at least one additional site which is not a member in the initial set of sites;

providing object recognition results for the additional site/s by using the pattern recognition engine on said images as uploaded;

verifying said object recognition results; and

using a processor for operating the pattern recognition engine on images generated at each said additional site/s including modifying the pattern recognition engine according to and when indicated by said verifying, thereby to provide no-configuration object recognition video analytics at said additional site/s.

2. A method according to claim 1 wherein said verifying is performed remotely from the additional site/s.

3. A method according to claim 1 wherein said verifying comprises presenting said object recognition results to a human and accepting a verifying input provided by the human.

4. A method according to claim 3 wherein said accepting comprises displaying 2 selectable options to the human, corresponding to “

object” and

“

not object” and

accepting the human'"'"'s selection of one of the two options.

5. A computerized system for providing no-configuration object recognition video analytics, the system comprising:

a user interface for accepting uploaded images of additional site/s including at least one additional site which is not a member in the initial set of sites; and

a processor configured for providing object recognition results for the additional site/s by using a pattern recognition engine on said images as uploaded;

verifying said object recognition results;

operating the pattern recognition engine on images generated at each said additional site/s including modifying the pattern recognition engine according to and when indicated by said verifying, thereby to provide no-configuration object recognition video analytics at said additional site/s.

6. A system according to claim 5 and also comprising a pattern recognition engine in data communication with the processor.

7. A system according to claim 5 and also comprising:

a database including labelled images of objects recognized at an initial set of sites including at least one site; and

a processor configured for using the database as a training set to train a pattern recognition engine.

9. A system according to claim 5 and wherein said pattern recognition engine comprises a semantic segmentation engine.

10. A system according to claim 5 and wherein said pattern recognition engine comprises an object detection engine.

11. A system according to claim 5 and wherein said pattern recognition engine comprises an object recognition engine.

8. A computer program product, comprising a non-transitory tangible computer readable medium having computer readable program code embodied therein, said computer readable program code adapted to be executed to implement a computerized method for providing no-configuration object recognition video analytics, the method comprising:

generating a database stored in computer memory and including labelled images of recognized objects imaged at an initial set of sites including at least one site;

using the database as a training set to train a pattern recognition engine ;

uploading images of additional site/s including at least one additional site which is not a member in the initial set of sites;

providing object recognition results for the additional site/s by using the pattern recognition engine on said images as uploaded;

verifying said object recognition results; and

using a processor for operating the pattern recognition engine on images generated at each said additional site/s including modifying the pattern recognition engine according to and when indicated by said verifying, thereby to provide no-configuration object recognition video analytics at said additional site/s.