Camera analyzing images on basis of artificial intelligence, and operating method therefor

1. An operating method for an artificial intelligence (AI) camera that communicates with at least one another AI camera through a network, the AI camera comprising an AI processor configured to perform image analysis using a deep learning method, the operating method comprising:

configuring a cluster for the image analysis together with the other AI camera by exchanging registration information about at least one of the AI camera and the other AI camera with the other AI camera through the network;

sharing, with the other AI camera, registration information about normal cameras used to access the normal cameras through the network;

receiving, based on one of the normal cameras being allocated to AI camera, an image captured by the allocated normal camera by accessing the allocated normal camera; analyzing the received image using the AI processor; and

transmitting a result of the analyzing the received image together with an identifier of the allocated normal camera to an external device through the network,

wherein the receiving the image captured by the allocated normal camera comprises:

receiving the image having a first length from the allocated normal camera, when a probability according to deep learning is greater than or equal to a threshold value based on the received image being analyzed using the AI processor; and

receiving the image having a second length from the allocated normal camera, when the probability according to deep learning is smaller than the threshold value based on the received image being analyzed using the AI processor,

wherein the second length is greater than the first length.

2. The operating method of claim 1 , further comprising:

receiving registration information about an additional AI camera; and

accessing the additional AI camera according to the received registration information to add the additional AI camera to the cluster.

3. The operating method of claim 1 , wherein the configuring the cluster comprises communicating with the other AI camera to determine one of the AI camera and the other AI camera as a master node of the cluster, and

wherein the allocated normal camera is selected according to a command from the master node.

4. The operating method of claim 1 , wherein the receiving the captured image includes:

receiving an event alarm signal generated by the allocated normal camera; and

requesting the allocated normal camera to provide the captured image in response to the event alarm signal.

5. The operating method of claim 4 , wherein the configuring the cluster comprises communicating with the other AI camera to determine one of the AI camera and the other AI camera as a master node of the cluster, and

wherein the event alarm signal is received through the master node.

6. The operating method of claim 4 , wherein the receiving the captured image further comprises changing a setting value of the allocated normal camera into a predetermined value in response to the event alarm signal before requesting the allocated normal camera to provide the captured image.

7. The operating method of claim 1 , further comprising:

communicating status messages with the other AI camera;

additionally receiving an image captured by another normal camera allocated to the other AI camera by accessing the other normal camera based on the other AI camera being determined to be abnormal on the basis of the status messages;

analyzing the additionally received image using the AI processor; and

transmitting a result of the analyzing the additionally received images together with an identifier of the other normal camera to the external device through the network.

8. The operating method of claim 1 , wherein the AI camera further comprises an image sensor, and

wherein the operating method further comprises:

capturing an image through the image sensor; and

analyzing the captured image using the AI processor.

9. The operating method of claim 8 , wherein the transmitting the result of the analyzing the received image together with the identifier of the allocated normal camera to the external device through the network comprises transmitting the captured image, first metadata, and second metadata to the external device,

wherein the first metadata comprises a result of the analyzing the captured image, and

wherein the second metadata comprises the result of the analyzing the received image and the identifier of the allocated normal camera.

10. The operating method of claim 1 , wherein the configuring the cluster comprises:

receiving the registration information about the other AI camera from a user terminal; and

configuring the cluster by performing communication with the other AI camera using the received registration information.

11. The operating method of claim 1 , wherein the sharing the registration information about the normal cameras with the other AI camera comprises:

receiving the registration information about the normal cameras from a user terminal; and

providing the received registration information to the other AI camera.

12. A camera comprising:

an optical system;

a first processor configured to process an image generated according to light received through the optical system;

a second processor configured to operate in response to control of the first processor and analyze the processed image on the basis of a deep learning method; and

a network interface providing communication through a network,

wherein the first processor is configured to:

configure a cluster for an image analysis together with at least one external AI camera by exchanging registration information about at least one of the camera and the external AI camera with the external AI camera through the network;

share, with the external AI camera, registration information about normal cameras used to access the normal cameras through the network;

receive, based on one of the normal cameras being allocated, an image captured by the allocated normal camera by accessing the allocated normal camera;

control the second processor to analyze the received image; and

transmit a result of the analysis of the received image together with an identifier of the allocated normal camera to an external device through the network,

wherein the first processor is configured to adjust a length of the image to a first length when a probability according to deep learning is greater than or equal to a threshold value based on the received image being analyzed by the second processor, and adjust a length of the image to a second length when the probability according to deep learning is greater than or equal to the threshold value based on the received image being analyzed by the second processor and,

wherein the second length is greater than the first length.

13. The camera of claim 12 , wherein the first processor is configured to access an additional AI camera according to registration information about the additional AI camera to add the additional AI camera to the cluster, based on the registration information about the additional AI camera being received.

14. The camera of claim 12 , wherein the first processor is configured to communicate with the external AI camera to determine one of the camera and the external AI camera included in the cluster as a master node of the cluster, and

wherein the allocated normal camera is selected according to a command from the master node.

15. The camera of claim 14 , wherein, based on being selected as the master node, the first processor is further configured to allocate another normal camera among the normal cameras to the external AI camera based on determining a resource of the external AI camera so that an image captured by the other normal camera is analyzed by the external AI camera.

16. The camera of claim 12 , wherein the first processor is configured to change a setting value of the allocated normal camera into a predetermined setting value before requesting the allocated normal camera to provide the captured image.

17. The camera of claim 16 , wherein the captured image is an image captured by the allocated normal camera according to the predetermined setting value, and

wherein the setting value comprises a value of sharpness and a value of exposure.

18. The camera of claim 12 , wherein the registration information about at least one of the camera and the external AI camera comprises at least one of a uniform resource locator (URL) address, an Internet protocol (IP) address, a port number, and a camera login account.