WO2014101387A1 - 三维数据处理和识别方法 - Google Patents
三维数据处理和识别方法 Download PDFInfo
- Publication number
- WO2014101387A1 WO2014101387A1 PCT/CN2013/078884 CN2013078884W WO2014101387A1 WO 2014101387 A1 WO2014101387 A1 WO 2014101387A1 CN 2013078884 W CN2013078884 W CN 2013078884W WO 2014101387 A1 WO2014101387 A1 WO 2014101387A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- interest
- point
- dimensional data
- data processing
- recognition method
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/05—Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs
Definitions
- the present invention relates to the field of three-dimensional data processing and identification, and more particularly to intelligent identification of an item to be inspected for a CT contraband or a nuclear magnetic resonance system of a security instrument. Background technique
- the US government decided to implement additional aviation safety, requiring explosives inspection of all selected baggage.
- the known explosives detection system uses X-ray (perspective) or CT technology to obtain the contents of the package. image.
- the US government has stipulated that from December 2001, all selected baggage must use the technology certified by the newly established Transportation Security Agency for explosives inspection. To date, the only technology TSA has proven is CT.
- Three-dimensional CT data can be obtained from the current mainstream security CT. Due to the high traffic volume at the airport, high explosive throughput is required for explosives detection systems for consignments and hand luggage. It is very urgent to be able to intelligently identify contraband, which can reduce the work intensity of security personnel, reduce human factors and increase the pass rate.
- a new three-dimensional data processing and identification method is provided.
- the invention discloses a three-dimensional data processing and recognition method, which comprises the following steps: comprising the steps of: performing scan reconstruction on an item to be inspected to obtain three-dimensional data for identifying an item to be detected; and extracting feature matching data from the three-dimensional data.
- the extracted three-dimensional data constitutes an object of interest; for the matched data, the immediately adjacent data points are merged into one type to form an image of the merged object of interest; and the cross-section of the object of interest is identified; Intercepting a pair of interest from at least one vertical plane of the cross-section and perpendicular to the cross-section Obtaining a graphic; and identifying a shape of the object of interest based on attributes of the graphic.
- the general idea of the present invention is to search, extract, merge, statistically and shape the three-dimensional data obtained by scanning and reconstructing the security CT system with characteristic data of the object of interest or suspected object (e.g., dangerous goods or contraband).
- characteristic data of the object of interest or suspected object e.g., dangerous goods or contraband.
- the present invention proposes the three-dimensional data processing and recognition method of the present invention from a different angle, which solves the sense of the opposite. Problems with search, statistics, and shape recognition of objects of interest.
- Figure 1 is a schematic view of a cone
- Figure 2 is a schematic diagram of culling data points that are not on the surface
- Figure 3 is a schematic illustration of a cross section of a selected coordinate origin within an object of interest and a cross section parallel thereto;
- Figure 4 is a schematic illustration of two vertical planes passing through the center point of the cross section after identifying the cross section of the object of interest;
- Figure 5 is a schematic illustration of a graph obtained by taking an object of interest of a cylinder and a cube perpendicular to the plane of the cross section.
- the embodiment of the present invention takes the CT image data reconstructed by the security CT system as an example to illustrate how the identification of contraband or dangerous goods can be performed by the three-dimensional data processing and identification method of the present invention. It should be noted herein that those skilled in the art will appreciate that the three-dimensional data processing and identification method of the present invention can also be used in a nuclear magnetic resonance system or a similar system for identifying an object of interest.
- the general idea of the present invention is to search, extract, merge, count, and shape three-dimensional data obtained by scanning reconstruction of a security CT system using feature data of an object of interest or a suspected object (such as dangerous goods or contraband). Identification.
- the present invention proposes the three-dimensional data processing and recognition method of the present invention from a different angle, which solves the sense of the opposite. Problems with search, statistics, and shape recognition of objects of interest.
- the primary application of the present invention is to identify dangerous objects such as sharp dangerous objects, sharp dangerous goods, arrows and sharp weapons. Furthermore, the identification method of the present invention can also be used to identify pillars, such as firearms and the like.
- a cone will be exemplified below, but it should be understood that the cylinder also has similar properties, so that the three-dimensional data processing and identification method of the present invention can be used to identify the cone and/or the cylinder.
- the axis AG of the cone in Fig. 1 intercepts a plane ⁇ (shown as triangle ABC in Fig. 1).
- the plane ⁇ intersects the cross section of the cone and the intersection line is EF, apparently EF ⁇ AG.
- the plane ⁇ intersects the oblique section of the cone and the intersection line is JK, assuming the line LM// line JK.
- the point P is the midpoint of the line segment JK
- the line AP intersects the line LM at point Q.
- the point Q is the midpoint of the line segment LM.
- ZAPK ⁇ ZADK, and ZADK ⁇ ZADF so ZAPK ⁇ ZADF, ie ZAPK ⁇ 90°. Therefore, the present invention can utilize this property of the cone as a basis for judging the cross section of the cone. Specifically, the three-dimensional data processing and identification method is described in detail below.
- the three-dimensional data processing and recognition method of the present invention mainly includes the following two parts: data processing, shape and size identification of the cone/cylinder. data processing
- the object to be detected is scanned by the security CT system and reconstructed to obtain CT image data (i.e., three-dimensional data), and then the contraband (such as a tool) can be identified based on the obtained three-dimensional data.
- CT image data i.e., three-dimensional data
- contraband such as a tool
- the obtained three-dimensional data is searched, merged, and matched with the three-dimensional data obtained by using the feature data of the contraband, so that the extracted three-dimensional data constitutes the object of interest.
- the contraband can be a common dangerous item such as a knife, an explosive, a gun, and the like.
- the characteristic data may be data of constituent materials of common dangerous goods (such as iron, copper or heavy metals, etc.).
- the data may be any one of their attenuation coefficient data, density data or atomic number or any combination thereof. Typically or preferably, the data uses density data and original Sub ordinal data.
- the size of the contraband can be estimated by the number of data points.
- Information that helps to further identify contraband It can be understood that, depending on the density and the atomic number, it can be identified whether the item to be detected is a drug or an explosive.
- the object of interest formed by the extracted three-dimensional data or the object of interest formed by the combined three-dimensional data may perform the step of constructing the surface data from the three-dimensional data before performing the shape and size recognition step. Building surface data from 3D data
- the step of constructing the surface data from the three-dimensional data will be described by taking the object of interest composed of the combined three-dimensional data as an example. It is to be understood that the step of "building surface data from three-dimensional data" may be performed on the basis of the interesting object composed of the extracted three-dimensional data.
- the above-described combined three-dimensional data constitutes a three-dimensional object (i.e., an object of interest).
- the method for selecting the I point is: selecting the maximum and minimum values of the data in the combined three-dimensional data in three directions of x, y, z, respectively calculating the maximum and minimum values in the three directions. The value, its coordinates as the coordinates of the selected I point.
- an interpolation point of the point is obtained by interpolation, and if the distance from the interpolation point to the I point is greater than the distance from the point to the I point, the point is eliminated.
- Figure 2 shows four points A, B, C, D. It is considered as a surface data point
- point B is obtained by linear interpolation of A and C. The point distance from point I is larger than the distance from point B to point I. , so remove point B.
- the remaining data can be considered as reliable surface data.
- Another preferred method of culling data is to retain the ratio of the interpolated point to point I distance to the point to point I within a predetermined threshold range (as an example, such as [0.95, 1.05]). Point, otherwise remove the point.
- a predetermined threshold range as an example, such as [0.95, 1.05]. Point, otherwise remove the point.
- the method can also be applied to the above-described culling of surface data and internal surface data.
- the constructed surface data can be displayed to the operator to visually and clearly see the shape of the object of interest for preliminary identification (eg, shape).
- the object of interest identifying the cone/cylinder it may be the object of interest formed by the three-dimensional data obtained in the above-mentioned “data processing” step (ie, the combined processed three-dimensional data), or may be "built surface"
- the object of interest is formed by the three-dimensional data after the step of the data.
- the recognition process is performed by taking an object of interest formed by the process of "structuring surface data from three-dimensional data” as an example. It will be appreciated that the object of interest after the step “Build Surface Data from Three-Dimensional Data” contains less redundant data and is easier to handle because some data points that are not on the surface are removed.
- a method for preferably selecting the point I is: selecting the maximum and minimum values of the data in the three directions x, y, z, and calculating the median values of the maximum and minimum values in the three directions, respectively, and the coordinates thereof. ( , yo , zo ) as the coordinates of the selected point I.
- the ⁇ plane is a cross section. If the line RS is not perpendicular to the ⁇ plane, transform the ⁇ plane through the normal direction of the I point ( ⁇ , ⁇ ) to re-intercept the object of interest, repeat the steps 1) -3) until it roughly satisfies the straight line RS ⁇ plane.
- the cross section can be searched using a coarse and fine strategy.
- some known information can also be used to guide the search to speed up the search.
- the cross-section search can also use the following quick identification method (of course, the above method can also be used, but the calculation speed may be slower):
- the cross section ⁇ of the object of interest is found. Then, the center point of the cross section ⁇ is the two vertical planes ⁇ and ⁇ of the cross section a, and the two planes ⁇ are also perpendicular to each other (when the algorithm time is saved, only one vertical perpendicular to the cross section ⁇ can be made. flat).
- the object of interest is a cone.
- the cone tip angle is the apex angle of the triangle.
- the vertical plane ⁇ or the figure obtained by intercepting the object of interest is trapezoidal, and the four endpoints X, Y, U and ⁇ of the trapezoid (as shown in Figure 3) constitute a line segment 1!; ⁇ line segment ⁇ ; calculate the line segment TU The difference between the length of the line segment ⁇ divided by the sum of the line segment TU and the length of the line segment ⁇ ⁇ ( TU-XY) I ( TU+XY) ⁇ ; If the ratio is greater than the threshold (eg 0.1), then the object of interest is determined to be a cone If the ratio is less than the threshold, it is determined that the object of interest is a cylinder.
- the endpoints X, ⁇ are the upper endpoints of the trapezoid, and the endpoints U and ⁇ are the lower endpoints of the trapezoid.
- the actual cone is often a round table (or edge due to processing or wear). Taiwan) shape.
- the pattern obtained with a vertical plane ⁇ or ⁇ truncated cone or rib is usually trapezoidal.
- the vertical plane ⁇ intercepts the object of interest to obtain a trapezoidal XYTU (or triangle ATU).
- the length of the line segment XY is calculated as the taper tip scale; the angle between the line segment XT and the line segment YU is calculated as the taper tip angle.
- the cone angle can be obtained by the formula Zsiif 1 (TU-XY) /2XT).
- other methods known in the art can also be used to calculate the cone tip angle.
- the system alarm can be signaled. In the same way, you can get the vertical plane to intercept the cone tip scale and the cone tip angle of the object of interest, and alarm according to the same threshold.
- the material such as copper
- the cone tip scale, and the cone tip angle satisfy the characteristics of the bullet, it can be judged to be a bullet. If the vertical plane ⁇ or ⁇ intercepts the image obtained by the object of interest is a rectangle, it is determined that the object of interest is a pillar. By calculating the length and width of the rectangle, the size of the pillar can be obtained, as shown in FIG. Fig. 5 shows that when the vertical plane ⁇ intercepts an object of interest of a cylinder or a cube, the figure of the object of interest obtained by the interception is a rectangle.
- the object of interest is identified as a cylinder.
- the cylinder is identified as being hollow, it is determined that the object of interest is a tubular.
- the inner diameter of the tubular conforms to the inner diameter of the barrel and the material of the tubular is metal (such as copper, iron), it is determined that the object of interest is a firearm.
- the object of interest is a cuboid.
- this method After identifying the cone or approximating cone, depending on its cone size, cone angle, and the material is metal (or high-density material), this method also recognizes arrows, sharp knives, screwdrivers, shells, and missile heads. In security applications, glass cones and arrows are also potentially dangerous. Under high-precision images, needles and the like can be recognized. After the tube is identified, if the material is metal and the dimensions are the same, the presence of the missile body (or projectile body) can be judged. If the contained or adjacently placed packing meets ammunition characteristics (such as density or atomic number), the presence of a high-risk missile body (or projectile body) can be accurately determined.
- ammunition characteristics such as density or atomic number
- the method of this patent is applicable to systems that generate three-dimensional data such as CT and nuclear magnetic resonance.
- the text is described in Cartesian coordinate system and spherical coordinate system. If other coordinate systems are used or simple extensions of the present invention fall within the scope of this patent.
- the present invention extracts three-dimensional data by a feature matching method, and then identifies a cross section of the object of interest, intercepts the center point of the cross section and is perpendicular to at least one vertical plane of the cross section.
- the object obtains a graphic; and identifies a shape of the object of interest based on an attribute of the graphic, thereby identifying a contraband such as a spike or a firearm.
- Various CT systems can use this method for dangerous goods identification.
- Other systems that generate three-dimensional data such as nuclear magnetic resonance systems, can also use this method to identify objects of interest.
- the three-dimensional data is searched, extracted, merged, statistically and shape-recognized using the feature data of the object of interest. Because image segmentation of 3D data is still difficult, and accuracy and versatility are not good, this method solves the problem of object search, statistics and shape recognition from another angle.
- the method of the present invention is applicable to a system for generating three-dimensional data such as D and CT and nuclear magnetic resonance.
- the three-dimensional data processing and identification method of the present invention is described herein by taking a Cartesian coordinate system and a spherical coordinate system as an example, but it can be understood that other coordinate systems or simple extensions to the present invention fall within the scope of the present invention.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
- Image Generation (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015549950A JP6013621B2 (ja) | 2012-12-27 | 2013-07-05 | 3次元データの処理及び識別方法 |
KR1020157020434A KR101813771B1 (ko) | 2012-12-27 | 2013-07-05 | 3차원 데이터 처리 및 식별 방법 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210581559.9 | 2012-12-27 | ||
CN201210581559.9A CN103903298B (zh) | 2012-12-27 | 2012-12-27 | 三维数据处理和识别方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014101387A1 true WO2014101387A1 (zh) | 2014-07-03 |
Family
ID=50115667
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2013/078884 WO2014101387A1 (zh) | 2012-12-27 | 2013-07-05 | 三维数据处理和识别方法 |
Country Status (7)
Country | Link |
---|---|
US (1) | US9111128B2 (zh) |
EP (1) | EP2750078B1 (zh) |
JP (1) | JP6013621B2 (zh) |
KR (1) | KR101813771B1 (zh) |
CN (1) | CN103903298B (zh) |
PL (1) | PL2750078T3 (zh) |
WO (1) | WO2014101387A1 (zh) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103903297B (zh) | 2012-12-27 | 2016-12-28 | 同方威视技术股份有限公司 | 三维数据处理和识别方法 |
CN103900503B (zh) | 2012-12-27 | 2016-12-28 | 清华大学 | 提取形状特征的方法、安全检查方法以及设备 |
JP6152488B2 (ja) * | 2014-09-29 | 2017-06-21 | 株式会社Ihi | 画像解析装置、画像解析方法及びプログラム |
CN106296797A (zh) * | 2015-06-10 | 2017-01-04 | 西安蒜泥电子科技有限责任公司 | 一种三维扫描仪特征点建模数据处理方法 |
US10621406B2 (en) * | 2017-09-15 | 2020-04-14 | Key Technology, Inc. | Method of sorting |
CN113128346B (zh) * | 2021-03-23 | 2024-02-02 | 广州大学 | 起重机施工现场的目标识别方法、系统、装置及存储介质 |
CN114608450B (zh) * | 2022-03-10 | 2023-09-26 | 西安应用光学研究所 | 机载光电系统对远距离海面目标三维尺寸测算方法 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1993710A (zh) * | 2004-06-01 | 2007-07-04 | 美国西门子医疗解决公司 | 改进使用切割平面检测球状和椭圆状对象的分水岭分割 |
CN101320397A (zh) * | 2007-06-07 | 2008-12-10 | 乐必峰软件公司 | 使用三维扫描数据计算放样表面的系统和方法 |
CN101499177A (zh) * | 2008-01-28 | 2009-08-05 | 上海西门子医疗器械有限公司 | 一种三维模型的建立方法和系统 |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4687933A (en) * | 1976-12-14 | 1987-08-18 | Telecommunications Radioelectriques Et Telephoniques, Trt | Optical and mechanical scanning device |
US5114662A (en) * | 1987-05-26 | 1992-05-19 | Science Applications International Corporation | Explosive detection system |
US5006299A (en) * | 1987-05-26 | 1991-04-09 | Science Applications International Corporation | Explosive detection system |
JP3378401B2 (ja) * | 1994-08-30 | 2003-02-17 | 株式会社日立メディコ | X線装置 |
US6148095A (en) * | 1997-09-08 | 2000-11-14 | University Of Iowa Research Foundation | Apparatus and method for determining three-dimensional representations of tortuous vessels |
US6345113B1 (en) * | 1999-01-12 | 2002-02-05 | Analogic Corporation | Apparatus and method for processing object data in computed tomography data using object projections |
US6539330B2 (en) * | 2000-07-19 | 2003-03-25 | Pentax Corporation | Method and apparatus for measuring 3-D information |
US7813540B1 (en) * | 2005-01-13 | 2010-10-12 | Oro Grande Technologies Llc | System and method for detecting nuclear material in shipping containers |
JP4632891B2 (ja) * | 2005-07-22 | 2011-02-16 | 株式会社モリタ製作所 | X線ct撮影装置およびx線ct撮影方法 |
CN101326437A (zh) * | 2005-12-12 | 2008-12-17 | 显示成像技术有限公司 | 移置光线型ct检查 |
CN101382508A (zh) * | 2007-09-05 | 2009-03-11 | 同方威视技术股份有限公司 | 一种检查航空货运集装箱中违禁物品的装置和方法 |
WO2010064687A1 (ja) * | 2008-12-05 | 2010-06-10 | 株式会社 日立メディコ | 医用画像表示装置及び医用画像表示方法 |
CN103903297B (zh) * | 2012-12-27 | 2016-12-28 | 同方威视技术股份有限公司 | 三维数据处理和识别方法 |
CN103900503B (zh) | 2012-12-27 | 2016-12-28 | 清华大学 | 提取形状特征的方法、安全检查方法以及设备 |
-
2012
- 2012-12-27 CN CN201210581559.9A patent/CN103903298B/zh active Active
-
2013
- 2013-07-05 JP JP2015549950A patent/JP6013621B2/ja not_active Expired - Fee Related
- 2013-07-05 KR KR1020157020434A patent/KR101813771B1/ko active IP Right Grant
- 2013-07-05 WO PCT/CN2013/078884 patent/WO2014101387A1/zh active Application Filing
- 2013-12-20 US US14/136,426 patent/US9111128B2/en active Active
- 2013-12-23 EP EP13199463.4A patent/EP2750078B1/en not_active Not-in-force
- 2013-12-23 PL PL13199463T patent/PL2750078T3/pl unknown
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1993710A (zh) * | 2004-06-01 | 2007-07-04 | 美国西门子医疗解决公司 | 改进使用切割平面检测球状和椭圆状对象的分水岭分割 |
CN101320397A (zh) * | 2007-06-07 | 2008-12-10 | 乐必峰软件公司 | 使用三维扫描数据计算放样表面的系统和方法 |
CN101499177A (zh) * | 2008-01-28 | 2009-08-05 | 上海西门子医疗器械有限公司 | 一种三维模型的建立方法和系统 |
Also Published As
Publication number | Publication date |
---|---|
EP2750078A3 (en) | 2016-06-01 |
CN103903298B (zh) | 2017-03-01 |
US9111128B2 (en) | 2015-08-18 |
JP2016505976A (ja) | 2016-02-25 |
PL2750078T3 (pl) | 2019-02-28 |
EP2750078A2 (en) | 2014-07-02 |
KR101813771B1 (ko) | 2017-12-29 |
EP2750078B1 (en) | 2018-09-12 |
KR20150103160A (ko) | 2015-09-09 |
US20140185874A1 (en) | 2014-07-03 |
CN103903298A (zh) | 2014-07-02 |
JP6013621B2 (ja) | 2016-10-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2014101387A1 (zh) | 三维数据处理和识别方法 | |
US9465975B2 (en) | Three-dimensional data processing and recognizing method involving inspecting an object and extracting data matching to features | |
AU2013370770A1 (en) | Method for processing and identifying three-dimensional data | |
Fry | Random point distributions and strain measurement in rocks | |
Wei et al. | Occluded prohibited items detection: An x-ray security inspection benchmark and de-occlusion attention module | |
US7945105B1 (en) | Automated target shape detection for vehicle muon tomography | |
US9087267B2 (en) | Image scene recognition | |
Zhang et al. | Automated method for extracting and analysing the rock discontinuities from point clouds based on digital surface model of rock mass | |
EP2762928B1 (en) | Recognizing method of flaky or blocky prohibited articles, explosives or drugs | |
WO2012044296A1 (en) | Object classification using two-dimensional projection | |
CN106372111A (zh) | 局部特征点筛选方法及系统 | |
CN104658034B (zh) | Ct图像数据的融合绘制方法 | |
CN111028345A (zh) | 一种港口场景下圆形管道的自动识别与对接方法 | |
Yong et al. | Class ratio transform with an application to describing the roughness anisotropy of natural rock joints | |
Daghigh et al. | Discontinuity plane extraction from a rock mass point cloud using unsupervised machine learning | |
Ponce et al. | Seeking for toroidal event horizons from initially stationary BH configurations | |
CN113076880A (zh) | 一种危险品图形识别算法 | |
Tonbul et al. | The effect of shape and compactness parameters on segmentation quality: a case study | |
Wu et al. | A graph-based approach for rectangle detection using corners | |
Qiu et al. | Multi-Aspect Feature Enhancement Network for Aircraft Detection in High-Resolution SAR Images | |
Tucker et al. | Statistical analysis and classification of acoustic color functions | |
US20230228904A1 (en) | Muon tomography method and apparatus | |
CN112287907A (zh) | 一种基于点云密度梯度的孔洞识别方法 | |
Du et al. | Cross-section analysis method of ice-covered power lines for UAV blasting de-icing | |
Waxman et al. | Small particle impact damage on different glass substrates |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13868073 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015549950 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 20157020434 Country of ref document: KR Kind code of ref document: A |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 13868073 Country of ref document: EP Kind code of ref document: A1 |