Bowl-shaped imaging system

• US 10,210,597 B2
• Filed: 12/19/2013
• Issued: 02/19/2019
• Est. Priority Date: 12/19/2013
• Status: Active Grant

• Current Assignee: Tahoe Research Limited (f/k/a Learndale Limited) (Vector Capital Corporation)
• Original Assignee: Intel Corporation
• Inventors: Scholl, Kay-Ulrich, Natroshvili, Koba
• Primary Examiner(s): Kalapodas, Dramos I
• Application Number:
  US14/367,987
• Publication Number:
  US 20150178884A1
• Time in Patent Office: 1,888 Days
• CPC Class Codes: B60R 1/00 Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
• CPC Class Codes: B60R 1/27 providing all-round vision, e.g. using omnidirectional cameras
• CPC Class Codes: B60R 1/28 with an adjustable field of view
• CPC Class Codes: B60R 2300/105 using multiple cameras
• CPC Class Codes: B60R 2300/303 using joined images, e.g. multiple camera images
• CPC Class Codes: B60R 2300/802 for monitoring and displaying vehicle exterior blind spot views
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 3/047 Fisheye or wide-angle transformations
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 10/247 by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: H04N 23/698 for achieving an enlarged field of view, e.g. panoramic image capture
• CPC Class Codes: H04N 5/265 Mixing

Abstract

A method for flexibly sintering rare earth permanent magnetic alloy comprises: (1) weighing fine powder of rare earth permanent magnetic alloy, loading the fine powder in molds, and orientedly compacting the fine powder in a press machine and in inert atmosphere to obtain blanks and loading the blanks into charging boxes; (2) after air between the second conveying vehicle and the first isolating valve of the glove box is replaced with inert gas, opening the two isolating valves connected with each other; wherein after a first rolling wheel transmission in the second conveying vehicle transfers the charging tray into the first chamber of the glove box, the two isolating valves are closed, and the second conveying vehicle leaves; (3) after a first conveying vehicle is coupled with a third isolating valve at an end of the second chamber, locking two matching flanges of the two isolating valves tightly; (4) after the first conveying vehicle is coupled with an isolating valve of a sintering furnace, locking matching flanges tightly; and (5) after the sintering furnace is evacuated to a vacuum degree more than 50 Pa, or the sintering furnace is filled with protective gas, processing the blanks with heating and heat preservation according to a preset process curve; wherein the blanks are sintered at a highest temperature of 1200° C. The present invention significantly increases performance of magnets.

Claims

1. A computing system for utilizing a bowl-shaped image, the computing system comprising:

a first fisheye camera to capture a first fisheye image including a first scene;

a second fisheye camera to capture a second fisheye image including a second scene overlapping the first scene at an overlapping region;

a feature detection module to perform feature detection on the first fisheye image and the second fisheye image to detect one or more features located in the overlapping region;

a feature matching module to perform feature matching on the detected features to determine one or more matched features of the first fisheye image and the second fisheye image;

a seam determination module to (i) determine a first seam of the first fisheye image in the overlapping region based on the matched features of the first fisheye image and the second fisheye image, (ii) determine a second seam of the second fisheye image in the overlapping region based on the matched features of the first fisheye image and the second fisheye image, (iii) project the first fisheye image and the second fisheye image onto a virtual bowl-shaped projection surface to generate corresponding projected images, and (iv) determine a third seam in an overlapping region of the corresponding projected images based on corresponding projections of the first seam and the second seam;

an image synthesis module to generate a combined image of the first fisheye image and the second fisheye image by a combination of the projections of the first and second fisheye images at the determined third seam; and

a bowl-generation module to generate a portion of a bowl-shaped image based on the combined image.

2. The computing system of claim 1, wherein the feature matching module is further to determine a fundamental matrix of a camera system including the first fisheye camera the second fisheye camera;

wherein the fundamental matrix is based on the geometry of the camera system; and

wherein to perform feature matching comprises to filter feature match candidates based on the fundamental matrix.

3. The computing system of claim 2, wherein to perform feature matching comprises to generate the fundamental matrix by minimization of an expression

4. The computing system of claim 1, wherein to determine the third seam comprises to determine a third seam as an average seam of the corresponding projections of the first seam and the second seam.

5. The computing system of claim 1, wherein the image synthesis module is further to perform at least one of interpolation or extrapolation of image pixels located between the corresponding projections of the first and second seams in the overlapping region.

6. The computing system of claim 1, wherein the bowl-generation module comprises:

a bowl geometry module to (i) determine a major semi-axis and a minor semi-axis of a vertical slice of a virtual bowl-shaped projection surface to be generated, (ii) determine, for each horizontal slice of the virtual bowl-shaped projection surface, a first semi-axis of the corresponding horizontal slice based on the major semi-axis and the minor semi-axis of the vertical slice, and (iii) determine, for each horizontal slice of the virtual bowl-shaped projection surface, a second semi-axis of the corresponding horizontal slice perpendicular to the first semi-axis based on an adaptive ratio between the first semi-axis and the second semi-axis of the corresponding horizontal slice, wherein the adaptive ratio for the corresponding horizontal slice is different from each adaptive ratio associated with the other horizontal slices, wherein the top horizontal slice of the virtual bowl-shaped projection surface has a smaller first semi-axis than at least one other horizontal slice of the virtual bowl-shaped projection surface; and

a bowl synthesis module to generate the virtual bowl-shaped projection surface based on a combination of the horizontal slices.

7. The computing system of claim 6, further comprising a bowl warping module to smooth a section of the generated virtual bowl-shaped projection surface adjacent a ground plane of the virtual bowl-shaped projection surface.

8. The computing system of claim 6, wherein:

the computing system comprises an in-vehicle computing system of a vehicle;

the bowl geometry module is further to determine a horizontal offset of the corresponding horizontal slice, wherein the horizontal offset is less than a length of the vehicle; and

wherein to determine the first semi-axis of the corresponding horizontal slice comprises to determine, for each horizontal slice, the first semi-axis of the corresponding horizontal slice based on the horizontal offset.

9. The computing system of claim 8, wherein the horizontal offset is greater than half the length of the vehicle.

10. The computing system of claim 8, wherein to determine the first semi-axis of the corresponding horizontal slice comprises to determine, for each horizontal slice, the first semi-axis of the corresponding horizontal slice as

11. The computing system of claim 6, wherein the computing system comprises an in-vehicle computing system of a vehicle;

and

the adaptive ratio changes linearly between adjacent horizontal slices, the adaptive ratio is equal to one for the top horizontal slice, and the adaptive ratio is a ratio of a length of the vehicle and a width of the vehicle for the bottom horizontal slice.

12. The computing system of claim 6, wherein the top horizontal slice of the virtual bowl-shaped projection surface has a circular geometric shape and the bottom horizontal slice of the virtual bowl-shaped projection surface has a non-circular elliptical geometric shape.

13. The computing system of claim 6, wherein to determine the second semi-axis of the corresponding horizontal slice comprises to determine, for each horizontal slice, the second semi-axis of the corresponding horizontal slice as a ratio of the first semi-axis of the corresponding horizontal slice and the adaptive ratio for the corresponding horizontal slice.

14. The computing system of claim 6, further comprising a display module to:

project an image onto the generated virtual bowl-shaped projection surface to generate the portion of the bowl-shaped image; and

display the portion of the bowl-shaped image on a display of the computing system.

15. The computing system of claim 14, wherein to display the portion of the bowl-shaped image comprises to display a segment of the bowl-shaped image corresponding with a field of view of a virtual camera of a vehicle.

30. The computing system of claim 1, wherein the overlapping region of the corresponding projected images containing the third seam is defined by the first seam, the second seam, and one or more edges of the virtual bowl-shaped projection surface.

16. One or more non-transitory machine-readable storage media comprising a plurality of instructions stored thereon that, in response to execution by a computing device, cause the computing device to:

receive a first fisheye image capturing a first scene and a second fisheye image capturing a second scene overlapping with the first scene at an overlapping region;

perform feature detection on the first fisheye image and the second fisheye image to detect one or more features located in the overlapping region;

perform feature matching on the detected features to determine one or more matched features of the first fisheye image and the second fisheye image;

determine a first seam of the first fisheye image in the overlapping region based on the matched features of the first fisheye image and the second fisheye image;

determine a second seam of the second fisheye image in the overlapping region based on the matched features of the first fisheye image and the second fisheye image;

project the first fisheye image and the second fisheye image onto a virtual bowl-shaped projection surface to generate corresponding projected images;

determine a third seam in an overlapping region of the corresponding projected images based on corresponding projections of the first seam and the second seam;

generate a combined image of the first fisheye image and the second fisheye image by a combination of the projections of the first and second fisheye images at the determined third seam; and

generate a portion of a bowl-shaped image based on the combined image.

22. The one or more non-transitory machine-readable storage media of claim 16, wherein the plurality of instructions further causes the computing device to determine a fundamental matrix of a camera system including the first fisheye camera the second fisheye camera,

wherein the fundamental matrix is based on the geometry of the camera system;

and

wherein to perform feature matching comprises to filter feature match candidates based on the fundamental matrix.

23. The one or more non-transitory machine-readable storage media of claim 16, wherein to determine the third seam comprises to determine a third seam as an average seam of the corresponding projections of the first seam and the second seam.

24. The one or more non-transitory machine-readable storage media of claim 16, wherein the plurality of instructions further causes the computing device to perform at least one of interpolation or extrapolation of image pixels located between the corresponding projections of the first and second seams in the overlapping region.

25. The one or more non-transitory machine-readable storage media of claim 16, wherein the plurality of instructions further causes the computing device to:

determine a major semi-axis and a minor semi-axis of a vertical slice of a virtual bowl-shaped projection surface to be generated;

determine, for each horizontal slice of the virtual bowl-shaped projection surface, a first semi-axis of the corresponding horizontal slice based on the major semi-axis and the minor semi-axis of the vertical slice;

determine, for each horizontal slice of the virtual bowl-shaped projection surface, a second semi-axis of the corresponding horizontal slice perpendicular to the first semi-axis based on an adaptive ratio between the first semi-axis and the second semi-axis of the corresponding horizontal slice, wherein the adaptive ratio for the corresponding horizontal slice is different from each adaptive ratio associated with the other horizontal slices, wherein the top horizontal slice of the virtual bowl-shaped projection surface has a smaller first semi-axis than at least one other horizontal slice of the virtual bowl-shaped projection surface; and

generate the virtual bowl-shaped projection surface based on a combination of the horizontal slices.

26. The one or more non-transitory machine-readable storage media of claim 25, wherein the plurality of instructions further causes the computing device to determine a horizontal offset of the corresponding horizontal slice, wherein the horizontal offset is less than a length of the vehicle;

and

wherein to determine the first semi-axis of the corresponding horizontal slice comprises to determine, for each horizontal slice, the first semi-axis of the corresponding horizontal slice based on the horizontal offset.

27. The one or more non-transitory machine-readable storage media of claim 26, wherein the horizontal offset is greater than half the length of the vehicle.

28. The one or more non-transitory machine-readable storage media of claim 25, wherein the adaptive ratio changes linearly between adjacent horizontal slices, the adaptive ratio is equal to one for the top horizontal slice, and the adaptive ratio is a ratio of a length of the vehicle and a width of the vehicle for the bottom horizontal slice.

29. The one or more non-transitory machine-readable storage media of claim 25, wherein the top horizontal slice of the virtual bowl-shaped projection surface has a circular geometric shape and the bottom horizontal slice of the virtual bowl-shaped projection surface has a non-circular elliptical geometric shape.

17. A method for utilizing a bowl-shaped image on a computing device, the method comprising:

receiving, by the computing device, a first fisheye image capturing a first scene and a second fisheye image capturing a second scene overlapping with the first scene at an overlapping region;

performing, by the computing device, feature detection on the first fisheye image and the second fisheye image to detect one or more features located in the overlapping region;

performing, by the computing device, feature matching on the detected features to determine one or more matched features of the first fisheye image and the second fisheye image;

determining, by the computing device, a first seam of the first fisheye image in the overlapping region based on the matched features of the first fisheye image and the second fisheye image;

determining, by the computing device, a second seam of the second fisheye image in the overlapping region based on the matched features of the first fisheye image and the second fisheye image;

projecting, by the computing device, the first fisheye image and the second fisheye image onto a virtual bowl-shaped projection surface to generate corresponding projected images;

determining, by the computing device, a third seam in an overlapping region of the corresponding projected images based on corresponding projections of the first seam and the second seam;

generating, by the computing device, a combined image of the first fisheye image and the second fisheye image by a combination of the projections of the first and second fisheye images at the determined third seam; and

generating, by the computing device, a portion of a bowl-shaped image based on the combined image.

18. The method of claim 17, further comprising:

determining a region of interest in one of the first fisheye image or the second fisheye image;

generating a rectilinear image by (i) projecting the region of interest onto a virtual hemispherical display surface to generate a hemispherical image region and (ii) projecting the hemispherical image region onto a plane perpendicular to a point in the hemispherical image region; and

classifying an object in the rectilinear image.

19. The method of claim 18, wherein determining the region of interest comprises utilizing an optical flow algorithm to identify a moving object, the region of interest corresponding with an image region including the moving object.

20. The method of claim 18, wherein determining the region of interest comprises performing object detection on at least one of the first fisheye image or the second fisheye image to identify an object of interest, wherein the region of interest corresponds with the identified object of interest.

21. The method of claim 18, wherein classifying the object comprises:

retrieving an object profile from a memory of the computing device; and

comparing an object detected in the rectilinear image to the retrieved object profile.