System and method for three-dimensional (3D) object detection

1. A system, comprising:

a data processor; and

a 3D image processing system, executable by the data processor, the 3D image processing system being configured to:

receive image data from a camera associated with a vehicle, the image data representing an image frame;

determine at least one pixel coordinate of a two-dimensional (2D) bounding box around an object in the image frame;

determine at least one vertex of a three-dimensional (3D) bounding box around the object, wherein the 2D bounding box or the 3D bounding box is refined using Non-Maximum Suppression (NMS) method;

obtain camera calibration information associated with the camera; and

determine 3D attributes of the object using the 3D bounding box and the camera calibration information,

wherein the 3D attributes of the object comprise a length, a height, and a width of the object, and

wherein the length, the height, and the width have predefined bounds greater than a first value and less than a second value.

2. The system of claim 1 , wherein the 3D attributes of the object comprise 3D spatial location and heading of the object.

3. The system of claim 1 , wherein the camera comprises a camera lens of a type that includes a wide-angle or close-range lens, a medium-range lens, and a long-range lens.

4. The system of claim 1 , wherein the at least one vertex of the three-dimensional (3D) bounding box around the object is determined in the at least one pixel coordinate.

5. The system of claim 1 ,

wherein the 3D image processing system is further configured to obtain geological information associated with the image frame,

wherein the 3D attributes of the object are determined by the data processor further configured to:

determine the 3D attributes of the object using the 3D bounding box, the geological information, and the camera calibration information.

6. The system of claim 5 , wherein the geological information is obtained from a terrain map comprising global positioning system (GPS) locations with a height of terrain.

7. The system of claim 1 , wherein the camera calibration information comprises camera calibration matrices with a camera extrinsic matrix and a camera intrinsic matrix.

8. A method, comprising:

receiving image data from a camera associated with a vehicle, the image data representing an image frame;

determining at least one pixel coordinate of a two-dimensional (2D) bounding box around an object in the image frame;

determining at least one vertex of a three-dimensional (3D) bounding box around the object, wherein the 2D bounding box or the 3D bounding box is refined using Non-Maximum Suppression (NMS) method;

obtaining camera calibration information associated with the camera; and

determining 3D attributes of the object using the 3D bounding box and the camera calibration information,

wherein the 3D attributes of the object comprise a length, a height, and a width of the object, and

wherein the length, the height, and the width have predefined bounds greater than a first value and less than a second value.

9. The method of claim 8 , wherein the 3D bounding box around the object is a cuboid in a 3D space.

10. The method of claim 8 , wherein the 2D bounding box or the 3D bounding box is determined by deep learning method.

11. The method of claim 8 , further comprising:

obtaining geological information associated with the image frame, from a global positioning system (GPS), an accelerometer, or a WiFi triangulation, wherein the 3D attributes of the object are further determined using the geological information.

12. The method of claim 8 ,

wherein the camera calibration information comprises camera calibration matrices with a camera extrinsic matrix,

wherein the camera extrinsic matrix denotes coordinate system transformations from 3D world coordinates to 3D camera coordinates.

13. The method of claim 8 ,

wherein the camera calibration information comprises camera calibration matrices with a camera intrinsic matrix,

wherein the camera intrinsic matrix denotes coordinate system transformations from 3D camera coordinates to 2D image coordinates.

14. A non-transitory machine-useable storage medium embodying instructions which, when executed by a machine, cause the machine to:

receive image data from a camera associated with a vehicle, the image data representing an image frame;

determine at least one pixel coordinate of a two-dimensional (2D) bounding box around an object in the image frame;

determine at least one vertex of a three-dimensional (3D) bounding box around the object wherein the 2D bounding box or the 3D bounding box is refined using Non-Maximum Suppression (NMS) method;

obtain camera calibration information associated with the camera; and

determine 3D attributes of the object using the 3D bounding box and the camera calibration information,

wherein the 3D attributes of the object comprise a length, a height, and a width of the object, and

wherein the length, the height, and the width have predefined bounds greater than a first value and less than a second value.

15. The non-transitory machine-useable storage medium of claim 14 , wherein the object is over 200 meters away from the vehicle.

16. The non-transitory machine-useable storage medium of claim 14 , wherein the machine is further configured to receive point cloud data from a laser range finder or a LIDAR associated with the vehicle.

17. The non-transitory machine-useable storage medium of claim 14 , wherein the 3D bounding box has eight corners.

18. The non-transitory machine-useable storage medium of claim 14 , wherein the machine is further configured to obtain geological information associated with the image frame, from a terrain map with the height of terrain, wherein the 3D attributes of the object are further determined using the geological information.

19. The non-transitory machine-useable storage medium of claim 14 , wherein the first value is 1 meter and the second value is 50 meters.