CN111220093A - Trolley image identification method and device with three-dimensional vision and storage medium - Google Patents

Trolley image identification method and device with three-dimensional vision and storage medium Download PDF

Info

Publication number
CN111220093A
CN111220093A CN202010112178.0A CN202010112178A CN111220093A CN 111220093 A CN111220093 A CN 111220093A CN 202010112178 A CN202010112178 A CN 202010112178A CN 111220093 A CN111220093 A CN 111220093A
Authority
CN
China
Prior art keywords
phase
trolley
image recognition
industrial
dimensional vision
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010112178.0A
Other languages
Chinese (zh)
Inventor
龙佳乐
陈润松
郑英明
韩宏志
凌钟发
廖霞秦
张建民
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuyi University
Original Assignee
Wuyi University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wuyi University filed Critical Wuyi University
Priority to CN202010112178.0A priority Critical patent/CN111220093A/en
Priority to PCT/CN2020/081651 priority patent/WO2021168972A1/en
Publication of CN111220093A publication Critical patent/CN111220093A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
    • G01B11/25—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures by projecting a pattern, e.g. one or more lines, moiré fringes on the object
    • G01B11/254—Projection of a pattern, viewing through a pattern, e.g. moiré
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
    • G01B11/03—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring coordinates of points
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geometry (AREA)
  • Theoretical Computer Science (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a trolley image recognition method with three-dimensional vision, a device and a storage medium, comprising the following steps: after detecting an object to be detected, a ranging sensor arranged on the trolley sends a first signal to an upper computer; the upper computer sends a second signal to start the industrial projector; the industrial projector sequentially projects a plurality of fringe patterns to irradiate an object to be measured, and when the industrial projector changes the projected fringe patterns once, a third signal is sent to the industrial camera; after receiving the third signal, the industrial camera is started and shoots an object to be detected, and a plurality of deformation fringe patterns are acquired; the industrial camera sends the plurality of deformed stripe patterns to the upper computer; and the upper computer calculates the plurality of deformed fringe patterns by adopting a three-dimensional shape measurement algorithm to obtain the three-dimensional shape information of the object.

Description

Trolley image identification method and device with three-dimensional vision and storage medium
Technical Field
The invention relates to the field of image recognition, in particular to a trolley image recognition method with three-dimensional vision, a trolley image recognition device with three-dimensional vision and a storage medium.
Background
At present, most factories still use a manual forklift for carrying, so that the production efficiency is greatly reduced, and the manufacturing cost is improved. Although AGV dolly assisted transport appears now, AGV transport dolly intelligence in the market traveles at single route, and the object of transport specification singleness if change object specification then probably can't successfully transport, and in the face of the diversified product of production factory, then need drop into a large amount of transport dollies and just can realize intelligent operation, has increased the cost like this and has also caused the excessive consumption of resource.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides the trolley image recognition method with three-dimensional vision, which can enable the trolley to have vision, autonomously measure the three-dimensional information of an object, has an autonomous classification carrying function, and has strong compatibility and higher practicability compared with the traditional AGV.
The invention also provides a device for automatically identifying the three-dimensional visual trolley image by applying the trolley image identification method with the three-dimensional visual sense.
The invention also provides a storage medium for automatically carrying out three-dimensional visual trolley image recognition by applying the trolley image recognition method with three-dimensional visual sense.
According to the embodiment of the first aspect of the invention, the trolley image identification method with three-dimensional vision comprises the following steps: after detecting an object to be detected, a ranging sensor arranged on the trolley sends a first signal to an upper computer; the upper computer sends a second signal to start the industrial projector; the industrial projector sequentially projects a plurality of fringe patterns to irradiate an object to be measured, and when the industrial projector changes the projected fringe patterns once, a third signal is sent to the industrial camera; after receiving the third signal, the industrial camera is started and shoots an object to be detected, and a plurality of deformation fringe patterns are acquired; the industrial camera sends the plurality of deformed stripe patterns to the upper computer; the upper computer calculates the deformation fringe patterns by adopting a three-dimensional shape measurement algorithm, and the method comprises the following steps: respectively calculating phase values of pixels of two wavelengths in one period through a six-step phase shift formula, and solving to obtain a wrapped phase diagram of the phase values of the two wavelengths; respectively unfolding the wrapped phase diagram by a dual-wavelength phase unfolding method to obtain an absolute phase; and calculating the three-dimensional shape information of the object by combining the industrial projector and the industrial camera calibration data matrix C and the internal and external parameter matrix P of the industrial projector.
The trolley image recognition method with three-dimensional vision provided by the embodiment of the invention at least has the following beneficial effects: firstly, measuring the distance between the trolley and an object to be measured, starting the industrial projector to irradiate the object to be measured with a plurality of fringe patterns when the object to be measured enters a photographing range, starting the industrial camera to photograph the object to be measured irradiated by the plurality of fringe patterns to obtain image data, and uploading the image data to an upper computer for processing. And the upper computer performs calculation analysis on the image information according to a three-dimensional shape measurement algorithm to finally obtain the three-dimensional shape information of the measured object.
According to some embodiments of the present invention, the sending a first signal to an upper computer after the ranging sensor mounted on the cart detects the object to be measured specifically includes: the distance measuring sensor monitors the distance between the trolley and the object to be measured in real time; and when the distance is smaller than a preset distance threshold value, sending the first signal to the upper computer. When the trolley moves to the position near the object to be measured, the ranging sensor sends the first signal to the upper computer, and the upper computer executes the operation of starting the industrial projector.
According to some embodiments of the invention, the fringe pattern is six fringe patterns of two different wavelengths preset by the industrial projector, and the six fringe patterns of the same wavelength have different phase shifts; the gray value of each pixel point of the fringe pattern can be expressed as:
Ipi(Xp,Yp)＝1/2+1/2sin(φp(Xp,Yp)+δpi) Wherein phip(Xp,Yp) Is the phase, delta, of a certain pixel point in the image datapiThe phase difference of each fringe pattern in the same group of fringe patterns relative to the first fringe pattern is shown. The fringe patterns are divided into two groups of six each, each having the same wavelength. The above formula can limit the relation between the pixel and the phase of each pixel point
According to some embodiments of the present invention, the six-step phase shift formula is solved to obtain the phase value of each pixel of a specific wavelength in one period, and the six-step phase shift formula is as follows:
Figure BDA0002390400200000031
wherein Ici(Xp,Yp) Is the gray value, phi, of each pixel point of the deformed fringe patternc(Xc,Yc) The amplitude is 0 to 2 pi for the phase of a certain pixel in the image data. The six-step phase shift formula can obtain the phase of each pixel point according to the gray value of each pixel point. Finally, corresponding phases under two wavelengths are obtained
According to some embodiments of the invention, the wrapped phase map is obtained by dividing the phase value of each pixel by 2 pi, resulting in the wrapped phase map having an amplitude in the range of 0 to 1. And the wrapped phase diagrams are respectively processing results obtained by irradiating the two groups of fringe patterns with different wavelengths.
According to some embodiments of the invention, the absolute phase calculation formula is as follows:
Figure BDA0002390400200000032
wherein phic(Xc,Yc) For the wrapped phase, K (Xc, Yc) is given by the following equation:
Figure BDA0002390400200000033
wherein, T1 and T2 respectively indicate the wavelength phi of six fringe patterns with two different wavelengthsc1(Xc,Yc) And phic1(Xc,Yc) Respectively the wrapped phases. The absolute phase equation can convert the wrapped phase to an absolute phase, which can be calculated from the wrapped phase map of the two wavelengths.
According to some embodiments of the present invention, the three-dimensional shape information of the object is represented by Xw, Yw, Zw, and is calculated by the following formula:
Figure BDA0002390400200000041
Figure BDA0002390400200000042
Figure BDA0002390400200000043
wherein
Figure BDA0002390400200000044
The absolute phase is the absolute phase, the industrial projector and industrial camera calibration data matrix C is a three-row four-column matrix, the industrial projector internal and external parameter matrix P is a three-row four-column matrix, Uc and Vc are coordinate matrices which are the same as the size of a shot picture, and if the size of the picture is 1024 x 1280, Uch and Vc are data matrices of 1024 x 1280
Figure BDA0002390400200000045
Figure BDA0002390400200000046
According to the formula, the three-dimensional shape information of the object is represented as Xw, Yw and Zw, and the height, width and area data of the object can be obtained.
According to the cart image recognition device with three-dimensional vision of the second aspect of the present invention, the cart image recognition method with three-dimensional vision of the first aspect of the present invention can be applied.
The trolley image recognition device with three-dimensional vision provided by the embodiment of the invention at least has the following beneficial effects: the trolley irradiates and takes a picture of the object to be measured, and calculates the data such as the phase position of the object to be measured, so as to obtain the three-dimensional shape information of the object to be measured.
The cart image recognition storage medium with three-dimensional vision according to the third aspect of the present invention can apply the cart image recognition method with three-dimensional vision according to the first aspect of the present invention.
The storage medium capable of automatically classifying the garbage according to the embodiment of the invention at least has the following beneficial effects: the trolley irradiates and takes a picture of the object to be measured, and calculates the data such as the phase position of the object to be measured, so as to obtain the three-dimensional shape information of the object to be measured. .
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flowchart of a cart image recognition method with three-dimensional vision according to a first embodiment of the present invention;
FIG. 2 is a flowchart of a three-dimensional topography measurement algorithm in the cart image recognition method with three-dimensional vision according to the first embodiment of the present invention;
fig. 3 is a schematic structural diagram of a cart image recognition apparatus with three-dimensional vision according to a second embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise explicitly defined, terms such as arrangement, connection and the like should be broadly construed, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the detailed contents of the technical solutions.
Example one
Referring to fig. 1, in one embodiment of the present invention, a cart image recognition method with three-dimensional vision is provided, wherein one embodiment includes, but is not limited to, the following steps:
and S101, sending a first signal to an upper computer after a ranging sensor arranged on the trolley detects an object to be measured.
In this embodiment, in this step, the distance between the cart and the object to be measured is first measured, and when the object to be measured enters the range in which photographing can be performed, preparation is made for subsequently starting the industrial projector to perform irradiation of a plurality of fringe patterns on the object to be measured.
And S102, the upper computer sends a second signal to start the industrial projector.
In this embodiment, the industrial projector is started to irradiate the object to be measured with a plurality of fringe patterns. The industrial projector presets a plurality of fringe patterns, the fringe patterns are six fringe patterns with two different wavelengths preset by the industrial projector, and the six fringe patterns with the same wavelength have different phase shifts. And preparing for solving and obtaining the phase value of each pixel of the specific wavelength in one period by using the six-step phase shift formula.
And S103, the industrial projector sequentially projects a plurality of fringe patterns to irradiate the object to be measured, and the industrial projector sends a third signal to the industrial camera every time the projected fringe patterns are replaced.
In this embodiment, in this step, when the industrial projector changes the projected fringe pattern every time, the third signal is sent to the industrial camera, and when the industrial camera receives the third signal, the industrial camera can start to take a picture once, so that the technical effect that the shooting opportunity is not missed can be achieved.
And step S104, after receiving the third signal, the industrial camera is started and shoots the object to be detected, and a plurality of deformation fringe patterns are acquired.
In this embodiment, in this step, a plurality of deformed fringe patterns are acquired, where each deformed fringe pattern is a fringe pattern that appears after an object to be measured is irradiated by a certain fringe pattern, and the deformed fringe patterns are a basis of a subsequent image processing step, so as to prepare for subsequently applying the six-step phase shift formula to solve and obtain a phase value of each pixel of a specific wavelength in one period.
And step S105, the industrial camera sends the plurality of deformation fringe patterns to the upper computer.
In this embodiment, in this step, the upper computer receives 12 deformed fringe patterns, and prepares for subsequent image data processing.
And S106, calculating the plurality of deformed fringe patterns by the upper computer by adopting a three-dimensional topography measurement algorithm. And finally obtaining the three-dimensional shape information of the measured object.
In this embodiment, in this step, the upper computer receives 12 deformed bar graphs uploaded from the industrial camera, respectively calculates phase values of pixels of two wavelengths in one period through a six-step phase shift formula, and solves to obtain a wrapped phase diagram of the phase values of the two wavelengths; respectively unfolding the wrapped phase diagram by a dual-wavelength phase unfolding method to obtain an absolute phase; and calculating the three-dimensional shape information of the object by combining the industrial projector and the industrial camera calibration data matrix C.
Referring to fig. 2, in step S106 of the present embodiment, the following steps may be included, but are not limited to:
in step S201, phase values of pixels of two wavelengths in one period are calculated respectively by a six-step phase shift formula.
In this embodiment, the phase value of each pixel of a specific wavelength in one period is obtained by solving the six-step phase shift formula in this step, where the six-step phase shift formula is as follows:
Figure BDA0002390400200000071
wherein Ici(Xp,Yp) Is the gray value, phi, of each pixel point of the deformed fringe patternc(Xc,Yc) The amplitude is 0 to 2 pi for the phase of a certain pixel in the image data. And calculating through the six-step phase shift formula to obtain the phase of a certain pixel point in the image data.
Step S202, solving to obtain a wrapped phase diagram of two wavelength phase values.
In this embodiment, the wrapped phase map is obtained by dividing the phase value of the phase of the certain pixel by 2 pi.
And step S203, respectively unfolding the wrapped phase diagrams by a dual-wavelength phase unfolding method to obtain absolute phases. The absolute phase calculation formula is as follows:
Figure BDA0002390400200000072
wherein phic(Xc,Yc) For the wrapped phase, K (Xc, Yc) is given by the following equation:
Figure BDA0002390400200000081
wherein, T1 and T2 respectively indicate the wavelength phi of six fringe patterns with two different wavelengthsc1(Xc,Yc) And phic1(Xc,Yc) Respectively the wrapped phases. The absolute phase equation can convert the wrapped phase to an absolute phase, which can be calculated from the wrapped phase map of the two wavelengths.
And step S204, calculating the three-dimensional shape information of the object by combining the industrial projector and the industrial camera calibration data matrix C. The three-dimensional shape information of the object in the step is calculated by the following formula:
Figure BDA0002390400200000082
Figure BDA0002390400200000083
Figure BDA0002390400200000084
wherein
Figure BDA0002390400200000085
The absolute phase is the absolute phase, the industrial projector and industrial camera calibration data matrix C is a three-row and four-column matrix, Uc and Vc are coordinate matrices which are as large as the shot picture, and if the size of the picture is 1024 x 1280, Uch and Vc are data matrices of 1024 x 1280
Figure BDA0002390400200000086
Figure BDA0002390400200000087
Figure BDA0002390400200000091
According to the formula, the three-dimensional shape information of the object is represented as Xw, Yw and Zw, and the height, width and area data of the object can be obtained.
Example two
Referring to fig. 3, a cart image recognition apparatus 300 with three-dimensional vision according to a second embodiment of the present invention includes:
the distance measurement sensor unit 301 is used for monitoring the distance between the trolley and the object to be measured;
an industrial projector unit 302 for illuminating an object to be measured;
the industrial camera acquires image data 303 for photographing an object to be measured;
and the data processing unit 304 is configured to apply a three-dimensional topography measurement algorithm to calculate a plurality of the deformed fringe patterns.
It should be noted that, since the cart image recognition apparatus with three-dimensional vision in the present embodiment is based on the same inventive concept as the cart image recognition method with three-dimensional vision in the first embodiment, the corresponding contents in the first method embodiment are also applicable to the present apparatus embodiment, and are not described in detail herein.
According to the scheme, the distance measuring sensor unit 301 monitors the distance between the trolley and the object to be measured; the industrial projector unit 302 illuminates an object to be measured; the industrial camera acquires image data unit 303 to photograph an object to be measured; the data processing unit 304 calculates a plurality of the deformed fringe patterns by using a three-dimensional topography measurement algorithm. And the trolley irradiates and shoots the object to be measured, and calculates the data such as the phase of the measured object to obtain the three-dimensional shape information of the measured object.
EXAMPLE III
The third embodiment of the present invention further provides a cart image recognition storage medium with three-dimensional vision, where the cart image recognition storage medium with three-dimensional vision stores machine executable instructions, which are executed by one or more control processors, and can cause the one or more control processors to execute the cart image recognition method with three-dimensional vision in the first embodiment of the method, for example, execute the above-described method steps S101 to S106 in fig. 1, and the method steps S201 to S204 in fig. 2, and implement the functions of the units 301 to 304 in fig. 3.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims (9)

1. A trolley image identification method with three-dimensional vision is characterized in that: the method comprises the following steps:
after detecting an object to be detected, a ranging sensor arranged on the trolley sends a first signal to an upper computer;
the upper computer sends a second signal to start the industrial projector;
the industrial projector sequentially projects a plurality of fringe patterns to irradiate an object to be measured, and when the industrial projector changes the projected fringe patterns once, a third signal is sent to the industrial camera;
after receiving the third signal, the industrial camera is started and shoots an object to be detected, and a plurality of deformation fringe patterns are acquired;
the industrial camera sends the plurality of deformed stripe patterns to the upper computer;
the upper computer calculates the deformation fringe patterns by adopting a three-dimensional shape measurement algorithm, and the method comprises the following steps:
the phase values of the pixels of two wavelengths in one period are respectively calculated by a six-step phase shift formula,
solving to obtain a wrapped phase diagram of two wavelength phase values;
respectively unfolding the wrapped phase diagram by a dual-wavelength phase unfolding method to obtain an absolute phase;
and calculating the three-dimensional shape information of the object by combining the industrial projector and the industrial camera calibration data matrix C and the internal and external parameter matrix P of the industrial projector.
2. The trolley image recognition method with three-dimensional vision as claimed in claim 1, wherein: the range finding sensor installed on the trolley sends a first signal to the upper computer after detecting an object to be measured, and the range finding sensor specifically comprises:
the distance measuring sensor monitors the distance between the trolley and the object to be measured in real time;
and when the distance is smaller than a preset distance threshold value, sending the first signal to the upper computer.
3. The trolley image recognition method with three-dimensional vision as claimed in claim 1, wherein: the fringe pattern is preset by an industrial projector and is six fringe patterns with two different wavelengths, and the six fringe patterns with the same wavelength have different phase shifts; the gray value of each pixel point of the fringe pattern can be expressed as:
Ipi(Xp,Yp)＝1/2+1/2sin(φp(Xp,Yp)+δpi) Wherein phip(Xp,Yp) Is the phase, delta, of a certain pixel point in the image datapiIs the phase difference.
4. The trolley image recognition method with three-dimensional vision as claimed in claim 1, wherein: the six-step phase shift formula is solved to obtain the phase value of each pixel of the specific wavelength in one period, and the six-step phase shift formula is as follows:
Figure FDA0002390400190000021
wherein Ici(Xp,Yp) Is the gray value, phi, of each pixel point of the deformed fringe patternc(Xc,Yc) The amplitude is 0 to 2 pi for the phase of a certain pixel in the image data.
5. The trolley image recognition method with three-dimensional vision as claimed in claim 4, wherein: the wrapped phase map is obtained by dividing the phase value of each pixel by 2 pi, and the amplitude value of the wrapped phase map is 0 to 1.
6. The trolley image recognition method with three-dimensional vision as claimed in claim 4, wherein: the absolute phase
Figure FDA0002390400190000022
The calculation formula is as follows:
Figure FDA0002390400190000023
wherein phic(Xc,Yc) For the wrapped phase, K (Xc, Yc) is given by the following equation:
Figure FDA0002390400190000024
wherein, T1 and T2 respectively indicate the wavelength phi of six fringe patterns with two different wavelengthsc1(Xc,Yc) And phic1(Xc,Yc) Respectively the wrapped phases.
7. The trolley image recognition method with three-dimensional vision as claimed in claim 1, wherein: the three-dimensional shape information of the object is represented as Xw, Yw and Zw, and is calculated by the following formula:
Figure FDA0002390400190000031
Figure FDA0002390400190000032
Figure FDA0002390400190000033
wherein
Figure FDA0002390400190000034
The industrial projector and the industrial camera calibration data matrix C are a three-row and four-column matrix, the industrial projector internal and external parameter matrix P is a three-row and four-column matrix, and Uc and Vc are coordinate matrices with the same size as the shot picture.
8. A cart image recognition apparatus with three-dimensional vision using the cart image recognition method with three-dimensional vision of claims 1 to 7, characterized in that: the method comprises the following steps:
the distance measuring sensor unit is used for monitoring the distance between the trolley and the object to be measured;
an industrial projector unit for illuminating an object to be measured;
the industrial camera acquires an image data unit and is used for photographing an object to be detected;
and the data processing unit is used for calculating the plurality of deformed fringe patterns by applying a three-dimensional topography measurement algorithm.
9. A storage medium of a three-dimensional visual trolley image recognition device is characterized in that: the storage medium of the cart image recognition apparatus with three-dimensional vision stores executable instructions of a cart image recognition method with three-dimensional vision, which are used for causing the cart image recognition apparatus with three-dimensional vision to execute the cart image recognition method with three-dimensional vision according to any one of claims 1 to 7.
CN202010112178.0A 2020-02-24 2020-02-24 Trolley image identification method and device with three-dimensional vision and storage medium Pending CN111220093A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202010112178.0A CN111220093A (en) 2020-02-24 2020-02-24 Trolley image identification method and device with three-dimensional vision and storage medium
PCT/CN2020/081651 WO2021168972A1 (en) 2020-02-24 2020-03-27 Trolley image recognition method and apparatus with three-dimensional vision, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010112178.0A CN111220093A (en) 2020-02-24 2020-02-24 Trolley image identification method and device with three-dimensional vision and storage medium

Publications (1)

Publication Number Publication Date
CN111220093A true CN111220093A (en) 2020-06-02

Family

ID=70827226

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010112178.0A Pending CN111220093A (en) 2020-02-24 2020-02-24 Trolley image identification method and device with three-dimensional vision and storage medium

Country Status (2)

Country Link
CN (1) CN111220093A (en)
WO (1) WO2021168972A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115958607A (en) * 2023-01-18 2023-04-14 上海宏滩生物科技有限公司 Nucleic acid sample transferring robot, system and transferring method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN205561781U (en) * 2016-03-08 2016-09-07 五邑大学 Quick three -dimensional measurement system based on projection of three -wavelength stripe
CN106032976A (en) * 2015-03-20 2016-10-19 五邑大学 Three-fringe projection phase unwrapping method based on wavelength selection
CN108344972A (en) * 2017-10-27 2018-07-31 江苏理工学院 Robotic vision system based on grating loss stereoscopic vision and air navigation aid
CN208239889U (en) * 2018-05-14 2018-12-14 五邑大学 A kind of intelligent vehicle control for detecting and three-dimension space image reconstructs
CN110450129A (en) * 2019-07-19 2019-11-15 五邑大学 A kind of carrying mode of progression and its transfer robot applied to transfer robot
CN110480631A (en) * 2019-07-19 2019-11-22 五邑大学 A kind of target method for carrying and its transfer robot applied to transfer robot

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101813461B (en) * 2010-04-07 2011-06-22 河北工业大学 Absolute phase measurement method based on composite color fringe projection
CN108109201B (en) * 2017-12-28 2021-11-30 深圳市易尚展示股份有限公司 Three-dimensional reconstruction method and system for complex color surface object

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106032976A (en) * 2015-03-20 2016-10-19 五邑大学 Three-fringe projection phase unwrapping method based on wavelength selection
CN205561781U (en) * 2016-03-08 2016-09-07 五邑大学 Quick three -dimensional measurement system based on projection of three -wavelength stripe
CN108344972A (en) * 2017-10-27 2018-07-31 江苏理工学院 Robotic vision system based on grating loss stereoscopic vision and air navigation aid
CN208239889U (en) * 2018-05-14 2018-12-14 五邑大学 A kind of intelligent vehicle control for detecting and three-dimension space image reconstructs
CN110450129A (en) * 2019-07-19 2019-11-15 五邑大学 A kind of carrying mode of progression and its transfer robot applied to transfer robot
CN110480631A (en) * 2019-07-19 2019-11-22 五邑大学 A kind of target method for carrying and its transfer robot applied to transfer robot

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张建民等: "三维立体视觉机械臂智能抓取分类系统的开发", 《计算机工程与应用》 *

Also Published As

Publication number Publication date
WO2021168972A1 (en) 2021-09-02

Similar Documents

Publication Publication Date Title
Fan et al. Road damage detection based on unsupervised disparity map segmentation
US10979694B2 (en) Information processing apparatus, method, and storage medium
CN106462968B (en) Method and device for calibrating a camera system of a motor vehicle
WO2022052313A1 (en) Calibration method for 3d structured light system, and electronic device and storage medium
Usamentiaga et al. Multi-camera calibration for accurate geometric measurements in industrial environments
US8781256B2 (en) Method to match color image and depth image using feature points
CN104408460B (en) A kind of lane detection and tracking detection method
Wang et al. Single-shot three-dimensional reconstruction based on structured light line pattern
CN110163904A (en) Object marking method, control method for movement, device, equipment and storage medium
US8786700B2 (en) Position and orientation measurement apparatus, position and orientation measurement method, and storage medium
JP4986679B2 (en) Non-stationary object three-dimensional image measurement apparatus, three-dimensional image measurement method, and three-dimensional image measurement program
US10311591B2 (en) Displacement detecting apparatus and displacement detecting method
EP2194725A1 (en) Method and apparatus for correcting a depth image
CN106032976B (en) The three fringe projection phase developing methods based on wavelength selection
TWI521448B (en) Vehicle identification system and method
Liu et al. Fast dimensional measurement method and experiment of the forgings under high temperature
CN112329747B (en) Vehicle parameter detection method based on video identification and deep learning and related device
CN110108253B (en) Distance measuring method, device and equipment for monocular thermal infrared imager and readable storage equipment
CN111220093A (en) Trolley image identification method and device with three-dimensional vision and storage medium
Chen et al. A self-recalibration method based on scale-invariant registration for structured light measurement systems
Chen et al. Automated exposures selection for high dynamic range structured-light 3-D scanning
CN113838043A (en) Machine vision-based quality analysis method in metal foil manufacturing
US20110007155A1 (en) Position measurement apparatus and position measuring method
KR20190105760A (en) Pantograph monitoring apparatus and method for electric railway based on image processing
Beltran et al. A comparison between active and passive 3d vision sensors: Bumblebeexb3 and Microsoft Kinect

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20200602