CN112489041B - Ship liquid container defect detection method and system based on monocular vision - Google Patents
Ship liquid container defect detection method and system based on monocular vision Download PDFInfo
- Publication number
- CN112489041B CN112489041B CN202011504088.2A CN202011504088A CN112489041B CN 112489041 B CN112489041 B CN 112489041B CN 202011504088 A CN202011504088 A CN 202011504088A CN 112489041 B CN112489041 B CN 112489041B
- Authority
- CN
- China
- Prior art keywords
- liquid container
- displacement
- image
- tracer particles
- tracer
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
Abstract
The invention provides a ship liquid container defect detection method based on monocular vision, which comprises the steps of uniformly putting a plurality of tracer particles into a liquid container, and continuously collecting a multi-frame detection image comprising a plurality of tracer particle positions in a first time interval; sequentially extracting displacement tracks of the trace particles between adjacent detection images by using a characteristic point tracking algorithm; superposing the corresponding continuous displacement tracks to obtain a displacement track image of the tracer particles in a first time interval; and judging whether a defect area exists in the liquid container or not according to the trace of the tracer particles in the displacement trace image and the position information of the defect area in the liquid container. The method and the system can convert the technology of measuring the fluid by the tracer particles into the ship liquid container, and realize the early detection of the micro cracks in the ship static liquid container.
Description
Technical Field
The invention belongs to the field of internal anomaly detection of large equipment, and particularly relates to a ship liquid container defect detection method and system based on monocular vision.
Background
The state of a ship power system comprising a plurality of large liquid containers such as various water tanks, condensers, lubricating oil tanks and the like is related to the overall operation safety of an electromechanical system of a ship. Defects of such liquid containers, such as leakage, dirt, etc., may affect the operational effectiveness of the liquid container. Currently, for the defect conditions of leakage, the water level is generally monitored by a water level sensor, but when liquid continuously enters the container, the tiny leakage in the container cannot be measured, and more needs to be checked manually. In the case of defects such as the accumulation of internal dirt, manual inspection is also possible only when the vessel is out of service.
At present, a particle image measurement technique PIV is a non-contact measurement method for accurately measuring the fluid velocity by releasing trace particles in a fluid. The measuring method has the characteristics of high precision, transient state, non-contact and full-field measurement, and is suitable for measuring the flow velocity of an unsteady flow.
Disclosure of Invention
In response to the above deficiencies of the prior art or needs for improvement, the inventors have discovered that to accurately capture trace changes of trace particles at low flow rates, a high precision monocular camera may be employed to obtain the particle trace changes. Therefore, the invention provides a monocular vision-based method and a monocular vision-based system for detecting internal defects of a liquid container, which can be used for transferring the technology of measuring fluid by using tracer particles to a ship liquid container.
In order to achieve the above object, a first aspect of the present invention provides a method for detecting defects of a ship liquid container based on monocular vision, including:
uniformly placing a plurality of tracer particles in the liquid container, and continuously acquiring a detection image comprising a plurality of tracer particle positions within a first time interval;
sequentially extracting displacement tracks of the tracer particles between adjacent detection images by using a characteristic point tracking algorithm; superposing a plurality of corresponding continuous displacement tracks to obtain a displacement track image of the tracer particles in the first time interval;
judging whether a defect area exists in the liquid container or not according to the trace of the tracer particles in the displacement trace image and the position information of the defect area in the liquid container;
wherein the tracer particles have a density greater than a density of the liquid in the liquid container.
Further, the continuously acquiring detection images including a plurality of the trace particle locations over a first time interval includes:
projecting at least one detection light source into the liquid container at the tracer particle distribution region;
continuously acquiring a plurality of frames of detection images including a plurality of the trace particle locations over a first time interval using at least one monocular camera;
the number of the tracer particles is at least 10.
Further, the determining whether a defect region exists in the liquid container according to the trace of the trace particles in the displacement trace image comprises:
and if a plurality of displacement track deviations of the tracer particles and disappearance of the displacement tracks exist in the displacement track image at the same time, judging that a defect area exists in the liquid container.
Further, the position information of the defect area in the liquid container includes:
establishing a first coordinate system in the displacement track image, extracting a plurality of pixel points with disappeared trace particles of the trace particles to fit in the first coordinate system, and acquiring first position information;
and establishing a second coordinate system in the liquid container, and calculating the position distribution of the first position information in the second coordinate system according to the space mapping relation between the transfer track image and the liquid container, so as to obtain the position information of the defect area in the liquid container.
Further, the sequentially extracting the displacement tracks of the trace particles between the adjacent detection images by using a feature point tracking algorithm includes:
establishing a third coordinate system in the detection image, performing characteristic point matching in the continuous Nth detection image to the (N + m) th detection image according to a pyramid LK characteristic point tracking algorithm, and extracting pixel coordinates of the same tracer particles; wherein m is an integer of 1 to 10
And acquiring the displacement tracks of the tracer particles according to the pixel coordinates, and thus sequentially acquiring a plurality of displacement tracks of the corresponding tracer particles in a third coordinate system.
Further, the superimposing a plurality of corresponding continuous displacement tracks, and acquiring a displacement track image of the trace particle within the first time interval includes:
and extracting displacement tracks corresponding to the tracer particles, and forming displacement track images of the tracer particles in the first time interval after the displacement tracks are superposed in the third coordinate system.
The invention provides a ship liquid container defect detection system based on monocular vision, which comprises:
a plurality of tracer particles for uniform placement in the liquid container, the tracer particles having a density greater than a density of liquid in the liquid container;
at least one detection light source for projecting into said tracer particle distribution region in said liquid container;
the monocular camera is arranged at the upper end of the inner space of the liquid container and is used for continuously acquiring multi-frame detection images comprising a plurality of tracer particle positions within a first time interval;
the first image processing module is used for sequentially extracting displacement tracks of the tracer particles between adjacent detection images by using a characteristic point tracking algorithm; superposing a plurality of corresponding continuous displacement tracks to obtain a displacement track image of the tracer particles in the first time interval;
and the second image processing module is used for judging whether a defect area exists in the liquid container or not and the position information of the defect area in the liquid container according to the trace of the tracer particles in the displacement trace image.
Further, the tracer particles are solid particles for scattering the detection light source, and the number of the tracer particles is at least 10.
Further, the second image processing module includes:
the first image processing submodule is used for judging whether a defect area exists in the liquid container or not according to whether displacement track deviation and displacement track disappearance of a plurality of tracer particles exist in the displacement track image at the same time or not;
the second image processing submodule is used for establishing a first coordinate system in the displacement track image, extracting a plurality of pixel points with disappeared trace particle tracks to fit in the first coordinate system, and acquiring first position information; and the system is also used for establishing a second coordinate system in the liquid container, and calculating the distribution of the first position information at the corresponding position of the second coordinate system according to the space mapping relation between the transfer track image and the liquid container, so as to obtain the position information of the defect area in the liquid container.
A third aspect of the invention provides a computer-readable medium storing a computer program for execution by an electronic device, which, when run on the electronic device, causes the electronic device to perform the method as described above.
Generally, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects:
the problem that small cracks and liquid leakage of an existing ship static liquid container are often found through manual inspection and are difficult to effectively detect in an early stage is solved. The method and the system for detecting the internal defects of the liquid container based on the monocular vision can effectively utilize the tracer particle technology, observe the track change of the tracer particles through the image observation system, and detect the tiny cracks of the container in time when liquid leakage occurs; on the one hand, the detection accuracy is effectively improved, and on the other hand, the labor cost is reduced.
Drawings
FIG. 1 is a schematic diagram of a monocular vision based vessel liquid container defect detection system that may be implemented in accordance with the present invention;
fig. 2 is an exemplary diagram of a displacement trajectory image of a monocular vision based ship liquid container defect detection method that may be implemented according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
It should be noted that the terms "first \ second" and "first \ second" are used herein only for distinguishing similar objects and do not represent a specific ordering for the objects, and it should be understood that "first \ second" and "first \ second" may be interchanged in a specific order or sequence where permitted. It should be understood that "first \ second" distinct objects may be interchanged under appropriate circumstances such that embodiments of the invention described herein may be practiced in sequences other than those described or illustrated herein.
According to a specific embodiment, the invention provides a ship liquid container defect detection method based on monocular vision, which comprises the following steps: uniformly putting a plurality of tracer particles into a liquid container, and continuously acquiring multi-frame detection images comprising a plurality of tracer particle positions within a first time interval; sequentially extracting displacement tracks of the trace particles between adjacent detection images by using a characteristic point tracking algorithm; superposing the corresponding continuous displacement tracks to obtain a displacement track image of the tracer particles in a first time interval; judging whether a defect area exists in the liquid container or not according to the trace of the tracer particles in the displacement trace image and position information of the defect area in the liquid container; the method comprises the following specific steps:
step 1, arranging the monocular camera on the upper part of the inner space of the ship liquid container, and matching with a detection light source to form a set of stereoscopic vision observation device.
Step 2, as shown in fig. 1, a proper amount of tracer particles are uniformly put into the inlet section of the ship liquid container, the density of the tracer particles is slightly greater than that of the liquid in the liquid container, preferably, the tracer particles are immersed in the bottom surface of the liquid container, and simultaneously, under the irradiation of a detection light source inside the space of the liquid container, the inside of the liquid container and the tracer particles can be well observed by a single-lens camera.
Specifically, the tracer particles are solid particles with good light scattering property when irradiated by the detection light source, and the number of the tracer particles is at least 10.
And 3, continuously tracking the tracer particles of the continuous frame detection images acquired by the high-speed camera by using a characteristic point tracking algorithm, so that the displacement tracks of the tracer particles between adjacent frames can be obtained, and the pixel displacement information of the tracer particles can be obtained under the condition of monocular vision.
Specifically, a characteristic point tracking algorithm is used for sequentially extracting displacement tracks of the trace particles between adjacent detection images, and a pyramid LK characteristic point tracking algorithm is preferably adopted.
More specifically, a coordinate system is established in the detection image, feature point matching is carried out in the adjacent Nth detection image and the adjacent Nth + m detection image according to a pyramid LK feature point tracking algorithm, the matching interval between the detection image frames can be adjusted according to the movement speed of the tracer particles, for example, the same feature point between the N-th detection image and the Nth + m detection image can be simultaneously extracted for matching, m is an integer between 1 and 10, and the pixel coordinates of the same tracer particle are extracted; and acquiring the displacement tracks of the tracer particles according to the pixel coordinates, and acquiring a plurality of displacement tracks of the corresponding tracer particles in the standard system in sequence. The frequency of the successive acquisition of detection images may depend on the mobility characteristics of the tracer example in different specific liquids, and is preferably not less than 30 fps.
More specifically, pixel coordinates of the trace particles matched and corresponding in the first detection image and the second detection image are extracted according to the pyramid LK characteristic point tracking algorithm, pixel coordinates of the trace particles matched and corresponding in the second detection image and the third detection image are extracted according to the pyramid LK characteristic point tracking algorithm, and pixel coordinates of the trace particle displacement tracks are sequentially processed.
And 4, overlapping the displacement tracks of the tracer particles in the multi-frame detection image to obtain a continuous change track of a batch of specific tracer particles within a period of time, namely a displacement track image.
Specifically, the corresponding continuous displacement tracks are superposed, and a displacement track image of the tracer particles in the first time interval is obtained. More specifically, pixel coordinates of displacement tracks corresponding to the trace particles are extracted and overlapped in a detection image coordinate system, and then a displacement track image of the trace particles in a first time interval is formed.
And 5, judging whether a defect area exists in the liquid container or not according to the trace of the tracer particles in the displacement trace image and the position information of the defect area in the liquid container.
Specifically, judging whether a defect area exists in the liquid container according to the trace of the tracer particles in the displacement trace image; more specifically, if a plurality of trace particle displacement track deviations and displacement track disappearance exist simultaneously in the displacement track image, it is determined that a defect region exists in the liquid container.
Specifically, the position information of the defect area in the liquid container is judged according to the trace of the tracer particles in the displacement trace image; furthermore, a first coordinate system is established in the displacement trajectory image, and a plurality of pixel points with trace particle trajectories disappearing are extracted to be fitted in the first coordinate system to obtain first position information; and establishing a second coordinate system in the liquid container, and calculating the position distribution of the first position information in the second coordinate system according to the space mapping relation between the transfer track image and the liquid container, thereby acquiring the position information of the defect area in the liquid container.
In this embodiment, in the case of a micro crack in a liquid container, disappearance of trace particles continues to occur at a liquid leakage portion of the crack. When the particle trajectory is reflected, a part of the particle trajectory deviates from the main trajectory direction, and a part of the particle trajectory disappears, and by analyzing the trajectory characteristics, it can be determined that a crack occurs and liquid leakage occurs, as shown in fig. 2. Therefore, pixel coordinates of the end vanishing position points of the multiple particle tracks in the displacement track image are extracted, curve fitting is carried out in a displacement track image coordinate system, the shape and the coordinate position of the crack in the displacement track image coordinate system are obtained, then mapping is established between the displacement track image coordinate system and the space coordinate system of the solution according to the imaging relation, and the specific position of the micro crack can be roughly estimated according to the mapping.
According to another specific embodiment, the invention provides a ship liquid container defect detection system based on monocular vision, comprising:
the tracer particles are uniformly put into the liquid container, and the density of the tracer particles is greater than that of the liquid in the liquid container; more specifically, the tracer particles may be dispensed from an outlet above the solution containment space or a tracer particle dispenser may be positioned above the solution containment space.
At least one detection light source for projecting to a tracer particle distribution area in the liquid container; the detection light source is a special light source and can form a stereoscopic vision observation device together with the monocular camera.
The monocular camera is arranged at the upper end of the inner space of the liquid container and is used for continuously acquiring multi-frame detection images comprising a plurality of tracer particle positions within a first time interval; preferably, the monocular camera is a monocular high-speed camera;
the first image processing module is used for sequentially extracting displacement tracks of the tracer particles between adjacent detection images by using a characteristic point tracking algorithm; superposing the corresponding continuous displacement tracks to obtain a displacement track image of the tracer particles in a first time interval;
and the second image processing module is used for judging whether a defect area exists in the liquid container or not according to the trace of the tracer particles in the displacement trace image and the position information of the defect area in the liquid container.
Specifically, the tracer particles are solid particles with good light scattering property when irradiated by the detection light source, and the number of the tracer particles is at least 10.
Specifically, the second image processing module includes:
the first image processing submodule is used for judging whether a defect area exists in the liquid container or not according to whether displacement track deviation and displacement track disappearance of a plurality of tracer particles exist in the displacement track image at the same time or not;
a second image processing submodule comprising an image fitting unit and a position determination unit, wherein,
the image fitting unit is used for establishing a first coordinate system in the displacement track image, extracting pixel points with a plurality of trace particle tracks disappeared to fit in the first coordinate system, and acquiring first position information;
and the position judging unit is used for establishing a second coordinate system in the liquid container, and calculating the corresponding position distribution of the first position information in the second coordinate system according to the space mapping relation between the transfer track image and the liquid container so as to acquire the position information of the defect area in the liquid container.
Specifically, the first image processing module includes:
the third image processing submodule comprises a position extraction unit and a displacement extraction unit; wherein the content of the first and second substances,
the position extraction unit is used for establishing a third coordinate system in the detection image, performing characteristic point matching in the adjacent Nth detection image to the (N + m) th detection image according to a pyramid LK characteristic point tracking algorithm, and extracting pixel coordinates of the same tracer particle;
and the displacement extraction unit is used for acquiring the displacement tracks of the tracer particles according to the pixel coordinates, and accordingly sequentially acquiring a plurality of displacement tracks of the corresponding tracer particles in a third coordinate system. And the fourth image processing submodule is used for extracting displacement tracks of corresponding tracer particles, and forming displacement track images of the tracer particles in the first time interval after the displacement tracks are superposed in the third coordinate system.
According to another specific embodiment of the present invention, a computer-readable medium is provided, which stores a computer program for execution by an electronic device, and when the computer program runs on the electronic device, causes the electronic device to perform the above method.
It should be understood that any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process, and that the scope of preferred embodiments of the present invention includes additional implementations where functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried out in the method of implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer-readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art without departing from the principle and spirit of the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A ship liquid container defect detection method based on monocular vision is characterized by comprising the following steps:
uniformly putting a plurality of tracer particles into the liquid container, and continuously acquiring detection images comprising a plurality of tracer particle positions within a first time interval;
sequentially extracting displacement tracks of the tracer particles between adjacent detection images by using a characteristic point tracking algorithm; superposing a plurality of corresponding continuous displacement tracks to obtain a displacement track image of the tracer particles in the first time interval;
judging whether a defect area exists in the liquid container or not according to the trace of the tracer particles in the displacement trace image and the position information of the defect area in the liquid container;
wherein the tracer particles have a density greater than the density of the liquid in the liquid container;
the position information of the defect area in the liquid container comprises:
establishing a first coordinate system in the displacement track image, extracting a plurality of pixel points with disappeared trace particles of the trace particles to fit in the first coordinate system, and acquiring first position information;
and establishing a second coordinate system in the liquid container, and calculating the position distribution of the first position information in the second coordinate system according to the space mapping relation between the transfer track image and the liquid container, so as to obtain the position information of the defect area in the liquid container.
2. The vessel liquid container defect detection method based on monocular vision of claim 1, wherein the continuously acquiring detection images including a plurality of the tracer particle locations over a first time interval comprises:
projecting at least one detection light source into the liquid container at the tracer particle distribution region;
continuously acquiring a plurality of frames of detection images including a plurality of the trace particle locations over a first time interval using at least one monocular camera;
the number of the tracer particles is at least 10.
3. The vessel liquid container defect detection method based on monocular vision according to claim 1 or 2, wherein the determining whether a defect region exists in the liquid container according to a trace of a tracer particle in the displacement trace image includes:
and if a plurality of displacement track deviations of the tracer particles and disappearance of the displacement tracks exist in the displacement track image at the same time, judging that a defect area exists in the liquid container.
4. The vessel liquid container defect detection method based on monocular vision as set forth in claim 1 or 2, wherein the sequentially extracting displacement trajectories of the tracer particles between adjacent detection images using a feature point tracking algorithm comprises:
establishing a third coordinate system in the detection image, performing characteristic point matching in the continuous Nth detection image to the N + m detection image according to a pyramid LK characteristic point tracking algorithm, and extracting pixel coordinates of the same tracer particles; wherein m is an integer between 1 and 10;
and acquiring the displacement tracks of the tracer particles according to the pixel coordinates, and thus sequentially acquiring a plurality of displacement tracks of the corresponding tracer particles in a third coordinate system.
5. The vessel liquid container defect detection method based on monocular vision of claim 4, wherein the superimposing a corresponding consecutive plurality of the displacement trajectories, and the obtaining the displacement trajectory image of the tracer particle within the first time interval comprises:
and extracting displacement tracks corresponding to the tracer particles, and forming displacement track images of the tracer particles in the first time interval after the displacement tracks are superposed in the third coordinate system.
6. A ship liquid container defect detection system based on monocular vision is characterized by comprising:
a plurality of tracer particles for uniform placement in the liquid container, the tracer particles having a density greater than a density of liquid in the liquid container;
at least one detection light source for projecting into said tracer particle distribution region in said liquid container;
the monocular camera is arranged at the upper end of the inner space of the liquid container and is used for continuously acquiring multi-frame detection images comprising a plurality of tracer particle positions within a first time interval;
the first image processing module is used for sequentially extracting displacement tracks of the tracer particles between adjacent detection images by using a characteristic point tracking algorithm; superposing a plurality of corresponding continuous displacement tracks to obtain a displacement track image of the tracer particles in the first time interval;
the second image processing module is used for judging whether a defect area exists in the liquid container or not and the position information of the defect area in the liquid container according to the trace of the tracer particles in the displacement trace image;
the second image processing module includes:
the first image processing submodule is used for judging whether a defect area exists in the liquid container or not according to whether displacement track deviation and displacement track disappearance of a plurality of tracer particles exist in the displacement track image at the same time or not;
the second image processing submodule is used for establishing a first coordinate system in the displacement track image, extracting a plurality of pixel points with disappeared trace particle tracks to fit in the first coordinate system, and acquiring first position information; and the system is also used for establishing a second coordinate system in the liquid container, and calculating the distribution of the first position information in the corresponding position of the second coordinate system according to the space mapping relation between the moving track image and the liquid container, so as to obtain the position information of the defect area in the liquid container.
7. The monocular vision based marine liquid container defect detecting system of claim 6, wherein the tracer particles are solid particles for scattering the detection light source, and the number of the tracer particles is at least 10.
8. A computer-readable medium storing a computer program for execution by an electronic device, which when run on the electronic device, causes the electronic device to perform the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011504088.2A CN112489041B (en) | 2020-12-18 | 2020-12-18 | Ship liquid container defect detection method and system based on monocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011504088.2A CN112489041B (en) | 2020-12-18 | 2020-12-18 | Ship liquid container defect detection method and system based on monocular vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112489041A CN112489041A (en) | 2021-03-12 |
| CN112489041B true CN112489041B (en) | 2022-06-21 |
Family
ID=74914619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011504088.2A Active CN112489041B (en) | 2020-12-18 | 2020-12-18 | Ship liquid container defect detection method and system based on monocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489041B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130002622A (en) * | 2011-06-29 | 2013-01-08 | 자동차부품연구원 | System for measuring defect and method therefor |
| CN105144237A (en) * | 2013-03-15 | 2015-12-09 | 卢米耐克斯公司 | Real-time tracking and correlation of microspheres |
| CN108398321A (en) * | 2018-01-26 | 2018-08-14 | 河北工业大学 | The three-dimensional rectangular crack of observation is destroyed and the experimental method and experimental provision of strain field |
| CN110566190A (en) * | 2019-09-29 | 2019-12-13 | 西南石油大学 | method for tracking motion trail of intra-slit proppant under high-particle-concentration experimental condition |
| CN110634364A (en) * | 2019-09-30 | 2019-12-31 | 华中科技大学 | Simple speed field measuring system based on particle image velocimetry technology |
| WO2020122926A1 (en) * | 2018-12-13 | 2020-06-18 | Lockheed Martin Corporation | Modified track-etched substrates for composite graphene membranes |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8351683B2 (en) * | 2007-12-25 | 2013-01-08 | Hitachi High-Technologies Corporation | Inspection apparatus and inspection method |
-
2020
- 2020-12-18 CN CN202011504088.2A patent/CN112489041B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130002622A (en) * | 2011-06-29 | 2013-01-08 | 자동차부품연구원 | System for measuring defect and method therefor |
| CN105144237A (en) * | 2013-03-15 | 2015-12-09 | 卢米耐克斯公司 | Real-time tracking and correlation of microspheres |
| CN108398321A (en) * | 2018-01-26 | 2018-08-14 | 河北工业大学 | The three-dimensional rectangular crack of observation is destroyed and the experimental method and experimental provision of strain field |
| WO2020122926A1 (en) * | 2018-12-13 | 2020-06-18 | Lockheed Martin Corporation | Modified track-etched substrates for composite graphene membranes |
| CN110566190A (en) * | 2019-09-29 | 2019-12-13 | 西南石油大学 | method for tracking motion trail of intra-slit proppant under high-particle-concentration experimental condition |
| CN110634364A (en) * | 2019-09-30 | 2019-12-31 | 华中科技大学 | Simple speed field measuring system based on particle image velocimetry technology |
Non-Patent Citations (2)
| Title |
|---|
| A simple and inexpensive technique for assessing contamination during drilling operations;Andre Friese et al;《Limnology and Oceanography: Methods》;20170228;第200-211页 * |
| 基于平动撞击下的玻璃微珠运动轨迹测量系统;刘明明;《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》;20130215;第1-44页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112489041A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20100086172A1 (en) | Method and apparatus for automatic sediment or sludge detection, monitoring, and inspection in oil storage and other facilities | |
| JP4765890B2 (en) | Foreign object detection device | |
| CN106197612B (en) | A kind of transparent bottled liquid-level detecting method based on machine vision | |
| CN106996751B (en) | A kind of grain-transporting vehicle cereal loading condition detection method and device of view-based access control model image | |
| CN109488888A (en) | Based on the metallic conduit leakage monitoring method to the multivariate analysis of infrared temperature field | |
| Ali et al. | A cascading fuzzy logic with image processing algorithm–based defect detection for automatic visual inspection of industrial cylindrical object’s surface | |
| CN114235809A (en) | Optical non-contact method for measuring large particles in pipeline | |
| Guan et al. | Automatic fault diagnosis algorithm for hot water pipes based on infrared thermal images | |
| Kulkarni et al. | An automated computer vision based system for bottle cap fitting inspection | |
| CN109115417B (en) | Pressure container air tightness detection method based on connected domain judgment | |
| Felipe et al. | Vision-based liquid level detection in amber glass bottles using OpenCV | |
| JP2007155724A5 (en) | ||
| CN112489041B (en) | Ship liquid container defect detection method and system based on monocular vision | |
| Agudo et al. | Detection of particle motion using image processing with particular emphasis on rolling motion | |
| JP2009019972A (en) | Liquid amount measuring apparatus and liquid amount measuring method | |
| JP2007333579A (en) | Inspection method and system for honeycomb structure | |
| TWI396832B (en) | Liquid level identification method | |
| Foglia et al. | An inspection system for pharmaceutical glass tubes | |
| CN112241970B (en) | Schlieren imaging-based gas-liquid two-phase gas-liquid flow field velocity measuring method and system | |
| Samann | Real-time liquid level and color detection system using image processing | |
| Lin et al. | A development of visual inspection system for surface mounted devices on printed circuit board | |
| CN116879708A (en) | Method for detecting faults of printed circuit board by utilizing infrared cloud picture recognition technology | |
| Ye et al. | Deep Learning and Laser-based 3D Pixel-level Rail Surface Defect Detection Method | |
| CN109626302A (en) | A kind of online test method of beer foreign matter in bottles | |
| JP2006170635A (en) | Detector of flaw by image processing and flaw detecting method using it |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |