CAMERA MODELING SYSTEM

• US 20150288878A1
• Filed: 03/30/2015
• Published: 10/08/2015
• Est. Priority Date: 04/03/2014
• Status: Active Grant

• Current Assignee: Hanwha Vision Company Limited (Hanwha Corporation)
• Original Assignee: Samsung Techwin Co., Ltd. (Hanwha Corporation)
• Inventors: BAE, Soonmin, HONG, Hana
• Granted Patent: US 10,348,961 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof

Abstract

A camera modeling system. The camera modeling system includes: a vanishing point detecting module configured to detect, from at least one reference detection object existing in a detection region, a first vanishing point and a second vanishing point; a view mode determining module configured to determine a camera view mode on the basis of a distance from a first position in the detection region to the first vanishing point and a distance from the first position to the second vanishing point; and a camera modeling module configured to select a camera modeling mode corresponding to the determined camera view mode and perform camera modeling through the selected camera modeling mode.

Claims

1. A camera modeling system comprising:

a vanishing point detecting module configured to detect, from at least one reference detection object existing in a detection region, a first vanishing point and a second vanishing point;

a view mode determining module configured to determine a camera view mode on the basis of a distance from a first position in the detection region to the first vanishing point and a distance from the first position to the second vanishing point; and

a camera modeling module configured to select a camera modeling mode corresponding to the determined camera view mode and perform camera modeling through the selected camera modeling mode.

2. The camera modeling system of claim 1, wherein the vanishing point detecting module is configured to detect the first and second vanishing points from a plurality of reference detection objects and is further configured to surround each reference detection object with a respective box;

the first vanishing point is derived from intersection points of straight lines connecting correspondent points of at least one pair of boxes among the boxes; and

the second vanishing point is an intersection point of straight lines connecting tops and bottoms of the boxes respectively.

3. The camera modeling system of claim 1, wherein the first position is a center of the detection region.

4. The camera modeling system of claim 1, wherein the view mode determining module is further configured to determine the camera view mode according to a difference between the distance from the first position to the first vanishing point and the distance from the first position to the second vanishing point.

5. The camera modeling system of claim 1, wherein the camera view mode includes one from among a side-view mode, a top-view mode, and a uniform-view mode.

6. The camera modeling system of claim 5, wherein the camera modeling module is further configured to:

perform the camera modeling by selecting the camera modeling mode as an adaptive parameter determination mode when the camera view mode is the side-view mode;

perform the camera modeling by selecting the camera modeling mode as a direct parameter determination mode when the camera view mode is the top-view mode; and

perform the camera modeling by selecting the camera modeling mode as the adaptive parameter determination mode, the direct parameter determination mode, or a combination of the adaptive parameter determination mode and the direct parameter determination mode when the camera view mode is the uniform-view mode.

7. The camera modeling system of claim 5, wherein the uniform-view mode includes one from among a uniform-view mode close to the side-view mode and a uniform-view mode close to the top-view mode.

8. The camera modeling system of claim 7, wherein the camera modeling module is further configured to:

perform the camera modeling by selecting the camera modeling mode as an adaptive parameter determination mode when the camera view mode is the uniform-view mode close to the side-view mode; and

perform the camera modeling by selecting the camera modeling mode as a direct parameter determination mode when the camera view mode is the uniform-view mode close to the top-view mode.

9. A camera modeling method comprising:

detecting a first vanishing point and a second vanishing point from a plurality of reference detection objects existing in a detection region;

determining a camera view mode on the basis of a distance from a first position in the detection region to the first vanishing point and a distance from the first position to the second vanishing point; and

selecting a camera modeling mode corresponding to the determined camera view mode and performing camera modeling through the selected camera modeling mode.

10. An apparatus comprising:

a processor configured to;

identify an object in a detection region as a reference detection object that provides orientation information relative to a surface;

detect a first vanishing point based on the reference detection object;

detect a second vanishing point based on the reference detection object;

detect a first distance between a first point in the detection region and the first vanishing point;

detect a second distance between the first point and the second vanishing point; and

determine an orientation of a camera capturing the detection region based on the first distance and the second distance.

11. The apparatus according to claim 10, wherein the processor is further configured to determine a view mode of the camera according to the determined orientation of the camera.