STRUCTURED LIGHT MATCHING OF A SET OF CURVES FROM TWO CAMERAS

• US 20160350929A1
• Filed: 02/04/2015
• Published: 12/01/2016
• Est. Priority Date: 02/05/2014
• Status: Active Grant

• Current Assignee: Creaform, Inc. (Ametek Incorporated)
• Original Assignee: Creaform, Inc. (Ametek Incorporated)
• Inventors: TUBIC, Dragan, SOUCY, Martin, GIGNAC, Olivier, CARON, Antoine Thomas
• Granted Patent: US 10,271,039 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01B 11/25 by projecting a pattern, e.g. one or more lines, moiré fringes on the object G01B11/255 takes precedence ; image analysis for depth or shape recovery G06T7/50
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/10152 Varying illumination
• CPC Class Codes: G06T 2207/20068 Projection on vertical or horizontal image axis
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 7/521 from laser ranging, e.g. using interferometry; from the projection of structured light
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: H04N 13/239 using two 2D image sensors having a relative position equal to or related to the interocular distance H04N13/243 takes precedence
• CPC Class Codes: H04N 13/246 Calibration of cameras

Abstract

A method for matching points between two images of a scene acquired by two cameras, the method including: extracting blobs from the reflection in the images and individually labelling the blobs with a unique identifier; selecting a selected epipolar plane and defining a conjugate epipolar line on each of the images; identifying plausible combinations including a light sheet label of the projected pattern and the unique identifier for a plausible blob selected from the blobs in each of the images; calculating a matching error for each of the plausible combinations; repeating the steps of selecting, identifying and calculating for at least some epipolar planes; determining a most probable combination by computing a figure of merit for the plausible combinations; identifying matching points in the frame from the most probable combination.

Claims

1. A computer-implemented method performed by at least one computer processor for matching points between two images of a scene, the method including:

retrieving two images acquired by a sensor, said two images forming a frame captured at a single relative position between the scene and the sensor, said images each containing a reflection of a projected pattern on said scene;

extracting blobs from said reflection in said images and individually labelling said blobs with a unique identifier;

selecting a selected epipolar plane from a set of epipolar planes and defining a conjugate epipolar line on each of said images;

identifying plausible combinations, said plausible combinations including a light sheet label of said projected pattern and said unique identifier for a plausible blob selected from said blobs in each of said images, said plausible blob crossing the conjugate epipolar line;

calculating a matching error for each of the plausible combinations;

repeating said steps of selecting, identifying and calculating for each epipolar plane of said set of epipolar planes;

determining a most probable combination by computing a figure of merit for said plausible combinations using said matching error for each epipolar plane of said set of epipolar planes;

identifying matching points in said frame from said most probable combination;

generating an output identifying said matching points in said frame.

2. The method as claimed in claim 1, wherein said sensor has two cameras and a light projector unit, said projected pattern being provided by said light projector unit projecting at least one sheet of light onto said scene, the cameras and the light projector unit being calibrated in a common coordinate system.

3. The method as claimed in any one of claim 1, further comprising validating said matching points to discard said matching points if said figure of merit fails to meet a quality of match threshold.

4. The method as claimed in claim 1, further comprising repeating said computer-implemented method for a plurality of frames.

5. The method as claimed in claim 1, further comprising calculating sets of 3D points using said matching points in said frame.

6. The method as claimed in claim 5, further comprising estimating a position of the sensor at each frame to integrate said 3D points in a common coordinate system, wherein said estimating said position of the sensor includes using at least one of targets affixed to said scene, a geometry of said scene and a texture of said scene.

7. The method as claimed in claim 5, further comprising exploiting the images for said calculating said sets of 3D points to obtain segments of 3D curves.

11. A computer program product comprising a computer readable memory storing computer executable instructions thereon that when executed by at least one computer processor perform the method steps of claim 1.

8. A system for matching points between two images of a scene, including:

a sensor including

a light projector unit projecting at least one sheet of light onto said scene thereby providing a projected pattern on said scene; and

two cameras for acquiring said two images of said scene, said two images forming a frame captured at a single relative position between the scene and the sensor, said images each containing a reflection of said projected pattern on said scene;

wherein the cameras and the light projector unit are calibrated in a common coordinate system; and

at least one computer processor in electronic communications with said sensor for

retrieving said two images acquired by said cameras;

extracting blobs from said reflection in said images and individually labelling said blobs with a unique identifier;

selecting a selected epipolar plane from a set of epipolar planes and defining a conjugate epipolar line on each of said images;

identifying plausible combinations, said plausible combinations including a light sheet label of said projected pattern and said unique identifier for a plausible blob selected from said blobs in each of said images, said plausible blob crossing the conjugate epipolar line;

calculating a matching error for each of the plausible combinations;

repeating said steps of selecting, identifying and calculating for each epipolar plane of said set of epipolar planes;

determining a most probable combination by computing a figure of merit for said plausible combinations using said matching error for each epipolar plane of said set of epipolar planes; and

identifying matching points in said frame from said most probable combination;

at least one computer output in electronic communications with said processor for generating an output identifying said matching points in said frame.

9. The system as claimed in claim 8, wherein said light projector unit includes two light projectors each projecting at least one sheet of light onto said scene, said projected pattern being provided by a single one of said two light projectors at each frame and said projected pattern differing for each of said two light projectors.

10. The system as claimed in claim 8, wherein said at least one sheet of light is a plane of light.

12. A computer readable memory having recorded thereon statements and instructions for execution by at least one computer processor, said statements and instructions comprising:

code means for retrieving two images acquired by a sensor, said two images forming a frame captured at a single relative position between the scene and the sensor, said images each containing a reflection of a projected pattern on said scene;

code means for extracting blobs from said reflection in said images and individually labelling said blobs with a unique identifier;

code means for selecting a selected epipolar plane from a set of epipolar planes and defining a conjugate epipolar line on each of said images;

code means for identifying plausible combinations, said plausible combinations including a light sheet label of said projected pattern and said unique identifier for a plausible blob selected from said blobs in each of said images, said plausible blob crossing the conjugate epipolar line;

code means for calculating a matching error for each of the plausible combinations;

code means for repeating said steps of selecting, identifying and calculating for each epipolar plane of said set of epipolar planes;

code means for determining a most probable combination by computing a figure of merit for said plausible combinations using said matching error for each epipolar plane of said set of epipolar planes;

code means for identifying matching points in said frame from said most probable combination;

code means for generating an output identifying said matching points in said frame.