EP3580722A1 - Method for inspecting a surface - Google Patents
Method for inspecting a surfaceInfo
- Publication number
- EP3580722A1 EP3580722A1 EP18707094.1A EP18707094A EP3580722A1 EP 3580722 A1 EP3580722 A1 EP 3580722A1 EP 18707094 A EP18707094 A EP 18707094A EP 3580722 A1 EP3580722 A1 EP 3580722A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- treated
- areas
- inspected
- processed
- zones
- 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.)
- Withdrawn
Links
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
- G06T7/0004—Industrial image inspection
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30156—Vehicle coating
Definitions
- the present invention generally relates to the field of surface inspection methods for identifying and defining defects.
- it relates to a method of inspecting a surface using a plurality of stations in order to construct the inspected surface in three dimensions and to identify the defects therein.
- the method of inspecting a surface of the invention aims to remedy all or part of the disadvantages of the state of the art and aims in particular to provide a suitable method for exploring the entire surface to be analyzed to accurately identify and define defects from different inspection points of view.
- This objective is achieved through a method of inspecting a surface, in particular a boat hull, comprising the following steps: a) acquiring two-dimensional images further comprising three-dimensional point clouds of a surface to be inspected from at least two stations at different positions, said images having at least one overlapping zone, b) constructing in three dimensions said surface to be inspected in a reference frame from the different images acquired,
- the term station a camera or sensor capable of obtaining two-dimensional images further comprising point clouds in three dimensions.
- the marker may be any reference. It is in principle linked to one of the stations, for example the first one.
- the term "zone to be treated” means an area comprising one or more defects that can be defined by qualitative and / or quantitative characters.
- the first zone to be treated is defined as a zone to be treated defined according to a station.
- the second zone to be treated is further understood to mean a zone to be treated defined according to another station different from that according to which the first zone to be treated has been defined.
- treatment weighting coefficient means a coefficient that makes it possible to categorize the state of the zone to be treated (whether it is a first or second zone) according to quantitative factors and / or or qualitative that may correspond to the defined area to be treated.
- step a it is necessary to use at least two stations. Thus, it is possible to observe the surface to be inspected according to different points seen. This has the advantage of being able, later on, to identify and define second zones to be treated according to a second station, different from the first station used to locate and define first zones to be treated. It should be noted that, with the aid of the second station, it is therefore possible to perceive second zones to be treated, but also to perceive at least a portion of the first zones to be treated in order to correctly associate the latter with coefficients of appropriate processing weights when there is any doubt about the treatment weighting factors to be associated.
- the method can implement more than two stations if each station has at least one overlap area with at least one other station.
- the visualization step d) has the advantage of avoiding redefining the first or the first zones to be treated defined according to the first station, and defining one or more second zones to be treated according to the second station which could not be defined according to the first station.
- the method may further comprise, once said total surface to be treated obtained, a step of archiving said first and second areas to be treated.
- This archiving step has the advantage of archiving only information relating to the areas considered to be treated, whether they are first or second areas to be treated. Thus, it frees itself from an integral storage of the surface to be inspected in three dimensions by omitting the archiving of areas not defined as areas to be treated.
- the method may further comprise a step of comparing said first and second areas to be treated according to said treatment weighting coefficients to which they are associated.
- This present comparison step can be used to compare the different previously defined areas to be treated (whether these are first or second areas) as a function of weighting coefficients associated with them. This step can also make it possible to compare the totality of the zones to be treated defined during a first inspection with those obtained after a second inspection.
- first inspection means an inspection of a surface made at a time t.
- second inspection means an inspection of the same surface but carried out at a time t + 1.
- all of said surface to be inspected may be defined by said first and second areas to be treated.
- the invention also relates to a computer program comprising instructions adapted to the implementation of each of the steps of the method described above when said program is executed on a calculating machine.
- the invention also relates to a system comprising means adapted to the implementation of each of the steps of the method described above.
- the inspection method is applied to a surface of a hull of a boat.
- this process can be used in the field of aeronautics, penstocks for high pressure water, metal works, surface treatment, petrochemical, building, nuclear.
- two stations are used, a first and a second, such as Leica cameras P20, P40, C10.
- a first and a second such as Leica cameras P20, P40, C10.
- images of at least a portion of the surface to be inspected from a boat hull are acquired, including surface defects. These images are acquired from the two stations located at different positions, the images having at least one overlap area.
- the surface to be inspected in a reference frame is constructed in three dimensions from the different images previously acquired.
- An image representing the surface to be inspected is thus obtained, this image preferably being observable on at least one screen.
- This image shows a three-dimensional representation and a color representation of the scene.
- the surface to be inspected in three dimensions on the screen is visualized only according to the first station. It is thus possible to precisely explore the part of the surface obtained by this first station and identify any type of surface defect.
- first zones to be treated are defined, each of these first zones comprising a defect identified via the abovementioned image.
- the first areas to be treated were identified by an operator by clicking the four corners of a quadrilateral consistent with the defects identified. Then, this operator defines each of these first zones by assigning them weighting coefficients. For example, the weighting coefficients are associated with each of the first zones to be treated according to their type, their position, their geometry, their dimensions and their density.
- the allocation of these weighting coefficients can be performed following the assignment to each of these first zones, one or more labels, or labels, illustrating one or more particular characters mentioned above.
- the first zones to be treated are visualized according to the second station. In this way, it is possible to perceive differently the first zones to be treated but also to perceive new ones which were not perceptible according to the first station, these new zones being called second zones to be treated. Indeed, the use of a second station as a different point of view, may allow to observe subtleties, details, the surface not perceptible state according to the first station, and may be due to illumination or different surface orientation for example.
- several second zones to be treated are determined and the first zones to be treated are used to characterize the targeted defects by associating them with weighting coefficients.
- a total area to be treated is obtained.
- the storage of information relating to the areas considered to be not to be processed is dispensed with, and only the information relating to the zones is stored with a maximum resolution, for example. treat.
- This information may, for example, be relative to the designation of the area to be treated, the coordinates of the four corners of the quadrilateral encompassing it, the weighting coefficient or coefficients associated with it, and any additional comments added by the operator.
- the first and second zones to be treated can be compared as a function of the treatment weighting coefficients to which they are associated. It should be noted that it is also possible to compare the definitions of the areas to be treated with an inventory whose results were obtained during a previous implementation of the method.
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR1751059A FR3062741B1 (en) | 2017-02-08 | 2017-02-08 | SURFACE INSPECTION PROCESS |
PCT/FR2018/050304 WO2018146421A1 (en) | 2017-02-08 | 2018-02-07 | Method for inspecting a surface |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3580722A1 true EP3580722A1 (en) | 2019-12-18 |
Family
ID=59296914
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP18707094.1A Withdrawn EP3580722A1 (en) | 2017-02-08 | 2018-02-07 | Method for inspecting a surface |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP3580722A1 (en) |
FR (1) | FR3062741B1 (en) |
WO (1) | WO2018146421A1 (en) |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8477154B2 (en) * | 2006-03-20 | 2013-07-02 | Siemens Energy, Inc. | Method and system for interactive virtual inspection of modeled objects |
ES2724115T3 (en) * | 2007-06-29 | 2019-09-06 | Midmark Corp | Graphical user interface for computer-assisted margin marking on dentures |
-
2017
- 2017-02-08 FR FR1751059A patent/FR3062741B1/en active Active
-
2018
- 2018-02-07 EP EP18707094.1A patent/EP3580722A1/en not_active Withdrawn
- 2018-02-07 WO PCT/FR2018/050304 patent/WO2018146421A1/en unknown
Also Published As
Publication number | Publication date |
---|---|
FR3062741A1 (en) | 2018-08-10 |
WO2018146421A1 (en) | 2018-08-16 |
FR3062741B1 (en) | 2020-03-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
FR3067242B1 (en) | METHOD FOR EVALUATING AN ORTHODONTIC GUTTER | |
US8750596B2 (en) | System and method for identifying defects in a material | |
KR102363265B1 (en) | Adaptive local threshold and color filtering | |
TW201511157A (en) | Methods and systems for detecting repeating defects on semiconductor wafers using design data | |
EP2880623B1 (en) | Method and device for reconstructing super-resolution images | |
US9582869B2 (en) | Dynamic binning for diversification and defect discovery | |
Lu et al. | Invalid phase values removal method for absolute phase recovery | |
WO2020064323A1 (en) | Method and system for the non-destructive testing of an aerospace part by contour readjustment | |
FR2929416A1 (en) | METHOD FOR DETERMINING A THREE-DIMENSIONAL REPRESENTATION OF AN OBJECT FROM A CUTTING IMAGE SEQUENCE, COMPUTER PROGRAM PRODUCT, CORRESPONDING OBJECT ANALYSIS METHOD, AND IMAGING SYSTEM | |
US20230154158A1 (en) | Method and system for enhancing online reflected light ferrograph image | |
FR3026211A1 (en) | METHOD FOR IDENTIFYING THE ANISOTROPY OF THE TEXTURE OF A DIGITAL IMAGE | |
EP2856424B1 (en) | Method of three-dimensional measurements by stereo-correlation using a parametric representation of the measured object | |
EP3580722A1 (en) | Method for inspecting a surface | |
FR3050300A1 (en) | METHOD AND DEVICE FOR AUTOMATIC DETECTION OF POLLUTION ZONES ON A WATER SURFACE | |
CN115272258A (en) | Metal cylindrical surface defect detection method, system and medium based on machine vision | |
WO2016083676A1 (en) | Method and device for processing well data | |
TW202211154A (en) | Deep learning model for noise reduction in low snr imaging conditions | |
FR2697930A1 (en) | Method for producing a synthesized reference image for inspecting objects | |
TW202219497A (en) | System, method and non-transitory computer readable medium for tuning sensitivities of, and determining a process window for, a modulated wafer | |
Orlov et al. | Development and experimental investigation of algorithms for distinguishing fuzzy boundaries of objects in photographs of industrial materials | |
EP3163462A1 (en) | Method for estimating a convolution product | |
FR3048800A1 (en) | IMAGE PROCESSING METHOD | |
CN106778780B (en) | GPU-based edge detection image binarization method | |
Delanaye et al. | Protéinuries et bandelettes urinaires: une technique simple d'interprétation compliquée. | |
WO2021069973A1 (en) | System and method for object detection in holographic lens-free imaging by convolutional dictionary learning and encoding with phase recovery |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20190813 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: CHECCHIN, PAUL Inventor name: MALATERRE, LAURENT Inventor name: TRASSOUDAINE, LAURENT Inventor name: AIJAZI, AHMAD KAMAL |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20201013 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
18D | Application deemed to be withdrawn |
Effective date: 20210424 |