Camera system and method of tracking object using the same

Patent metadata

Field	Value
Publication number	US-10334150-B2
Application number	US-201514712039-A
Country	US
Kind code	B2
Filing date	May 14, 2015
Priority date	May 14, 2014
Publication date	Jun 25, 2019
Grant date	Jun 25, 2019

Abstract

Provided is a camera system capable of detecting and tracking an object. The camera system includes: a camera configured to detect at least one object in a surveillance region of which an image is captured by the camera directed in a first direction and generate metadata of the object; and a camera controller configured to control at least one of panning, tilting and zooming of the camera based on the metadata of a target object selected from among the at least one object.

First claim

What is claimed is:

1. A camera system comprising:
a camera configured to detect at least one object in a surveillance region of which an image is captured by the camera directed in a first direction, and generate metadata of the at least one object based on a result of detection of the at least one object; and
a camera controller configured to control at least one of panning, tilting and zooming of the camera based on the metadata of a target object selected from among the at least one object,
wherein the camera controller is further configured to:
set a first region in the image captured by the camera directed in the first direction based on a center of the image, the first region defining boundaries of the panning and the tilting of the camera; and
set a second region in the image captured by the camera directed in the first direction, the second region indicating a movable range of the target object which is determined to currently move within the first region,

wherein the camera controller is configured to set the second region to have a size and a direction with respect to the center of the image that are variable according to a velocity and a movement direction of the target object, the second region having a larger size in response to a higher velocity of the target object and having a smaller size in response to a lower velocity of the target object, and
wherein, when the target object departs from the first region, the camera controller is configured to control at least one of panning and tilting of the camera to direct the camera in a second direction toward the target object, based on metadata of the target object, obtained based on a result of detection, by the camera directed in the first direction, of the target object within the second region and excluding metadata obtained in a region outside of the second region,
wherein the camera controller is configured to control the at least one of panning and tilting of the camera with respect to the target object among the at least one object by comparing size and vector information about the target object with size and vector information about another object among the at least one object.

2. The camera system of claim 1 , wherein the metadata comprises a coordinate of the at least one object.

3. The camera system of claim 2 , wherein the camera controller is configured to calculate a size and a center coordinate of the at least one object from the metadata generated by the camera while the camera is maintained in the first direction without being moved, and
wherein the camera controller is configured to calculate vector information about the at least one object from variations of the center coordinate of the at least one object.

4. The camera system of claim 3 , wherein the vector information comprises a travel distance, a travel direction, and a velocity of the at least one object.

5. The camera system of claim 1 , wherein the camera controller is configured to select one of the at least one object having a preset size as the target object.

6. The camera system of claim 1 , wherein the camera controller is configured to control zooming of the camera such that a size of the target object in an image captured by the camera directed in the second direction is equal to a size of the target object in the image captured by the camera directed in the first direction.

7. The camera system of claim 1 , wherein the camera controller is configured to control the at least one of panning and tilting of the camera with respect to the target object among the target object and another object existing in the second region other than the target object by comparing size and vector information about the other object with size and vector information about the target object.

8. A method of tracking an object using a camera, the method comprising:
generating metadata about at least one object using the camera based on a result of detection of the at least one object, the at least one object being detected in a surveillance region of which an image is captured by the camera directed in a first direction;
selecting a target object from among the at least one object based on the metadata analyzed by a camera controller; and
generating a control signal based on the metadata of the target object to control at least one of panning, tilting and zooming of the camera,
wherein the generating the control signal comprises:
setting a first region in the image captured by the camera directed in the first direction based on a center of the image, the first region defining boundaries of the panning and the tilting of the camera; and
setting a second region in the image captured by the camera directed in the first direction, the second region indicating a movable range of the target object which is determined to currently move within the first region, wherein the second region is set to have a size and a direction with respect to the center of the image that are variable according to a velocity and a movement direction of the target object, the second region having a larger size in response to a higher velocity of the target object and having a smaller size in response to a lower velocity of the target object, and
when the target object departs from the first region, generating the control signal to control at least one of panning and tilting of the camera to direct the camera in a second direction toward the target object, based on metadata of the target object, obtained based on a result of detection, by the camera directed in the first direction, of the target object within the second region and excluding metadata obtained in a region outside of the second region,

wherein the generating the control signal further comprises generating the control signal to control the at least one of panning and tilting of the camera with respect to the target object among the at least one object by comparing size and vector information about the target object with size and vector information about another object among the at least one object.

9. The method of claim 8 , wherein the metadata comprises a coordinate of the at least one object.

10. The method of claim 9 , wherein the generating the control signal further comprises:
calculating a size and a center coordinate of the at least one object from the metadata generated by the camera while the camera is maintained in the first direction without being moved; and
calculating vector information about the at least one object from variations of the center coordinate of the at least one object.

11. The method of claim 10 , wherein the vector information comprises a travel distance, a travel direction, and a velocity of the at least one object.

12. The method of claim 8 , wherein the selecting the target object comprises selecting one of the at least one object having a preset size as the target object.

13. The method of claim 8 , wherein the generating the control signal further comprises generating the control signal to control zooming of the camera such that a size of the target object in an image captured by the camera directed in the second direction is equal to a size of the target object in the image captured by the camera directed in the first direction.

14. The method of claim 8 , wherein the generating the control signal further comprises generating the control signal to control the at least one of panning and tilting of the camera with respect to the target object among the target object and another object existing in the second region other than the target object by comparing size and vector information about the target object with size and vector information

Assignees

• Hanwha Techwin Co Ltd
• Hanwha Aerospace Co Ltd

Inventors

• Kim Kyunghyun
• Kim Daesung
• Park Jongin

Classifications

• H04N23/69

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

• H04N23/611 Primary

  where the recognised objects include parts of the human body · CPC title

• H04N7/183

  for receiving images from a single remote source · CPC title

• H04N5/232 Primary

  Electricity · mapped topic

• H04N5/23219

  Electricity · mapped topic