Positioning and measuring system based on flexible feature image scale

• US 10,475,205 B2
• Filed: 11/22/2017
• Issued: 11/12/2019
• Est. Priority Date: 09/13/2017
• Status: Active Grant

• Current Assignee: National Tsing Hua University
• Original Assignee: National Tsing Hua University
• Inventors: Tsai, Hung-Yin, Wu, Yu-Chen, Pan, Wei-Cheng
• Primary Examiner(s): Entezari, Michelle M
• Application Number:
  US15/821,336
• Publication Number:
  US 20190080469A1
• Time in Patent Office: 720 Days
• Field of Search: None
• CPC Class Codes: B23Q 17/249 using image analysis, e.g. for radar, infrared or array camera images
• CPC Class Codes: G01B 11/002 for measuring two or more coordinates
• CPC Class Codes: G01B 11/005 coordinate measuring machines
• CPC Class Codes: G01B 11/022 by means of tv-camera scanning
• CPC Class Codes: G01B 11/24 for measuring contours or curvatures
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 30/144 using a slot moved over the image; using discrete sensing elements at predetermined points; using automatic curve following means

Abstract

A positioning and measuring system includes: an image capturing device performing image capturing operations on an object; a driving mechanism mechanically connected to one or both of the image capturing device and the object to cause a relative movement between the image capturing device and the object; and a processor electrically connected to the image capturing device and the driving mechanism and performing steps of: controlling the image capturing device to capture N portions of the object to generate N images before and after controlling the driving mechanism to cause M relative movements between the object and the image capturing device; and extracting feature points of each of the N images corresponding to unique surface morphology of the object and respectively performing cross-image feature point matching according to the feature points of every neighboring two of the N images to obtain information of the M relative movements.

Claims

1. A positioning and measuring system, comprising:

an image capturing device performing image capturing operations on an object;

a driving mechanism mechanically connected to one or both of the image capturing device and the object to cause a relative movement between the image capturing device and the object; and

a processor, which is electrically connected to the image capturing device and the driving mechanism and performs steps of;

(a) controlling the image capturing device to capture N portions of the object to generate N images before and after controlling the driving mechanism to cause M relative motions between the object and the image capturing device, where N is a positive integer greater than or equal to 2, M is equal to (N−

1), and neighboring two of the N images partially overlap with each other;

(b) extracting feature points of each of the N images, and respectively performing cross-image feature point matching according to the feature points of every neighboring two of the N images to obtain information of the M relative motions, wherein the feature points correspond to unique surface morphology of the object; and

(c) detecting whether each of the N images contains a boundary of the object, selecting two images of the N images containing the two boundaries of the object that are seen at opposite sides of the two images as two boundary images of the object, and calculating a distance between the two opposite boundaries of the object inside the two boundary images according to the two boundary images and information of an accumulated motion of the relative motions corresponding to the two boundary images of the object in a distance measuring mode, wherein the distance is obtained by adding two partial lengths corresponding to the object in the two boundary images to lengths of the accumulated motion of the images covering the two boundary images.

2. The positioning and measuring system according to claim 1, further comprising a platform supporting the object, wherein the driving mechanism drives the object to generate the M relative motions through the platform.

3. The positioning and measuring system according to claim 1, further comprising a man-machine interface, which is electrically connected to the processor and receives a positioning point inputted by a user, wherein the processor performs the cross-image feature point matching according to the positioning point.

4. The positioning and measuring system according to claim 3, wherein the positioning point is different from the feature points.

5. The positioning and measuring system according to claim 1, wherein the information of the M relative motions comprises one or both of translation information and rotation information.

6. The positioning and measuring system according to claim 1, wherein in a positioning mode, the processor further performs steps of:

(d) judging whether the information of the M relative motions reaches required set information, and controlling the driving mechanism to cause an additional relative motion between the object and the image capturing device if the information of the M relative motions does not reach the required set information; and

(e) repeating steps (a), (b) and (d) until the information of the M relative motions reaches the required set information.

7. The positioning and measuring system according to claim 1, wherein the processor further performs, before the step (a), steps of:

(a1) controlling the image capturing device to capture a calibration sheet with a magnification power to obtain a calibration sheet image, wherein the image capturing device captures the calibration sheet and the object with the magnification power; and

(a2) processing the calibration sheet image to obtain a dimension of one pixel, wherein the processor further determines a dimension corresponding to the information of the M relative motions according to the information of the M relative motions and the dimension of the pixel.

8. A positioning and measuring system, comprising:

an image capturing device performing image capturing operations on an object;

a driving mechanism mechanically connected to one or both of the image capturing device and the object to cause a relative movement between the image capturing device and the object; and

a processor, which is electrically connected to the image capturing device and the driving mechanism and performs steps of;

(a) controlling the image capturing device to capture N portions of the object to generate N images before and after controlling the driving mechanism to cause M relative motions between the object and the image capturing device, where N is a positive integer greater than or equal to 2, M is equal to (N−

1), and neighboring two of the N images partially overlap with each other; and

(b) extracting feature points of each of the N images, and respectively performing cross-image feature point matching according to the feature points of every neighboring two of the N images to obtain information of the M relative motions, wherein the feature points correspond to unique surface morphology of the object,

wherein the processor further performs, before the step (a), steps of;

(a1) controlling the image capturing device to capture a calibration sheet with a magnification power to obtain a calibration sheet image, wherein the image capturing device captures the calibration sheet and the object with the magnification power; and

(a2) processing the calibration sheet image to obtain a dimension of one pixel, wherein the processor further determines a dimension corresponding to the information of the M relative motions according to the information of the M relative motions and the dimension of the pixel,

wherein in the step (a1), the processor controls the image capturing device to capture the calibration sheet with multiple focal lengths to obtain multiple focusing images, transforms the focusing images into a frequency domain to obtain multiple spectrograms, selects one of the spectrograms, which has a most obvious signal presented in an intermediate frequency portion, and captures the calibration sheet with the focal length corresponding to the spectrogram to obtain the calibration sheet image.