CN112070098B - Hyperspectral image salient target detection method based on frequency adjustment model - Google Patents
Hyperspectral image salient target detection method based on frequency adjustment model Download PDFInfo
- Publication number
- CN112070098B CN112070098B CN202010844360.5A CN202010844360A CN112070098B CN 112070098 B CN112070098 B CN 112070098B CN 202010844360 A CN202010844360 A CN 202010844360A CN 112070098 B CN112070098 B CN 112070098B
- Authority
- CN
- China
- Prior art keywords
- spectral
- image
- saliency
- map
- frequency adjustment
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 230000003595 spectral effect Effects 0.000 claims abstract description 54
- 238000001228 spectrum Methods 0.000 claims abstract description 35
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 description 9
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/58—Extraction of image or video features relating to hyperspectral data
-
- 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
- G06V2201/07—Target detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Spectrometry And Color Measurement (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a hyperspectral image salient target detection method based on a frequency adjustment model, which is implemented according to the following steps: 1. inputting a hyperspectral image and an RGB image corresponding to the hyperspectral image; 2. performing remarkable target detection on the hyperspectral RGB image by using a frequency adjustment model to obtain a remarkable graph of a frequency adjustment algorithm; 3. calculating spectral significance of the spectral band of the hyperspectral image in the step 1 by utilizing the spectral angular distance to obtain a spectral significance map; 4. and (3) respectively normalizing the frequency adjustment algorithm saliency map obtained in the step (2) and the spectrum saliency map obtained in the step (3), and then fusing to form a final hyperspectral image saliency target map. The invention solves the problems of fuzzy edge and incomplete information of the detected target of the existing hyperspectral image, and can completely represent the target object while ensuring the edge of the target to be accurate, thereby greatly improving the accuracy rate of the remarkable target detection.
Description
Technical Field
The invention belongs to the technical field of image processing, and relates to a hyperspectral image salient target detection method based on a frequency adjustment model.
Background
The significant target detection of the hyperspectral image has important significance in the aspects of image segmentation, target tracking, image classification and the like. The hyperspectral image contains a large amount of spectral information, the spectral response is related to the materials of various objects in the actual scene, and more accurate information can be provided for target detection. However, redundant spectral information also interferes with the process of target detection. Therefore, it is important how to quickly find effective information in a large amount of hyperspectral data without damaging the target quality.
Visual saliency detection can quickly select a region of interest from natural scenes. In the aspect of computer vision, the saliency detection mainly simulates a human vision attention mechanism, and realizes the extraction of a salient target in an image. Therefore, many people apply visual saliency algorithms to object detection of natural images to quickly find a region of interest. If an attempt is made to combine hyperspectral data with a saliency detection model, component bands as well as raw spectral features are described, replacing the bicolor opponent component in the Itti model with them. Or using spectral gradient contrast to calculate saliency, solves the problem of high contrast edge sensitivity caused by detection on the Itti model. However, some existing saliency detection algorithms still have some drawbacks for the detection of hyperspectral images, such as not well presenting boundaries of salient objects and insufficient description of objects, etc.
Therefore, how to quickly find the remarkable target of the hyperspectral image, and describe the target object more accurately are very important technology for the target detection field of the hyperspectral image.
Disclosure of Invention
The invention aims to provide a hyperspectral image remarkable target detection method based on a frequency adjustment model, which solves the problems of large calculated amount and blurred edges of detection targets in the hyperspectral image target detection method in the prior art.
The technical scheme adopted by the invention is that the hyperspectral image salient target detection method based on the frequency adjustment model is implemented according to the following steps:
step 1, inputting a hyperspectral image and an RGB image corresponding to the hyperspectral image;
step 2, performing significant target detection on the hyperspectral RGB image by using a frequency adjustment model to obtain a significant map of a frequency adjustment algorithm;
step 3, calculating spectral significance of the spectral band of the hyperspectral image in the step 1 by utilizing the spectral angular distance to obtain a spectral significance map;
and 4, respectively normalizing the frequency adjustment algorithm saliency map obtained in the step 2 and the spectrum saliency map obtained in the step 3, and then fusing to form a final hyperspectral image saliency target map.
The invention is also characterized in that:
the step 2 is specifically implemented according to the following steps:
step 2.1, performing color space transformation on an RGB image of the hyperspectral image, and transforming the image from the RGB space to the LAB space;
step 2.2, processing the hyperspectral image by using Gaussian filtering to obtain a Gaussian filtered image;
step 2.3, calculating the mean value of each pixel point in the LAB space and the pixel point of the Gaussian filtered image by using Euclidean distance to obtain a pixel significance value;
and 2.4, normalizing the significance value of each pixel to obtain a significance map of the frequency adjustment algorithm.
The pixel saliency value in step 2.3 is calculated as follows:
S(x，y)＝||Iμ(x，y)-Iwhc(x，y)|| (1)；
wherein,
where S (x, y) is the saliency value of the pixel, I μ (x, y) is the arithmetic mean of the image pixels, lab color features are used, iwhc (x, y) is the corresponding image pixel value after gaussian blur, and I is the euclidean distance.
The saliency map of the frequency adjustment algorithm in step 2.4 is calculated as follows:
where S (x, y) is the saliency value of the pixel, max [ S (x, y)]Representing the maximum saliency value, sal, of an image pixel FT Is a saliency map of the frequency adjustment algorithm obtained through normalization.
The step 3 is specifically implemented according to the following steps:
step 3.1, calculating the spectrum angle distance between the spectrum bands as the spectrum characteristics of the hyperspectral image, so as to obtain a spectrum characteristic diagram;
and 3.2, normalizing the spectrum characteristic diagram obtained in the step 3.1 to obtain a spectrum saliency map.
The spectral signature in step 3.1 is calculated as follows:
wherein M is c And M is as follows s Representing different spectral bands, SAD (c, s) represents the spectral angular distance between the different bands.
The calculation of the spectral saliency map in step 3.2 is as follows:
wherein SAD (c, s) represents the spectral angular distance between different bands, max (SAD (c, s)) represents the maximum spectral angular distance between spectral bands, sal Spectral And (5) representing a spectrum saliency map obtained by normalizing the spectrum characteristic map.
The salient target map of the hyperspectral image in step 4 is calculated as follows:
wherein S represents a salient object map of the hyperspectral image; sal (Sal) FT Representing a saliency map calculated by a frequency adjustment algorithm; sal (Sal) Spectral A spectral saliency map is shown.
The beneficial effects of the invention are as follows:
(1) According to the method, a frequency adjustment significance detection algorithm is introduced into target detection of the hyperspectral image, so that a significant target with a clear boundary can be obtained rapidly and effectively;
(2) According to the invention, the frequency adjustment significance detection algorithm is combined with the spectrum significance, so that the information of the spectrum characteristics is fully utilized, a more accurate target is obtained, and the detection accuracy is improved;
(3) The method and the device can quickly and effectively find the obvious target area of the hyperspectral image by using the saliency detection algorithm, detect the spectrum information of the hyperspectral image, more completely describe the information of the target object and improve the accuracy rate of target detection.
Drawings
FIG. 1 is a flow chart of a method for detecting a salient object of a hyperspectral image based on a frequency adjustment model of the present invention;
FIG. 2 is a saliency map calculated according to a frequency adjustment algorithm in the method for detecting a hyperspectral image saliency target based on a frequency adjustment model of the present invention;
FIG. 3 is a spectrum saliency map calculated according to a spectrum angular distance in the hyperspectral image saliency target detection method based on a frequency adjustment model of the present invention;
fig. 4 is a final salient object result graph of the hyperspectral image salient object detection method based on the frequency adjustment model of the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings and the detailed description.
The method for detecting the hyperspectral image salient target based on the frequency adjustment model is implemented as shown in fig. 1, and specifically comprises the following steps:
step 1, inputting a hyperspectral image and an RGB image corresponding to the hyperspectral image by using a published hyperspectral image saliency detection data set;
step 2, performing significant target detection on the hyperspectral RGB image by using a frequency adjustment model to obtain a significant map of a frequency adjustment algorithm, wherein the method is implemented specifically according to the following steps:
step 2.1, performing color space transformation on an RGB image of the hyperspectral image, and transforming the image from the RGB space to the LAB space;
step 2.2, processing the hyperspectral image by using Gaussian filtering to obtain a Gaussian filtered image;
and 2.3, calculating the mean value of each pixel point in the LAB space and the pixel point of the Gaussian filtered image by using Euclidean distance as pixel saliency values, wherein the pixel saliency values are calculated according to the following formula:
S(x，y)＝||Iμ(x，y)-Iwhc(x，y)|| (1)；
wherein,
where S (x, y) is the saliency value of the pixel, I μ (x, y) is the arithmetic mean of the image pixels, lab color features are used, iwhc (x, y) is the corresponding image pixel value after gaussian blur (using 5*5 binomial filter) to eliminate texture details and noise, and I is the euclidean distance;
step 2.4, normalizing the significance value of each pixel to obtain a significance map of a frequency adjustment algorithm, wherein the normalized significance map is calculated by a formula (2), and the significance map obtained by the frequency adjustment algorithm is shown in fig. 2;
where S (x, y) is the saliency value of the pixel, max [ S (x, y)]Representing the maximum saliency value, sal, of an image pixel FT In order to obtain a saliency map of the frequency adjustment algorithm through normalization, the pixel value of the image is converted into 0-1 from 0-255 through normalization, and the original information storage of the image is not changed, so that the method has great benefits for the subsequent image processing operation;
and 3, calculating spectral significance of the spectral bands of the hyperspectral image in the step 1 by utilizing the spectral angular distance to obtain a spectral significance map, wherein the method is implemented specifically according to the following steps:
step 3.1, calculating the spectrum angle distance between the spectrum bands as the spectrum characteristics of the hyperspectral image, so as to obtain a spectrum characteristic diagram;
the spectral signature is calculated as follows:
wherein M is c And M is as follows s Representing different spectral bands, SAD (c, s) representing spectral angular distances between different bands, the greater the spectral angular distance, the greater the difference between the two bands, indicating greater significance; the smaller the spectral angular distance, the smaller the difference between the two bands, indicating a stronger significance;
and 3.2, normalizing the spectrum characteristic diagram obtained in the step 3.1 to obtain a spectrum saliency diagram, wherein the calculation of the spectrum saliency diagram is as follows:
wherein SAD (c, s) represents the spectral angular distance between different bands, max (SAD (c, s)) represents the maximum spectral angular distance between spectral bands, sal Spectral The spectrum saliency map obtained by normalizing the spectrum characteristic map is represented; the spectrum saliency map is shown in figure 3;
and 4, respectively normalizing the frequency adjustment algorithm saliency map obtained in the step 2 and the spectrum saliency map obtained in the step 3, and then fusing to form a final hyperspectral image saliency target map, wherein the calculation of the hyperspectral image saliency target map is as follows:
wherein S represents a salient object map of the hyperspectral image; sal (Sal) FT Representation generalA saliency map obtained by calculation through a frequency adjustment algorithm; sal (Sal) Spectral A significant target result graph representing a spectral significance map, a hyperspectral image is shown in fig. 4.
As can be seen from fig. 2: the target object of the saliency map of the hyperspectral image obtained by utilizing the frequency adjustment saliency algorithm has a definite boundary;
as can be seen from fig. 3: the introduction of the spectral information more fully describes the target object;
as can be seen from fig. 4: the hyperspectral image salient object detection method based on the frequency adjustment model obtains objects with clear boundary definition, and meanwhile, the salient objects are more completely described by adding the spectral characteristics.
Claims (1)
1. The hyperspectral image salient target detection method based on the frequency adjustment model is characterized by comprising the following steps of:
step 1, inputting a hyperspectral image and an RGB image corresponding to the hyperspectral image;
step 2, performing significant target detection on the hyperspectral RGB image by using a frequency adjustment model to obtain a significant map of a frequency adjustment algorithm;
the step 2 is specifically implemented according to the following steps:
step 2.1, performing color space transformation on an RGB image of the hyperspectral image, and transforming the image from the RGB space to the LAB space;
step 2.2, processing the hyperspectral image by using Gaussian filtering to obtain a Gaussian filtered image;
step 2.3, calculating the mean value of each pixel point in the LAB space and the pixel point of the Gaussian filtered image by using Euclidean distance to obtain a pixel significance value;
the pixel saliency value in step 2.3 is calculated as follows:
S(x，y)＝||Iμ(x，y)-Iwhc(x，y)||
(1)；
wherein,
where S (x, y) is the saliency value of the pixel, I [ mu ] (x, y) is the arithmetic mean of the image pixels, the Lab color features are used, iwhc (x, y) is the corresponding image pixel value after Gaussian blur, and I is the Euclidean distance;
step 2.4, normalizing the significance value of each pixel to obtain a significance map of a frequency adjustment algorithm;
the calculation of the saliency map of the frequency adjustment algorithm in step 2.4 is as follows:
where S (x, y) is the saliency value of the pixel, max [ S (x, y)]Representing the maximum saliency value, sal, of an image pixel FT A saliency map of a frequency adjustment algorithm obtained through normalization;
step 3, calculating spectral significance of the spectral band of the hyperspectral image in the step 1 by utilizing the spectral angular distance to obtain a spectral significance map;
the step 3 is specifically implemented according to the following steps:
step 3.1, calculating the spectrum angle distance between the spectrum bands as the spectrum characteristics of the hyperspectral image, so as to obtain a spectrum characteristic diagram;
the calculation of the spectral signature in step 3.1 is as follows:
wherein M is c And M is as follows s Representing different spectral bands, SAD (c, s) representing the spectral angular distance between the different bands;
step 3.2, normalizing the spectrum characteristic diagram obtained in the step 3.1 to obtain a spectrum saliency map;
the calculation of the spectral saliency map in step 3.2 is as follows:
wherein SAD (c, s) represents the spectral angular distance between different bands, max (SAD (c, s)) represents the maximum spectral angular distance between spectral bands, sal Spectral The spectrum saliency map obtained by normalizing the spectrum characteristic map is represented;
step 4, respectively normalizing the frequency adjustment algorithm saliency map obtained in the step 2 and the spectrum saliency map obtained in the step 3, and then fusing to form a final hyperspectral image saliency target map;
the calculation of the salient object map of the hyperspectral image in the step 4 is as follows:
wherein S represents a salient object map of the hyperspectral image; sal (Sal) FT Representing a saliency map calculated by a frequency adjustment algorithm; sal (Sal) Spectral A spectral saliency map is shown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010844360.5A CN112070098B (en) | 2020-08-20 | 2020-08-20 | Hyperspectral image salient target detection method based on frequency adjustment model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010844360.5A CN112070098B (en) | 2020-08-20 | 2020-08-20 | Hyperspectral image salient target detection method based on frequency adjustment model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112070098A CN112070098A (en) | 2020-12-11 |
| CN112070098B true CN112070098B (en) | 2024-02-09 |
Family
ID=73662405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010844360.5A Active CN112070098B (en) | 2020-08-20 | 2020-08-20 | Hyperspectral image salient target detection method based on frequency adjustment model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112070098B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194099A (en) * | 2010-02-17 | 2011-09-21 | 波音公司 | Advanced background estimation technique and circuit for a hyper-spectral target detection method |
| CN103729848A (en) * | 2013-12-28 | 2014-04-16 | 北京工业大学 | Hyperspectral remote sensing image small target detection method based on spectrum saliency |
| CN107274416A (en) * | 2017-06-13 | 2017-10-20 | 西北工业大学 | High spectrum image conspicuousness object detection method based on spectrum gradient and hierarchical structure |
| CA3032487A1 (en) * | 2016-08-03 | 2018-02-08 | Jiangsu University | Saliency-based method for extracting road target from night vision infrared image |
| WO2018081929A1 (en) * | 2016-11-01 | 2018-05-11 | 深圳大学 | Hyperspectral remote sensing image feature extraction and classification method and system thereof |
-
2020
- 2020-08-20 CN CN202010844360.5A patent/CN112070098B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194099A (en) * | 2010-02-17 | 2011-09-21 | 波音公司 | Advanced background estimation technique and circuit for a hyper-spectral target detection method |
| CN103729848A (en) * | 2013-12-28 | 2014-04-16 | 北京工业大学 | Hyperspectral remote sensing image small target detection method based on spectrum saliency |
| CA3032487A1 (en) * | 2016-08-03 | 2018-02-08 | Jiangsu University | Saliency-based method for extracting road target from night vision infrared image |
| WO2018081929A1 (en) * | 2016-11-01 | 2018-05-11 | 深圳大学 | Hyperspectral remote sensing image feature extraction and classification method and system thereof |
| CN107274416A (en) * | 2017-06-13 | 2017-10-20 | 西北工业大学 | High spectrum image conspicuousness object detection method based on spectrum gradient and hierarchical structure |
Non-Patent Citations (2)
| Title |
|---|
| 徐金婧 ; 徐熙平 ; .基于时空显著特征的运动目标检测方法研究.长春理工大学学报(自然科学版).2020,(第04期),全文. * |
| 王曼 ; 王军 ; 丁娜 ; 解俊虎 ; 高蒙 ; 刘方 ; 郑雅卫 ; 李琼 ; .一种结合AOTF的偏振光谱目标检测算法.国外电子测量技术.2020,(第02期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112070098A (en) | 2020-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103020965B (en) | A kind of foreground segmentation method based on significance detection | |
| CN107610114B (en) | optical satellite remote sensing image cloud and snow fog detection method based on support vector machine | |
| CN109919960B (en) | Image continuous edge detection method based on multi-scale Gabor filter | |
| CN108446584B (en) | Automatic detection method for unmanned aerial vehicle reconnaissance video image target | |
| CN102496157B (en) | Image detection method based on Gaussian multi-scale transform and color complexity | |
| US20140063275A1 (en) | Visual saliency estimation for images and video | |
| CN102693426B (en) | Method for detecting image salient regions | |
| CN102426649A (en) | Simple steel seal digital automatic identification method with high accuracy rate | |
| CN109978848B (en) | Method for detecting hard exudation in fundus image based on multi-light-source color constancy model | |
| CN105590319A (en) | Method for detecting image saliency region for deep learning | |
| CN101916446A (en) | Gray level target tracking algorithm based on marginal information and mean shift | |
| CN105894520B (en) | A kind of automatic cloud detection method of optic of satellite image based on gauss hybrid models | |
| CN111489330B (en) | Weak and small target detection method based on multi-source information fusion | |
| CN111369605A (en) | Infrared and visible light image registration method and system based on edge features | |
| CN112308873B (en) | Edge detection method for multi-scale Gabor wavelet PCA fusion image | |
| CN115994870B (en) | Image processing method for enhancing denoising | |
| CN109767442B (en) | Remote sensing image airplane target detection method based on rotation invariant features | |
| Shi et al. | Urban feature shadow extraction based on high-resolution satellite remote sensing images | |
| CN108520252B (en) | Road sign identification method based on generalized Hough transform and wavelet transform | |
| CN112183633B (en) | Hyperspectral image salient target detection method based on improved FT algorithm | |
| CN107704864B (en) | Salient object detection method based on image object semantic detection | |
| CN106021610B (en) | A kind of method for extracting video fingerprints based on marking area | |
| CN112070098B (en) | Hyperspectral image salient target detection method based on frequency adjustment model | |
| CN111611940A (en) | Rapid video face recognition method based on big data processing | |
| Zhang et al. | Region-of-interest extraction based on spectrum saliency analysis and coherence-enhancing diffusion model in remote sensing images |
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 |