APPARATUS AND METHOD FOR CONTROLLING NETWORK CAMERA

• US 20170163868A1
• Filed: 12/03/2015
• Published: 06/08/2017
• Est. Priority Date: 07/23/2015
• Status: Active Grant

• Current Assignee: Hanwha Vision Company Limited (Hanwha Corporation)
• Original Assignee: Hanwha Techwin Co., Ltd. (Hanwha Corporation)
• Inventors: LEE, Hwalsuk, JANG, Jaeho
• Granted Patent: US 9,866,744 B2
• Time in Patent Office: Days
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• 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: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/661 Transmitting camera control signals through networks, e.g. control via the Internet
• CPC Class Codes: H04N 23/6811 based on the image signal
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof

Abstract

An apparatus for controlling a network camera includes: a receiver configured to receive at least one image captured by the network camera monitoring a predetermined region; and at least one processor configured to implement: a detector which detects a plurality of trajectories in accordance with movement of each of a plurality of objects in the image; and a controller which extracts object feature information from each of the plurality of trajectories, and, if object feature information extracted from a trajectory corresponds to first and second objects, separate the trajectory into a first trajectory comprising first object feature information and a second trajectory comprising second object feature information.

Claims

1. An apparatus for controlling a network camera, the apparatus comprising:

a receiver configured to receive at least one image captured by the network camera monitoring a predetermined region; and

at least one processor configured to implement;

a detector which detects a plurality of trajectories in accordance with movement of each of a plurality of objects in the image; and

a controller which extracts object feature information from each of the plurality of trajectories, and, if object feature information extracted from a trajectory corresponds to first and second objects, separate the trajectory into a first trajectory comprising first object feature information and a second trajectory comprising second object feature information.

2. The apparatus of claim 1, wherein each of the plurality of trajectories comprises:

an object identifier for identifying each of the plurality of objects;

object image information regarding at least a portion of an image where each of the plurality of objects is displayed; and

object moving line information extracted based on the object image information.

3. The apparatus of claim 2, wherein each of the plurality of trajectories are identified by the object identifier.

4. The apparatus of claim 2, wherein the controller assigns different object identifiers from an object identifier of the trajectory from which the object feature information is extracted to the first trajectory and the second trajectory, respectively.

5. The apparatus of claim 2, wherein the controller assigns a same object identifier as an object identifier of the trajectory from which the object feature information is extracted to the first trajectory, and assigns a different object identifier from the object identifier of the trajectory from which the object feature information is extracted to the second trajectory.

6. The apparatus of claim 2, wherein if the object feature information corresponds to the first object and the second object, two clusters of the first object and the second object correspond to the object feature information.

7. The apparatus of claim 2, wherein the object feature information is appearance information of an object extracted from the object image information.

8. The apparatus of claim 2, wherein the object moving line information is at least one of coordinate data and size data of an image of a plurality of object image frames constituting the object image information.

9. The apparatus of claim 1, wherein the controller compares a plurality of pieces of object feature information extracted from the plurality of trajectories, and if third object feature information and fourth object feature information among the plurality of pieces of object feature information are the same, to unites a third trajectory comprising the third object feature information with a fourth trajectory comprising the fourth object feature information.

10. The apparatus of claim 9, wherein the controller assigns a different object identifier from an existing object identifier of the third trajectory and an existing object identifier of the fourth trajectory to a trajectory united the third trajectory with the fourth trajectory.

11. The apparatus of claim 9, wherein the controller assigns the same object identifier as an existing object identifier of the third trajectory or an existing object identifier of the fourth trajectory to a trajectory united the third trajectory with the fourth trajectory.

12. The apparatus of claim 1, wherein the detector detects another trajectory comprising the first object feature information from at least one image captured by another network camera connected to the network camera and monitoring another predetermined region, and

wherein the controller assigns an object identifier which is the same as an object identifier assigned to the first trajectory to the other trajectory.

13. A method of controlling a network camera using at least one processor, the method comprising:

detecting a plurality of trajectories in accordance with movement of each of a plurality of objects from at least one image captured by the network camera monitoring a predetermined region;

extracting object feature information from each of the plurality of trajectories;

determining a number of trajectories corresponding to the object feature information;

if object feature information extracted from a trajectory corresponds to first and second objects, separating the trajectory into a first trajectory comprising first object feature information and a second trajectory comprising second object feature information.

14. The method of claim 13, wherein each of the plurality of trajectories comprises:

an object identifier for identifying each of the plurality of objects;

object image information regarding at least a portion of an image where each of the plurality of objects is displayed; and

object moving line information extracted based on the object image information.

15. The method of claim 14, wherein the first trajectory and the second trajectory are identified by different object identifiers from an object identifier of the trajectory from which the object feature information is extracted.

16. The method of claim 14, wherein the object feature information is appearance information of an object extracted from the object image information.

17. The method of claim 14, wherein the object moving line information is at least one of coordinate data and size data of an image of a plurality of object image frames constituting the object image information.

18. The method of claim 13, further comprising:

comparing a plurality of pieces of object feature information extracted from the plurality of trajectories; and

if third object feature information and fourth object feature information among the plurality of pieces of object feature information are the same, uniting a third trajectory comprising the third object feature information with a fourth trajectory comprising the fourth object feature information.

19. The method of claim 18, wherein a trajectory generated by uniting the third trajectory with the fourth trajectory is identified by a different object identifier from an existing object identifier of the third trajectory and an existing object identifier of the fourth trajectory.

20. The method of claim 13, further comprising:

detecting another trajectory comprising the first object feature information from at least one image captured by another network camera connected to the network camera and monitoring another predetermined region, and

assigning an object identifier which is the same as an object identifier assigned to the first trajectory to the other trajectory.