Methods and systems for video surveillance

Patent metadata

Field	Value
Publication number	US-11367287-B2
Application number	US-202016888861-A
Country	US
Kind code	B2
Filing date	Jun 1, 2020
Priority date	Jun 17, 2015
Publication date	Jun 21, 2022
Grant date	Jun 21, 2022

Abstract

A system for video surveillance includes an image sensor configured capture an image including a reference zone and a memory device that stores instructions. The system also includes one or more processors that are configured to execute the instructions to determine 3D coordinates of a target comprised in the image and determine 3D coordinates of the reference zone. The one or more processors are further configured to identify an event according to the 3D coordinates of the target and the 3D coordinates of the reference zone.

First claim

The invention claimed is:

1. A system comprising:
at least one image sensor configured to capture a plurality of two-dimensional (2D) images including a target and a reference zone;
a memory device that stores instructions; and
one or more processors that are configured to execute the instructions to:
determine three-dimensional (3D) coordinates of the target based on the plurality of 2D images;
determine 3D coordinates of the reference zone; and
identify an event according to the 3D coordinates of the target and the 3D coordinates of the reference zone, wherein identifying the event includes identifying the event based on a distance between a reference point on a reference line and the target, and the reference line is a straight line through a center of an image and vertical to a lower boundary of the image.

2. The system of claim 1 , wherein the reference zone is perpendicular to a ground plane in the plurality of 2D images.

3. The system of claim 1 , wherein to determine the 3D coordinates of the target, the one or more processors are configured to:
identify a pixel or a pixel group in the plurality of 2D images;
identify the pixel or the pixel group as the target; and
determine the 3D coordinates of the pixel or a pixel group.

4. The system of claim 1 , wherein the plurality of 2D images are captured by the at least one image sensor at different positions.

5. The system of claim 1 , wherein the plurality of 2D images are captured by the at least one image sensor at different time points.

6. The system of claim 1 , wherein to determine the 3D coordinates of the target, the one or more processors are configured to:
reconstruct a 3D image according to the plurality of 2D images; and
determine the 3D coordinates of the target according to the reconstructed 3D image.

7. The system of claim 1 , wherein to identify the event, the one or more processors are configured to:
determine horizontal information of the 3D coordinates of the target and horizontal information of the 3D coordinates of the reference zone; and
identify the event based on the determined horizontal information of the 3D coordinates of the target and the reference zone.

8. The system of claim 1 , wherein the one or more processors are further configured to:
determine a trail of the target over a period of time;
determine 3D coordinates of the trail of the target over the period of time; and
determine the event according to the 3D coordinates of the trail of the target over the period of time.

9. The system of claim 1 , wherein the event includes at least one of:
the target locating inside of the reference zone;
the target locating outside of the reference zone;
the target locating on a boundary of the reference zone;
the target passing through the reference zone from the outside of the reference zone to the inside of the reference zone;
the target passing through the reference zone from the inside of the reference zone to the outside of the reference zone;
the target leaving the reference zone without passing through the reference zone; or
the target approaching the reference zone without passing through the reference zone.

10. A method implemented on a computing device having at least one processor and at least one computer readable storage medium, the method comprising:
obtaining a plurality of two-dimensional (2D) images including a target and a reference zone;
determining three-dimensional (3D) coordinates of the target based on the plurality of 2D images;
determining 3D coordinates of the reference zone; and
identifying an event according to the 3D coordinates of the target and the 3D coordinates of the reference zone, wherein identifying the event includes identifying the event based on a distance between a reference point on a reference line and the target, and the reference line is a straight line through a center of an image and vertical to a lower boundary of the image.

11. The method of claim 10 , wherein the reference zone is perpendicular to a ground plane in the plurality of 2D images.

12. The method of claim 10 , wherein the determining 3D coordinates of the target comprising:
identifying a pixel or a pixel group in the plurality of 2D images;
identifying the pixel or the pixel group as the target; and
determining the 3D coordinates of the pixel or a pixel group.

13. The method of claim 10 , wherein the plurality of 2D images are captured by the at least one image sensor at different positions.

14. The method of claim 10 , wherein the plurality of 2D images are captured by the at least one image sensor at different time points.

15. The method of claim 10 , wherein the determining 3D coordinates of the target comprising:
reconstructing a 3D image according to the plurality of 2D images; and
determining the 3D coordinates of the target according to the reconstructed 3D image.

16. The method of claim 10 , wherein the identifying an event comprising:
determining horizontal information of the 3D coordinates of the target and horizontal information of the 3D coordinates of the reference zone; and
identifying the event based on the determined horizontal information of the 3D coordinates of the target and the reference zone.

17. The method of claim 10 , further comprising:
determining a trail of the target over a period of time;
determining 3D coordinates of the trail of the target over the period of time; and
determining the event according to the 3D coordinates of the trail of the target over the period of time.

18. The method of claim 10 , wherein the event includes at least one of:
the target locating inside of the reference zone;
the target locating outside of the reference zone;
the target locating on a boundary of the reference zone;
the target passing through the reference zone from the outside of the reference zone to the inside of the reference zone;
the target passing through the reference zone from the inside of the reference zone to the outside of the reference zone;
the target leaving the reference zone without passing through the reference zone; or
the target approaching the reference zone without passing through the reference zone.

19. A non-transitory computer readable medium embodying a computer program product, the computer program product comprising instructions configured to cause a computing device to perform a method comprising:
obtaining a plurality of two-dimensional (2D) images including a target and a reference zone;
determining three-dimensional (3D) coordinates of the target based on the plurality of 2D images;
determining 3D coordinates of the reference zone; and
identifying an event according to the 3D coordinates of the target and the 3D coordinates of the reference zone, wherein identifying the event includes identifying the event based on a distance between a reference point on a reference line and the target, and the reference line is a straight line through a center of an image and vertical to a lower boundary of the image.

20. The non-transitory computer readable medium of claim 19 , wherein the reference zone is perpendicular to a ground plane in the plurality of 2D images.

Assignees

• Zhejiang Dahua Technology Co

Inventors

• Pan Huadong
• Cheng Miao
• Pan shizhu
• Zhang Xingming

Classifications

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title

• G06V20/44

  Event detection · CPC title

• G06V20/52 Primary

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

• G08B25/08

  using communication transmission lines {(G08B13/19658, G08B21/0286, G08B25/016 take precedence)} · CPC title

• G08B5/36

  using visible light sources · CPC title