Systems and methods for image processing

Patent metadata

Field	Value
Publication number	US-11206376-B2
Application number	US-202016891085-A
Country	US
Kind code	B2
Filing date	Jun 3, 2020
Priority date	Dec 8, 2017
Publication date	Dec 21, 2021
Grant date	Dec 21, 2021

Abstract

A method for image acquisition may include receiving a video from a first video camera in a period, the video including a first view of a scene. The method may also include delineating a plurality of first regions within the first view of the scene. The method may further include determining an accumulated effect of at least one feature occurring within the period within at least one of the plurality of first regions. The method may further include directing a second video camera towards a second view of the scene based on the accumulated effect.

First claim

I claim:

1. A system for image acquisition, comprising:
at least one storage medium storing a set of instructions; and
at least one processor configured to communicate with the at least one storage medium, wherein when executing the set of instructions, the at least one processor is directed to cause the system to:
receive a video from a first video camera in a period, the video including a first view of a scene;
delineate a plurality of first regions within the first view of the scene;
determine an accumulated effect of at least one feature occurring within the period within at least one of the plurality of first regions;
identify, based on the plurality of accumulated effects of the plurality of first regions, a plurality of candidate first regions from the plurality of first regions;
identify at least one active region from the plurality of candidate first regions by clustering the plurality of candidate first regions; and
direct a second video camera towards a second view of the scene based on the coordinates of the at least one active region in the first video camera, and a coordinate mapping relationship between the first video camera and the second video camera.

2. The system of claim 1 , wherein the at least one processor is further directed to cause the system to:
control the second video camera to capture video according to the second view of the scene, wherein the second view of the scene provides a closer view than the first view based on a different level of zoom of the second video camera compared to the first video camera.

3. The system of claim 1 , wherein to determine the accumulated effect of at least one feature, the at least one processor is further directed to cause the system to:
generate a count of the at least one feature that occurs in the period within at least one of the plurality of first regions.

4. The system of claim 3 , wherein to delineate the plurality of first regions within the first view of the scene, the at least one processor is further directed to cause the system to:
delineate the plurality of first regions based on a resolution of the video.

5. The system of claim 3 , wherein to generate the count of the at least one feature that occurs in the period within at least one of the plurality of first regions, the at least one processor is further configured to:
for each of the plurality of first regions:
for every predetermined time interval in the period, identify whether the at least one feature occurs within the first region; and
generate the count of the at least one feature that occurs within the first region based on the plurality of identifications of whether the at least one feature occurs within the first region.

6. The system of claim 5 , wherein to identify the plurality of candidate first regions from the plurality of first regions based on the plurality of accumulated effects of the plurality of first regions, the at least one processor is further directed to cause the system to:
for each of the plurality of first regions:
compare the count of the at least one feature of the first region with a first threshold; and
determine the first region as a candidate first region based on a comparison result that the count of the at least one feature of the first region is greater than the first threshold.

7. The system of claim 1 , wherein to identify the at least one active region from the plurality of candidate first regions by clustering the plurality of candidate first regions, the at least one processor is further directed to cause the system to:
cluster the plurality of candidate first regions into at least one candidate active region;
for each of the at least one candidate active region;
determine a feature density of the candidate active region based on a number of candidate first regions included in the candidate active region and a number of first regions included in the candidate active region;
compare the feature density of the candidate active region with a second threshold; and
identify the candidate active region as the active region based on a comparison result that the feature density of the candidate active region is greater than the second threshold.

8. The system of claim 7 , wherein for each of the at least one candidate active region, the at least one processor is further directed to cause the system to:
determine a total count of the at least one feature of the candidate active region based on the count of the at least one feature of each candidate first region included in the candidate active region;
compare the total count of the at least one feature of the candidate active region with a third threshold; and
identify the candidate active region as the active region based on a comparison result that the total count of the at least one feature of the candidate active region is greater than the third threshold.

9. The system of claim 8 , wherein the at least one processor is further directed to cause the system to:
determine an active degree for each of the at least one active region;
determine a group of active regions based on the active degree of each of the at least one active region, wherein the active degree corresponding to each of the active regions in the group is greater than any of active degrees of the at least one active region not included in the group; and
direct the second video camera towards at least one second view according to the group of active regions.

10. The system of claim 9 , wherein to direct the second video camera towards at least one second view according to the group of active regions, the at least one processor is further directed to cause the system to:
rank the group of active regions based on the active degree of each active region included in the group;
determine a sequence for the group of active regions based on the ranking; and
direct the second video camera based on the sequence.

11. A method for image acquisition, comprising:
receiving a video from a first video camera in a period, the video including a first view of a scene;
delineating a plurality of first regions within the first view of the scene;
determining an accumulated effect of at least one feature occurring within the period within at least one of the plurality of first regions;
identifying, based on the plurality of accumulated effects of the plurality of first regions, a plurality of candidate first regions from the plurality of first regions;
identifying at least one active region from the plurality of candidate first regions by clustering the plurality of candidate first regions; and
directing a second video camera towards a second view of the scene based on the coordinates of the at least one active region in the first video camera, and a coordinate mapping relationship between the first video camera and the second video camera.

12. The method of claim 11 , wherein the determining the accumulated effect of at least one feature includes:
generating a count of the at least one feature that occurs in the period within at least one of the plurality of first regions.

13. The method of claim 12 , wherein the generating the count of the at least one feature that occurs in the period within at least one of the plurality of first regions includes:
for each of the plurality of first regions:
for every predetermined time interval in the period, identifying whether the at least one feature occurs within the first region; and
generating the count of the at least one feature that occurs within the first region based on the plurality of identifications of whether the at least one feature occurs within the first region.

14.

Assignees

• Zhejiang Dahua Technology Co

Inventors

• Zhang Lunqi

Classifications

• H04N23/90

  Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums · CPC title

• H04N23/695

  Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects · CPC title

• H04N23/69

  Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming · CPC title

• H04N7/188 Primary

  Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position (signal generation from motion picture films H04N5/253) · CPC title

• G06V20/52

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