CN110322452B - Multispectral image oil material distinguishing method and device - Google Patents
Multispectral image oil material distinguishing method and device Download PDFInfo
- Publication number
- CN110322452B CN110322452B CN201910597026.1A CN201910597026A CN110322452B CN 110322452 B CN110322452 B CN 110322452B CN 201910597026 A CN201910597026 A CN 201910597026A CN 110322452 B CN110322452 B CN 110322452B
- Authority
- CN
- China
- Prior art keywords
- pixel
- map
- area
- pixel points
- processed
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/10024—Color image
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
As can be seen from the above technology, the present application provides a method and an apparatus for dividing oil areas in multispectral images, wherein the method includes: separating a luminance map from the multispectral image; enhancing the contrast of the brightness map to obtain a processed brightness map; determining an initial region in the processed luminance map; calculating pixel difference values of the initial area and each adjacent pixel point; determining pixel points to be combined; merging the pixel points to be merged into the initial region to obtain a growth region; and repeating the steps of calculating the pixel difference and merging the pixels to be merged until the latest growing area does not have the pixels to be merged, thereby obtaining the target area. The multi-spectrum image oil material region dividing method provided by the application can accurately identify each pixel point belonging to the oil material region, and further accurately divide the oil material region.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a multispectral image oil material distinguishing method and device.
Background
The oil leakage of the transformer not only causes the damage of an internal insulation system and reduces the insulation strength of the transformer, but also can cause the power failure of the transformer. The transformer is shot by using multispectral, multispectral images are timely acquired, so that the problem of leakage of transformer oil liquid can be effectively and conveniently found, and the operation and maintenance quality of equipment is ensured.
The ultraviolet light in the multispectral can take place fluorescence effect when shining the oil, and the multispectral image of gathering can be comparatively bright in its oil region after the integration, if can detect and divide the oil region on the multispectral image, can more conveniently, accurately estimate the oil region area, and then improve the detection accuracy of transformer oil leak condition.
Disclosure of Invention
The application provides a multi-spectrum image oil area dividing method and device, which are used for improving the dividing accuracy of oil areas in multi-spectrum images.
In a first aspect, an embodiment of the present application provides a multispectral image oil classification method, including:
separating a brightness map from the multispectral image, wherein the brightness map is a channel image corresponding to a Y component in RGB pixel values of the multispectral image;
enhancing the contrast of the brightness map to obtain a processed brightness map;
determining an initial area in the processed brightness map, wherein the initial area is a square area which is formed by taking a pixel point in a multispectral image as a center and adjacent 9 pixel points and is a pixel value and a maximum pixel area in the processed brightness map;
calculating pixel difference values of the initial region and each adjacent pixel point, wherein the adjacent pixel points are 16 pixel points which take the initial region as a center and are adjacent to the initial region;
determining pixel points to be combined, wherein the pixel points to be combined are adjacent pixel points of which the pixel difference value is smaller than a preset difference value threshold value;
merging the pixel points to be merged into the initial region to obtain a growth region;
and repeating the steps of calculating pixel difference values and merging the pixel points to be merged until the latest growing area does not have the pixel points to be merged, so as to obtain a target area, wherein the target area is the latest growing area.
Optionally, the separating the luminance map from the multispectral image includes:
according to a preset pixel component formula, Y, U, V components of all pixels in the multispectral image are calculated;
and extracting Y components corresponding to all the pixel points to obtain a brightness map.
Optionally, the enhancing the contrast of the luminance map, the obtaining the processed luminance map includes:
according to the following equation, the pixel values of the processed luminance map are calculated,
wherein V represents the pixel value of the brightness map, V' represents the pixel value of the brightness map after processing, and b is a correlation coefficient;
and combining the pixel values of the processed brightness map to obtain the processed brightness map.
Optionally, the determining the pixel point to be combined includes:
according to the following, a preset difference threshold is calculated,
wherein T represents a preset difference threshold and b represents a correlation coefficient.
In a second aspect, the present application provides a multispectral image oil region division apparatus, comprising:
the separation unit is used for separating a brightness map from the multispectral image, wherein the brightness map is a channel image corresponding to a Y component in RGB pixel values of the multispectral image;
the contrast enhancement unit is used for enhancing the contrast of the brightness map to obtain a processed brightness map;
an initial region determining unit, configured to determine an initial region in the processed luminance map, where the initial region is a pixel value and a largest pixel region in the processed luminance map, and the pixel region is a square region formed by taking a pixel point in a multispectral image as a center and adjacent 9 pixel points;
a pixel difference calculating unit, configured to calculate a pixel difference between the initial area and each adjacent pixel point, where the adjacent pixel point is 16 pixel points that are centered on the initial area and adjacent to the initial area;
the pixel point to be combined determining unit is used for determining the pixel points to be combined, wherein the pixel points to be combined are adjacent pixel points with pixel difference values smaller than a preset difference value threshold value;
the pixel point merging unit is used for merging the pixel points to be merged into the initial area to obtain a growth area;
and the target area determining unit is used for repeatedly calculating pixel difference values and merging pixel points to be merged until the latest growing area does not have the pixel points to be merged, so as to obtain a target area, wherein the target area is the latest growing area.
Optionally, the separation unit includes:
according to a preset pixel component formula, Y, U, V components of all pixels in the multispectral image are calculated;
and extracting Y components corresponding to all the pixel points to obtain a brightness map.
Optionally, the contrast enhancement unit includes:
a pixel value calculating unit for calculating a pixel value of the processed luminance map according to the following formula,
wherein V represents the pixel value of the brightness map, V' represents the pixel value of the brightness map after processing, and b is a correlation coefficient;
and the processed brightness map generating unit is used for combining the pixel values of the processed brightness map to obtain the processed brightness map.
Optionally, the pixel point to be combined determining unit includes:
a preset difference threshold calculation unit for calculating a preset difference threshold according to the following equation,
wherein T represents a preset difference threshold and b represents a correlation coefficient.
As can be seen from the above technology, the present application provides a method and an apparatus for dividing oil areas in multispectral images, wherein the method includes: separating a luminance map from the multispectral image; enhancing the contrast of the brightness map to obtain a processed brightness map; determining an initial region in the processed luminance map; calculating pixel difference values of the initial area and each adjacent pixel point; determining pixel points to be combined; merging the pixel points to be merged into the initial region to obtain a growth region; and repeating the steps of calculating the pixel difference and merging the pixels to be merged until the latest growing area does not have the pixels to be merged, thereby obtaining the target area. When the multi-spectral image capturing device is used, a brightness map corresponding to a Y component in RGB pixel values of the multi-spectral image needs to be separated from the multi-spectral image obtained through capturing. Then, the contrast of the luminance map is further enhanced, resulting in a processed luminance map. And determining an initial area with the largest pixel value in the processed brightness map. And determining pixel points to be combined around the initial region by calculating pixel difference values of the initial region and each adjacent pixel point, and combining the pixel points to be combined into the initial region to obtain a growth region. If the adjacent pixel points close to the growth area still have the pixel points to be combined, continuing to combine the pixel points to be combined until the latest growth area does not have the pixel points to be combined, and obtaining the target area. The multi-spectrum image oil material region dividing method provided by the application can accurately identify each pixel point belonging to the oil material region, and further accurately divide the oil material region.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a flowchart of a method for partitioning oil areas in a multispectral image according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for separating luminance graphs from multispectral images according to an embodiment of the present application;
FIG. 3 is a flowchart of a method for enhancing contrast of a luminance map according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of an initial region and adjacent pixels thereof according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a multi-spectral image oil area dividing device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of a method for partitioning oil areas in a multispectral image according to an embodiment of the present application is provided, where the method includes:
s1, separating a brightness map from the multispectral image, wherein the brightness map is a channel image corresponding to a Y component in RGB pixel values of the multispectral image.
The pixel value of each pixel point of the multispectral image contains the values of three RGB channels, so that the components corresponding to any channel can be extracted according to the needs, and the corresponding channel image can be obtained.
Specifically, as shown in fig. 2, a flowchart of a method for separating a luminance map from a multispectral image according to an embodiment of the present application is provided, where the method includes:
s101, calculating Y, U, V components of each pixel point in a multispectral image according to a preset pixel point component formula;
s102, extracting Y components corresponding to all pixel points to obtain a brightness map.
The present embodiments provide a predetermined pixel component formula,it should be noted that, according to the actual requirement, the parameters in the pixel point component formula of the Yi-to-custom river can be adjusted. According to the formula, Y, U, V components corresponding to all pixel points in the multispectral image can be calculated, and in the embodiment of the present application, the channel image corresponding to the Y component is set as the luminance map, and the Y components corresponding to all the pixel points need to be extracted, so as to obtain the luminance map.
S2, enhancing the contrast of the brightness map to obtain a processed brightness map;
and determining an initial area in the processed brightness map, wherein the initial area is a square area which is formed by taking a pixel point in a multispectral image as a center and adjacent 9 pixel points and is a pixel value and a maximum pixel area in the processed brightness map.
The contrast is enhanced for the luminance map, which typically has a pixel value ranging from 0 to 255, and thus each pixel within the luminance map is changed using an adjusted exponential function in order to enhance the contrast of the luminance map.
Specifically, as shown in fig. 3, a flowchart of a method for enhancing contrast of a luminance map according to an embodiment of the present application is provided, where the method includes:
s201, calculating the pixel value of the brightness image after processing according to the following formula,
wherein V represents the pixel value of the brightness map, V' represents the pixel value of the brightness map after processing, and b is a correlation coefficient;
s202, combining the pixel values of the processed brightness map to obtain the processed brightness map.
The pixel value of the luminance map after processing can be calculated according to the above formula, wherein the larger the b value is, the stronger the suppression effect on the dark portion in the luminance map is, the stronger the emphasis effect on the bright portion is, and the value of the b value is related to the pixel distribution of the luminance map, and in this embodiment, b=10 is preferable. After the pixel values of the processed luminance map are calculated, the processed luminance map can be correspondingly obtained.
S3, determining an initial area in the processed brightness map, wherein the initial area is a pixel value and a maximum pixel area in the processed brightness map, and the pixel area is a square area which takes a pixel point in a multispectral image as a center and is formed by 9 adjacent pixel points.
The multispectral image is composed of pixel points, each pixel point is a point to be detected, the pixel points are taken as the center, and 8 adjacent pixel points on the left upper, upper right, left right, lower left, lower right and lower right are adjacent around the pixel points, so that a square area of 3×3 areas can be formed, and therefore, the multispectral image can form a plurality of square areas taking the pixel points as the center. Each square area has respective pixel value sums, and the pixel value and the largest square area are set as initial areas.
S4, calculating pixel difference values of the initial area and each adjacent pixel point, wherein the adjacent pixel points are 16 pixel points which are centered on the initial area and are adjacent to the initial area.
And (3) performing region growth by taking the central point of the initial region as a starting point, namely merging adjacent pixel points meeting merging conditions by taking the central point of the initial region as a starting point, and growing the pixel points into a pixel region capable of representing an oil region.
As shown in fig. 4, the initial area is a hatched area, and the blank area is an area corresponding to adjacent pixels, and it can be seen that the adjacent pixels in the initial area are 16. Each pixel point has a respective pixel value, so that a pixel difference value between the initial region and each adjacent pixel point can be calculated.
S5, determining pixel points to be combined, wherein the pixel points to be combined are adjacent pixel points with pixel difference values smaller than a preset difference value threshold.
Specifically, a preset difference threshold is calculated according to the following equation,
wherein T represents a preset difference threshold and b represents a correlation coefficient.
S6, merging the pixel points to be merged into the initial region to obtain a growth region;
and S7, repeating the steps of calculating pixel difference values and merging pixel points to be merged until the latest growing area does not have the pixel points to be merged, and obtaining a target area, wherein the target area is the latest growing area.
After the growth area is obtained, the current growth area is taken as an initial area, pixel points to be combined of the initial area are determined again according to the steps of S4-S5, a new growth area is formed after the pixel points to be combined are combined, and then the steps of S5-S6 are repeated continuously until the pixel points to be combined are not needed in the latest growth area, and the growth area at the moment is the final obtained target area.
Therefore, the multi-spectrum image oil region dividing method provided by the application can accurately identify each pixel point belonging to the oil region, and further accurately divide the oil region.
Fig. 5 is a schematic structural diagram of a multi-spectral image oil area dividing device according to an embodiment of the present application, including:
a separation unit 1, configured to separate a luminance map from a multispectral image, where the luminance map is a channel image corresponding to a Y component in RGB pixel values of the multispectral image;
a contrast enhancement unit 2, configured to enhance the contrast of the luminance map, and obtain a processed luminance map;
an initial region determining unit 3, configured to determine an initial region in the processed luminance map, where the initial region is a pixel value and a largest pixel region in the processed luminance map, and the pixel region is a square region formed by taking a pixel point in a multispectral image as a center and adjacent 9 pixel points;
a pixel difference calculating unit 4, configured to calculate a pixel difference between the initial area and each adjacent pixel point, where the adjacent pixel point is 16 pixel points that are centered on the initial area and adjacent to the initial area;
the pixel point to be combined determining unit 5 is configured to determine a pixel point to be combined, where the pixel point to be combined is an adjacent pixel point whose pixel difference value is smaller than a preset difference value threshold value;
a merging pixel point unit 6, configured to merge the pixel points to be merged into the initial area to obtain a growth area;
and the target area determining unit 7 is used for repeatedly calculating the pixel difference value and merging the pixel points to be merged until the latest growing area does not have the pixel points to be merged, so as to obtain a target area, wherein the target area is the latest growing area.
Optionally, the separation unit 1 comprises: according to a preset pixel component formula, Y, U, V components of all pixels in the multispectral image are calculated; and extracting Y components corresponding to all the pixel points to obtain a brightness map.
Optionally, the contrast enhancement unit 2 includes: a pixel value calculating unit for calculating a pixel value of the processed luminance map according to the following formula,
wherein V represents the pixel value of the brightness map, V' represents the pixel value of the brightness map after processing, and b is a correlation coefficient; and the processed brightness map generating unit is used for combining the pixel values of the processed brightness map to obtain the processed brightness map.
Optionally, the pixel point to be combined determining unit 6 includes: a preset difference threshold calculation unit for calculating a preset difference threshold according to the following equation,
wherein T represents a preset difference threshold and b represents a correlation coefficient.
It should be noted that, in a specific implementation, the present invention further provides a computer storage medium, where the computer storage medium may store a program, where the program may include some or all of the steps in each embodiment of the service providing method or the user registering method for user identity provided by the present invention when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random-access memory (random access memory, RAM), or the like.
It will be apparent to those skilled in the art that the techniques of embodiments of the present invention may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solutions in the embodiments of the present invention may be embodied in essence or what contributes to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the embodiments or some parts of the embodiments of the present invention.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (6)
1. A method for partitioning an oil field in a multispectral image, the method comprising:
separating a brightness map from the multispectral image, wherein the brightness map is a channel image corresponding to a Y component in RGB pixel values of the multispectral image;
enhancing the contrast of the brightness map to obtain a processed brightness map;
determining an initial area in the processed brightness map, wherein the initial area is a square area which is formed by taking a pixel point in a multispectral image as a center and adjacent 9 pixel points and is a pixel value and a maximum pixel area in the processed brightness map;
calculating pixel difference values of the initial region and each adjacent pixel point, wherein the adjacent pixel points are 16 pixel points which take the initial region as a center and are adjacent to the initial region;
determining pixel points to be combined, wherein the pixel points to be combined are adjacent pixel points of which the pixel difference value is smaller than a preset difference value threshold value; the determining the pixel points to be combined comprises: according to the following, a preset difference threshold is calculated,
merging the pixel points to be merged into the initial region to obtain a growth region;
and repeating the steps of calculating pixel difference values and merging the pixel points to be merged until the latest growing area does not have the pixel points to be merged, so as to obtain a target area, wherein the target area is the latest growing area.
2. The method of claim 1, wherein separating the luminance map from the multispectral image comprises:
according to a preset pixel component formula, Y, U, V components of all pixels in the multispectral image are calculated;
and extracting Y components corresponding to all the pixel points to obtain a brightness map.
3. The method of claim 1, wherein enhancing the contrast of the luminance map to obtain a processed luminance map comprises:
according to the following equation, the pixel values of the processed luminance map are calculated,
wherein V represents the pixel value of the luminance map, V ’ Representing the pixel value of the processed brightness image, b being the correlation coefficient;
and combining the pixel values of the processed brightness map to obtain the processed brightness map.
4. A multi-spectral image oil field divider, said apparatus comprising:
the separation unit is used for separating a brightness map from the multispectral image, wherein the brightness map is a channel image corresponding to a Y component in RGB pixel values of the multispectral image;
the contrast enhancement unit is used for enhancing the contrast of the brightness map to obtain a processed brightness map;
an initial region determining unit, configured to determine an initial region in the processed luminance map, where the initial region is a pixel value and a largest pixel region in the processed luminance map, and the pixel region is a square region formed by taking a pixel point in a multispectral image as a center and adjacent 9 pixel points;
a pixel difference calculating unit, configured to calculate a pixel difference between the initial area and each adjacent pixel point, where the adjacent pixel point is 16 pixel points that are centered on the initial area and adjacent to the initial area;
the pixel point to be combined determining unit is used for determining the pixel points to be combined, wherein the pixel points to be combined are adjacent pixel points with pixel difference values smaller than a preset difference value threshold value; the pixel point to be combined determining unit comprises: a preset difference threshold calculation unit for calculating a preset difference threshold according to the following equation,
the pixel point merging unit is used for merging the pixel points to be merged into the initial area to obtain a growth area;
and the target area determining unit is used for repeatedly calculating pixel difference values and merging pixel points to be merged until the latest growing area does not have the pixel points to be merged, so as to obtain a target area, wherein the target area is the latest growing area.
5. The apparatus of claim 4, wherein the separation unit comprises:
according to a preset pixel component formula, Y, U, V components of all pixels in the multispectral image are calculated;
and extracting Y components corresponding to all the pixel points to obtain a brightness map.
6. The apparatus of claim 4, wherein the contrast enhancement unit comprises:
a pixel value calculating unit for calculating a pixel value of the processed luminance map according to the following formula,
wherein V represents the pixel value of the luminance map, V ’ Representing the pixel value of the processed brightness image, b being the correlation coefficient;
and the processed brightness map generating unit is used for combining the pixel values of the processed brightness map to obtain the processed brightness map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910597026.1A CN110322452B (en) | 2019-07-03 | 2019-07-03 | Multispectral image oil material distinguishing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910597026.1A CN110322452B (en) | 2019-07-03 | 2019-07-03 | Multispectral image oil material distinguishing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110322452A CN110322452A (en) | 2019-10-11 |
CN110322452B true CN110322452B (en) | 2023-07-14 |
Family
ID=68122532
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910597026.1A Active CN110322452B (en) | 2019-07-03 | 2019-07-03 | Multispectral image oil material distinguishing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110322452B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101726693A (en) * | 2009-11-26 | 2010-06-09 | 绍兴电力局 | Method for seeking discharge regions of power devices on ultraviolet images |
CN103226832A (en) * | 2013-05-07 | 2013-07-31 | 西安电子科技大学 | Multispectral remote sensing image variation detection method based on spectral reflectivity variation analysis |
CN104616303A (en) * | 2015-02-11 | 2015-05-13 | 西安电子科技大学 | Ultraviolet image based water surface oil spill detection system and method |
CN104899853A (en) * | 2014-03-04 | 2015-09-09 | 腾讯科技(深圳)有限公司 | Image region dividing method and device |
CN105761286A (en) * | 2016-02-29 | 2016-07-13 | 环境保护部卫星环境应用中心 | Water color exception object extraction method and system based on multi-spectral remote sensing image |
CN106447688A (en) * | 2016-03-31 | 2017-02-22 | 大连海事大学 | Method for effectively segmenting hyperspectral oil-spill image |
CN107180421A (en) * | 2016-03-09 | 2017-09-19 | 中兴通讯股份有限公司 | A kind of eye fundus image lesion detection method and device |
CN107784661A (en) * | 2017-09-08 | 2018-03-09 | 上海电力学院 | Substation equipment infrared image classifying identification method based on region-growing method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8233712B2 (en) * | 2006-07-28 | 2012-07-31 | University Of New Brunswick | Methods of segmenting a digital image |
-
2019
- 2019-07-03 CN CN201910597026.1A patent/CN110322452B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101726693A (en) * | 2009-11-26 | 2010-06-09 | 绍兴电力局 | Method for seeking discharge regions of power devices on ultraviolet images |
CN103226832A (en) * | 2013-05-07 | 2013-07-31 | 西安电子科技大学 | Multispectral remote sensing image variation detection method based on spectral reflectivity variation analysis |
CN104899853A (en) * | 2014-03-04 | 2015-09-09 | 腾讯科技(深圳)有限公司 | Image region dividing method and device |
CN104616303A (en) * | 2015-02-11 | 2015-05-13 | 西安电子科技大学 | Ultraviolet image based water surface oil spill detection system and method |
CN105761286A (en) * | 2016-02-29 | 2016-07-13 | 环境保护部卫星环境应用中心 | Water color exception object extraction method and system based on multi-spectral remote sensing image |
CN107180421A (en) * | 2016-03-09 | 2017-09-19 | 中兴通讯股份有限公司 | A kind of eye fundus image lesion detection method and device |
CN106447688A (en) * | 2016-03-31 | 2017-02-22 | 大连海事大学 | Method for effectively segmenting hyperspectral oil-spill image |
CN107784661A (en) * | 2017-09-08 | 2018-03-09 | 上海电力学院 | Substation equipment infrared image classifying identification method based on region-growing method |
Non-Patent Citations (4)
Title |
---|
Performance comparison of image segmentation techniques for Infrared images;Irshad等;《2015 Annual IEEE India Conference (INDICON)》;20160331;1-5 * |
基于OTSU和区域生长的电气设备多点故障分割;余成波等;《红外技术》;20181018;正文3-4页"2 多种子点自动区域生长分割"部分 * |
彩色目标识别中的单通道目标分割方法;孙杰等;《南开大学学报(自然科学版)》;20020330(第01期);83-87 * |
航拍高光谱溢油图像中的连续油区划分方法研究;李若寒等;《中国水运(下半月)》;20160215(第02期);295-299+304 * |
Also Published As
Publication number | Publication date |
---|---|
CN110322452A (en) | 2019-10-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108549874B (en) | Target detection method, target detection equipment and computer-readable storage medium | |
US9530045B2 (en) | Method, system and non-transitory computer storage medium for face detection | |
CN106067177B (en) | HDR scene detection method and device | |
CN108682039B (en) | Binocular stereo vision measuring method | |
EP3142045B1 (en) | Predicting accuracy of object recognition in a stitched image | |
KR102567860B1 (en) | Improved inverse tone mapping method and corresponding device | |
CN109903294B (en) | Image processing method and device, electronic equipment and readable storage medium | |
CN107871319B (en) | Method and device for detecting beam limiter area, X-ray system and storage medium | |
CN113902641B (en) | Data center hot zone judging method and system based on infrared image | |
JP2010205067A (en) | Device, method and program for extracting area | |
US8908994B2 (en) | 2D to 3d image conversion | |
CN110188640B (en) | Face recognition method, face recognition device, server and computer readable medium | |
CN109816720B (en) | Road center detection method, airborne equipment and storage medium | |
US9135689B2 (en) | Apparatus and method for performing detail enhancement | |
CN111445487A (en) | Image segmentation method and device, computer equipment and storage medium | |
WO2018078806A1 (en) | Image processing device, image processing method, and image processing program | |
EP3143549B1 (en) | Segmentation based image transform | |
CN110322452B (en) | Multispectral image oil material distinguishing method and device | |
GB2522663A (en) | A method of selecting a region of interest | |
CN113569713A (en) | Stripe detection method and device for video image and computer readable storage medium | |
JP2013182330A (en) | Image processor and image processing method | |
CN110889817A (en) | Image fusion quality evaluation method and device | |
Turakhia et al. | Automatic crack detection in heritage site images for image inpainting | |
KR101554784B1 (en) | Method for estimating response of audience concerning content | |
KR100586227B1 (en) | Method for extraction region of face with learning colors distribution of a frame image |
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 |