Unmanned combat vehicle and target detection method thereof

Patent metadata

Field	Value
Publication number	US-12347206-B2
Application number	US-202217837635-A
Country	US
Kind code	B2
Filing date	Jun 10, 2022
Priority date	Jan 3, 2022
Publication date	Jul 1, 2025
Grant date	Jul 1, 2025

Abstract

An unmanned vehicle includes: at least one camera configured to obtain an image; and an image processor configured to: detect an object from the image; set a region of interest at the object in the image; and detect a target within the region of interest by detecting a change in pixel values from the region of interest, wherein the target is positioned behind the object.

First claim

What is claimed is:

1. A target detection method performed by an unmanned vehicle comprising a first camera using a first field of view and a second camera using a second field of view that is smaller than the first field of view, the target detection method comprising:
detecting an object from a first image obtained by the first camera, based on the first field of view;
setting a region of interest at the object in the first image;
detecting a target within the region of interest; and
detecting target information from a second image obtained from the second camera pointing to the region of interest from which the target is detected, based on the second field of view that is smaller than the first field of view.

2. The target detection method of claim 1 , wherein the detecting the object comprises detecting the object within a predetermined distance.

3. The target detection method of claim 2 , wherein the object within the predetermined distance is detected based on geographic information system (GIS) information about a road or a landmark detected from the first image.

4. The target detection method of claim 1 , further comprising calibrating a position of the region of interest in response to a change in orientation of the first camera relative to the unmanned aerial vehicle.

5. The target detection method of claim 4 , wherein the calibrating the position of the region of interest comprises:
calibrating the position of the region of interest by compensating for an amount of pixel movement which corresponds to an amount of the change in orientation of the first camera relative to the unmanned aerial vehicle.

6. The target detection method of claim 4 , wherein the calibrating the position of the region of interest comprises:
calibrating the region of interest by tracking the object according to an object tracking method and setting the region of interest at the object that is tracked.

7. The target detection method of claim 1 , further comprising:
determining whether the target is detected from the region of interest, based on a pixel value change around the object in the region of interest.

8. The target detection method of claim 1 , further comprising displaying the target information on the first image.

9. The target detection method of claim 8 , wherein the displaying the target information comprises:
determining a characteristic of the target based on the target information and displaying information about the characteristic on the first image.

10. The target detection method of claim 1 , further comprising:
obtain tracking information of the region of interest corresponding to an object based on detected movements of the object;
controlling an orientation of the second camera to point at the region of interest of the object based on the tracking information;
calibrating a position of the region of interest in response to a change in orientation of the first camera relative to the unmanned aerial vehicle; and
displaying the target information on the first image.

11. An unmanned vehicle comprising:
a first camera configured to obtain a first image using a first field of view;
a second camera configured to obtain a second image using a second field of view that is smaller than the first field of view; and
an image processor configured to detect an object from the first image, set a region of interest at the object in the first image, detect a target within the region of interest, and detect target information from the second image obtained by the second camera pointing to the region of interest from which the target is detected.

12. The unmanned vehicle of claim 11 , wherein the image processor is configured to detect, from the first image, the object within a predetermined distance.

13. The unmanned vehicle of claim 12 , wherein the image processor is configured to detect the object within the predetermined distance based on geographic information system (GIS) information about a road or a landmark detected from the first image.

14. The unmanned vehicle of claim 11 , wherein the image processor is configured to calibrate a position of the region of interest in response to a change in orientation of the first camera relative to the unmanned aerial vehicle.

15. The unmanned vehicle of claim 14 , wherein the image processor is configured to calibrate the position of the region of interest by compensating for an amount of pixel movement which corresponds to an amount of the change in the orientation of the first camera relative to the unmanned aerial vehicle.

16. The unmanned vehicle of claim 11 , wherein the image processor is configured to calibrate a position of the region of interest by tracking the object according to an object tracking method and setting the region of interest at the object that is tracked.

17. The unmanned vehicle of claim 11 , wherein the image processor is configured to determine whether the target is detected from the region of interest based on a change in pixel values around the object in the region of interest.

18. The unmanned vehicle of claim 11 , wherein the image processor is configured to display the target information on the first image.

19. An unmanned vehicle comprising:
at least one camera configured to obtain an image; and
an image processor configured to:
detect an object from the image;
set a region of interest at the object in the image;
detect a target within the region of interest by detecting a change in pixel values from the region of interest; and
adjust the region of interest in response to a change in orientation of the camera relative to the unmanned aerial vehicle,

wherein the target is positioned behind the object.

20. The unmanned vehicle of claim 19 , wherein the image processor is configured to change a position of the region of interest by compensating for an amount of pixel movement which corresponds a change in the orientation of the camera relative to the unmanned aerial vehicle.

Assignees

• Hanwha Aerospace Co Ltd

Inventors

• Song Jin Mo
• Seo Young Jin
• Park Jae Chan

Classifications

• G06V10/25 Primary

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title

• G06V10/24

  Aligning, centring, orientation detection or correction of the image · CPC title

• G06V2201/07

  Target detection · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G06T7/11

  Region-based segmentation · CPC title