IP Library › Granted Patent US 10,735,710
Granted Patent B2
US 10,735,710 · App. 15/700,169 · Granted Aug 4, 2020

Stereo vision image calibration method and related image capturing device

Inventors: Jian-Ping Fang (New Taipei, TW); Sheng-Yuan Chen (New Taipei, TW)
Assignee: VIVOTEK INC.
H04N13/128G06K9/03G06T7/85H04N13/111H04N13/239H04N13/246G06K2209/40H04N2013/0081
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,735,710
App. No.
15/700,169
Granted
Aug 4, 2020
Kind
B2
Abstract

A stereo vision image calibration method is applied to an image capturing device having a first camera, a second camera and an image rectifying function. The first camera and the second camera are arranged along a first direction. The first camera and the second camera are respectively utilized to acquire a first image and a second image. The image rectifying function rectifies the first image and the second image by a stereo vision parameter. The stereo image calibration method includes selecting the rectified first image and the rectified second image to compute a global disparity vector between the adjust image and the reference image, and if a vector component of the global disparity vector along a second direction which is different from the first direction has non-zero value, processing a stereo vision calibration according to the vector component.

Claims (28)

1. A stereo vision image calibration method, applied to an image capturing device having a first camera, a second camera and an operational processor with an image rectifying function, the first camera and the second camera being arranged along a first direction and utilized to respectively capture a first image and a second image, the image rectifying function being adapted to rectify the first image and the second image by a stereo vision parameter built in production to generate a rectified first image and a rectified second image, the stereo vision image calibration method comprising:

setting the rectified first image as a reference image and setting the rectified second image as an adjusting image;

moving the adjusting image relative to the reference image and defining an overlapped region and at least one non-overlapped region between the adjusting image and the reference image in each movement;

compute pixel value difference between overlapped pixels within each overlapped region for deciding a global disparity vector; and

dividing the global disparity vector into two vector components respectively in the first direction and a second direction different from arrangement direction of the first camera and the second camera for processing a stereo vision calibration along the vector component in the second direction while the vector component in the second direction has a non-zero value.

2. The stereo vision image calibration method of claim 1 , further comprising:

setting a searching range on the reference image;

moving the adjusting image relative to the reference image within the searching range to acquire a plurality of disparity motion vectors and to compute a similar value corresponding to each of the plurality of disparity motion vectors; and

utilizing one of the plurality of disparity motion vectors with a maximum similar value to acquire the global disparity vector between the rectified first image and the rectified second image.

3. The stereo vision image calibration method of claim 2 , wherein the searching range is a rectangle, and the plurality of disparity motion vectors cover all position of the searching range.

4. The stereo vision image calibration method of claim 2 , wherein the similar value is acquired by averaged error computation of overlapped images between the adjusting image and the reference image while the adjusting image is moved relative to the reference image according to the disparity motion vector.

5. The stereo vision image calibration method of claim 2 , wherein the similar value is acquired by image correlation measurement.

6. The stereo vision image calibration method of claim 2 , wherein the similar value is acquired by characteristic point computation.

7. The stereo vision image calibration method of claim 1 , wherein processing the stereo vision calibration according to the vector component of the second direction different from the first direction comprises:

varying a cropping range of at least one of the first camera and the second camera of the image capturing device.

8. The stereo vision image calibration method of claim 1 , wherein processing the stereo vision calibration according to the vector component of the second direction different from the first direction comprises:

varying the stereo vision parameter of the image rectifying function.

9. An image capturing device with a stereo vision image calibration function, the image capturing device comprising:

a first camera adapted to capture a first image;

a second camera adapted to capture a second image having a visual angle different from the first image; and

an operational processor with an image rectifying function for rectifying the first image and the second image as a rectified first image and a rectified second image and adapted to set the rectified first image as a reference image and set the rectified second image as an adjusting image, to move the adjusting image relative to the reference image and defining an overlapped region and at least one non-overlapped region between the adjusting image and the reference image in each movement, to compute pixel value difference between overlapped pixels within each overlapped region for deciding a global disparity vector, and to divide the global disparity vector into two vector components respectively in the first direction and a second direction different from arrangement direction of the first camera and the second camera for processing a stereo vision calibration along the vector component in the second direction while the vector component in the second direction has a non-zero value.

10. The image capturing device of claim 9 , wherein the operational processor is further adapted to set a searching range on the reference image, to move the adjusting image relative to the reference image within the searching range to acquire a plurality of disparity motion vectors and to compute a similar value corresponding to each of the plurality of disparity motion vectors, and to utilize one of the plurality of disparity motion vectors with a maximum similar value to acquire the global disparity vector between the rectified first image and the rectified second image.

11. The image capturing device of claim 10 , wherein the searching range is a rectangle, and the plurality of disparity motion vectors cover all position of the searching range.

12. The image capturing device of claim 10 , wherein the similar value is acquired by averaged error computation of overlapped images between the adjusting image and the reference image while the adjusting image is moved relative to the reference image according to the disparity motion vector.

13. The image capturing device of claim 10 , wherein the similar value is acquired by image correlation measurement.

14. The image capturing device of claim 10 , wherein the similar value is acquired by characteristic point computation.

15. The image capturing device of claim 9 , wherein the operational processor is further adapted to vary a cropping range of at least one of the first camera and the second camera of the image capturing device.

16. The image capturing device of claim 9 , wherein the operational processor is further adapted to vary the stereo vision parameter of the image rectifying function.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 10, 2017
From: FANG, JIAN-PING; CHEN, SHENG-YUAN
To: VIVOTEK INC.
Reel/Frame 043540/0426 →
Priority Claims (1)
TW 105132338 A · Oct 6, 2016 · national
Continuity (1)
Related Publication 20180103244A1 · Apr 12, 2018
Cited By (1)
US 12,657,772