Electronic device including NPU for detecting or tracking an object

1 . An electronic device comprising:

a first circuitry provided for a neural processing unit (NPU) configured to process an operation of an artificial neural network (ANN) model trained to detect or track at least one object by generating an inference result based on at least one image of a video acquired from at least one camera; and

a second circuitry provided for a signal generator generating a signal applicable to mechanically or electrically control the at least one camera,

wherein the generated signal includes a coordinate of the at least one object,

wherein when the at least one camera is mechanically or electrically controlled based on the generated signal, the at least one object is continuously detected or tracked based on the video,

wherein the at least one image is divided into a plurality of tiles by being processed by the NPU,

wherein the NPU is further configured to receive an index indicating at least one machine code set among a plurality of machine code sets, and

wherein the index is determined based on a size of the plurality of tiles.

2 . The electronic device of claim 1 , wherein the at least one camera includes a lens, an image sensor, and a motor for moving the lens to increase or decrease a distance between the lens and the image sensor.

3 . The electronic device of claim 1 , wherein the at least one camera includes:

a first camera and a second camera having a smaller viewing angle than a viewing angle of the first camera, or

wherein the at least one camera includes a wide-angle camera and a telephoto camera.

4 . The electronic device of claim 1 , wherein the at least one camera includes:

a visible light camera, an ultra violet camera, an infrared camera, a thermal imaging camera, or a night vision camera.

5 . The electronic device of claim 1 , wherein the generated signal includes:

at least one command for mechanically or electrically controlling the at least one camera to increase accuracy of the detecting or the tracking of the at least one object.

6 . The electronic device of claim 5 , wherein the at least one command is implemented to:

move or rotate at least one of a body, a lens, or an image sensor of the at least one camera in X, Y, or Z axis direction; or

increase or decrease a focal distance of the at least one camera.

7 . The electronic device of claim 5 , wherein the at least one command is implemented to:

increase or decrease a viewing angle of the at least one camera,

move or rotate a field of view (FoV) of the at least one camera in X, Y, or Z axis direction,

increase or decrease a frame per second (FPS) of the at least one camera, or

zoom-in or zoom-out the at least one camera.

8 . The electronic device of claim 1 , wherein the signal including the coordinate of the at least one object is used to enable the at least one camera to capture an image portion including the at least one object at a larger size.

9 . The electronic device of claim 1 ,

wherein the at least one camera includes a first camera and a second camera having a smaller viewing angle than a viewing angle of the first camera, and

wherein a field of view (FoV) of the second camera is moved or rotated in X, Y, or Z axis direction based on the coordinate.

10 . The electronic device of claim 1 ,

wherein the at least one camera includes a first camera and a second camera having a smaller viewing angle than a viewing angle of the first camera, and

wherein the first camera is used to enable the NPU to detect the at least one object, and the second camera is used to enable the NPU to track the detected at least one object.

11 . The electronic device of claim 10 , wherein the signal is generated based on flight altitude of the electronic device, height from sea level or ground of electronic device, or flight speed of electronic device.

12 . A method comprising:

detecting or tracking at least one object based on one or more images of a video obtained from one or more cameras;

generating a signal including at least one command for mechanically or electrically controlling the one or more cameras in order to increase an accuracy of the detecting or tracking when the at least one object is detected or tracked with a first confidence level lower than a first threshold,

wherein the generated signal includes a coordinate of the at least one object, and

mechanically or electrically controlling the one or more cameras based on the generated signal; and

continuing the detecting or tracking the at least one object based on a subsequent video obtained from the one or more cameras mechanically or electrically controlled based on the generated signal,

wherein the one or more images are divided into a plurality of tiles by being processed by a neural processing unit (NPU),

wherein the NPU is further configured to receive an index indicating at least one machine code set among a plurality of machine code sets, and

wherein the index is determined based on a size of the plurality of tiles.

13 . The method of claim 12 , wherein the one or more cameras include:

a lens, an image sensor, and a motor for moving the lens to increase or decrease a distance between the lens and the image sensor.

14 . The method of claim 12 , wherein the one or more cameras include:

a first camera and a second camera having a smaller viewing angle than a viewing angle of the first camera, or

wherein the one or more cameras include a wide-angle camera and a telephoto camera.

15 . The method of claim 12 , wherein the one or more cameras include:

a visible light camera, an ultra violet camera, an infrared camera, a thermal imaging camera, or a night vision camera.

16 . The method of claim 12 , wherein the generated signal includes:

at least one command for mechanically or electrically controlling the one or more cameras to increase accuracy of the detecting or the tracking of the at least one object.

17 . The method of claim 12 , wherein the at least one command is implemented to:

move or rotate at least one of a body, a lens, or an image sensor of the one or more cameras in X, Y, or Z axis direction; or

increase or decrease a focal distance of the one or more cameras.

18 . The method of claim 12 , wherein the at least one command is implemented to:

increase or decrease a viewing angle of the one or more cameras,

move or rotate a field of view (FoV) of the one or more cameras in X, Y, or Z axis direction,

increase or decrease a frame per second (FPS) of the one or more cameras, or

zoom-in or zoom-out the one or more cameras.

19 . The method of claim 12 ,

wherein when the at least one object is detected or tracked with the first confidence level lower than the first threshold, the signal is generated to include the coordinate of the at least one object.