CN105931198A - Icing insulator image enhancement method based on wavelet transformation - Google Patents
Icing insulator image enhancement method based on wavelet transformation Download PDFInfo
- Publication number
- CN105931198A CN105931198A CN201610230775.7A CN201610230775A CN105931198A CN 105931198 A CN105931198 A CN 105931198A CN 201610230775 A CN201610230775 A CN 201610230775A CN 105931198 A CN105931198 A CN 105931198A
- Authority
- CN
- China
- Prior art keywords
- image
- wavelet
- wavelet transformation
- icing insulator
- icing
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000009466 transformation Effects 0.000 title claims abstract description 38
- 239000012212 insulator Substances 0.000 title claims abstract description 36
- 230000005540 biological transmission Effects 0.000 claims abstract description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- 230000010339 dilation Effects 0.000 claims description 6
- 230000003628 erosive effect Effects 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 3
- 230000015572 biosynthetic process Effects 0.000 abstract 2
- 238000003786 synthesis reaction Methods 0.000 abstract 2
- 238000005516 engineering process Methods 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000002708 enhancing effect Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000009413 insulation Methods 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010297 mechanical methods and process Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Classifications
-
- G06T5/73—
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Abstract
The invention discloses an icing insulator enhancement method based on wavelet transformation. A digital image captured from a video stream in a power transmission line serves as a research object, early-stage processing is carried out on the image in image graying and mathematical morphology methods and the like, wavelet transformation and wavelet inverse transformation are carried out on the image after early-stage processing, the image after inverse transformation serves as a background image, the background image is divided by the grayed image to obtain a synthesis image, and whether the sharpness of the synthesis image satisfies the requirements is observed. The method of the invention can be used to realize enhanced detection for the insulator icing image rapidly and automatically needless of establishing an accurate mathematic model.
Description
Technical field
The invention belongs to transmission line of electricity on-line monitoring technique field, be specifically related to a kind of based on wavelet transformation
--icing insulator image enchancing method.
Background technology
Affected by Global climate change, mima type microrelief and microclimate condition,--icing insulator caused ice damage thing
Therefore frequently occur, cause the immediate cause of icing density be on a large scale, long low temperature, sleet and snow ice
Deng complicated weather environment, serious meeting is forgotten about it transmission pressure and is threatened electric power netting safe running, even causes huge
Economic loss and personnel casualty accidents.Therefore, in real time--icing insulator image is carried out enhancement process to enter
And recognition detection just seems necessary.Existing main covering ice for insulator identification technology has: pass through image
Treatment technology identifies powerline ice-covering automatically, uses Mechanical Method analysis identification icing, based on three-dimensional reconstruction
Powerline ice-covering on-line monitoring method etc. be both for single weather, the insulation of background condition lower wire
Sub-icing identification.In actual environment,--icing insulator ambient conditions is the most complicated.Same target,
The different time periods, environment may vary widely.Meanwhile, different time, the light of shooting image
According to the most also there being the biggest difference with contrast, therefore in--icing insulator identification is applied, residing for image
The change of environmental condition is inevitable.But, gatherer process can be by weather, season under real world conditions
The factor impacts such as joint, acquisition time, image background and contrast so that existing recognition detection technology is all
Have certain use limitation, the most simply, reliably, fast and automatically to covering under adverse circumstances
It is also a key technology difficult problem that ice insulator carry out enhancing to be just particularly important.
Summary of the invention
It is an object of the invention to provide a kind of--icing insulator image enchancing method based on wavelet transformation, solve
Icing insulation can not be processed under various environmental weather conditions the most in real time present in prior art of having determined
The problem of subimage.
The technical solution adopted in the present invention is, a kind of--icing insulator image enhaucament based on wavelet transformation
Method, specifically implements according to following steps:
Step 1: gather transmission line of electricity video image by the monopod video camera being arranged on electric power pylon and believe
Number, then in the way of video flowing, real-time online sends back Surveillance center；
Step 2: in Surveillance center, the numeral transmitted from video flowing in real-time intercepting step 1
Image, obtains target image to be identified；
Step 3: the target image to be identified obtained in step 2 is carried out gray processing process, obtains gray scale
Change image Y；
Step 4: the gray level image Y obtained in step 3 is used at mathematical morphology closed operation
Reason；
Step 5: the target image after processing the closed operation obtained in step 4 uses wavelet transformation, enters
Row two grades decomposition, obtains multi-level wavelet coefficient, and carries out wavelet inverse transformation；
Step 6: using the image that obtains after step 5 wavelet inverse transformation as the background image of original image, will
The gray level image Y that step 3 obtains, divided by background image, the composograph after being divided by, observes and closes
Become the definition of image, if the definition of composograph does not improves the m of original image definition, then turn
To step 4, if improve m, then--icing insulator image enhaucament terminates.
The feature of the present invention also resides in,
Step 3 particularly as follows:
In rgb space, the gray value of point corresponding to certain color is:
Wherein, (r, g, b) represent certain color coordinate vector in color space, and (255,255,255) represent face
Vector corresponding to diagonal in the colour space, | | represent vector field homoemorphism,
Through vector calculus, formula (1) abbreviation is:
Y is the gray level image after gray processing processes.
Step 4 particularly as follows:
Step 4.1: read in the pending image Y after step 3 gray processing processes；
Step 4.2: choice structure element S1And S2；
Step 4.3: use structural element S1Image Y is carried out dilation operation and obtains image
Step 4.4: use structural element S2To image Y1Carry out erosion operation and obtain image
For making target resolution improve, make the S used in twice gray scale computing1、S2For different structural elements
Element, and the S that dilation operation uses1The S used more than the erosion operation carried out subsequently2, i.e. S1＞ S2。
Wavelet transformation in step 5 particularly as follows:
Employing channel sub-band encodes, input picture Y2, export wavelet coefficient c, 2D wavelet transform
The single approximation coefficient of jth layer is decomposed into four components of jth+1 layer: approximation coefficient cAj+1With three
The detail coefficients in direction i.e. horizontal directionVertical directionWith diagonally opposed
In step 6
M=70% in step 6.
The invention has the beneficial effects as follows:
1. a kind of--icing insulator image enchancing method based on wavelet transformation of the present invention, it is not necessary to set up multiple
Miscellaneous mathematical model, only just can need to obtain severe nature by image procossing and simple calculating accurately
Enhancing image under environment, process is easy and result is accurate；
2. a kind of--icing insulator image enchancing method based on wavelet transformation of the present invention, used equipment
Less, simple in construction, with low cost, the existing video monitoring system of electrical network can be made full use of, by figure
As treatment technology and Radio Transmission Technology, it is achieved remote real-time data is processed and to electric power by Surveillance center
The complicated adverse circumstances of network carry out the monitoring of the overall situation；
3. a kind of--icing insulator image enchancing method based on wavelet transformation of the present invention, it is possible to achieve far
The Surveillance center of journey focuses on image by program and carries out the calculating realization enhancing being correlated with, to obtain
The global data of the image of--icing insulator in whole electrical network, be thus advantageous to realize real-time automatization
Security monitoring detects.
Accompanying drawing explanation
Fig. 1 is the flow chart of--icing insulator image enchancing method of the present invention；
Fig. 2 be in--icing insulator image enchancing method of the present invention gray processing process after gray-scale map；
Fig. 3 is two grades of decomposition charts of wavelet transformation in--icing insulator image enchancing method of the present invention；
Fig. 4 is that in--icing insulator image enchancing method of the present invention, wavelet transformation two grades decomposes scene photo；
Fig. 5 is two-dimensional wavelet transformation and the step of inverse transformation thereof in--icing insulator image enchancing method of the present invention
Rapid figure.
Detailed description of the invention
The present invention is described in detail with detailed description of the invention below in conjunction with the accompanying drawings.
A kind of--icing insulator image enchancing method based on wavelet transformation of the present invention, flow chart such as Fig. 1 institute
Show, specifically implement according to following steps:
Step 1: gather transmission line of electricity video image by the monopod video camera being arranged on electric power pylon and believe
Number, then by the way of 3G transmission channel is with video flowing, real-time online sends back Surveillance center；
Step 2: in Surveillance center, the numeral transmitted from video flowing in real-time intercepting step 1
Image, obtains target image to be identified；
Step 3: the target image to be identified obtained in step 2 is carried out gray processing process,
By image gray processing, color image color depth difference can be abandoned to wavelet field and inverse transformation image thereof
Impact, have simultaneously can improve image recognition rate reduce operand advantage.By finding certain color
Point corresponding in rgb space, datum point, to this some vector projection on the diagonal, obtains
The gray value of this color.R, g, b component all uses 8 to represent herein, and span is [0,255],
Gray value computing formula is as follows:
Wherein, (r, g, b) represent certain color coordinate vector in color space, and (255,255,255) represent face
Vector corresponding to diagonal in the colour space, | | it is to seek vector field homoemorphism.
Through vector calculus, formula (1) can abbreviation be:
By formula to shooting to vile weather under insulation subgraph carry out gray processing process, result as figure
Shown in 2 (a), Fig. 2 (b).
In insulator coloured image, the color of each pixel is determined by tri-components of r, g, b, each component
All having 256 values desirable, a pixel has 2553The excursion of individual color.Through gray proces
The pixel color variation range that can make image is reduced to 255 kinds.Insulator image after gray proces
Middle color intensity information is removed, and reduces original image data amount, makes subsequent treatment amount of calculation be substantially reduced.
Can be obtained by Fig. 2 (a), Fig. 2 (b) and original color image contrast image before and after i.e. contrast gray processing processes,
Gray level image, as coloured image, can reflect entirety and the colourity and bright of local of piece image accurately
The distribution of degree grade and feature.
Step 4: use mathematical morphology closed operation to process the gray level image obtained in step 3,
Carry out early stage for wavelet domain transform and composograph to process；
Step 4.1: read in pending image Y；
Step 4.2: choice structure element S1And S2；
Step 4.3: use structural element S1Image Y is carried out dilation operation and obtains image
Step 4.4: use structural element S2To image Y1Carry out erosion operation and obtain image
For making target resolution improve, make the S used in twice gray scale computing1、S2For different structural elements
Element, and the S that dilation operation uses1The S used more than the erosion operation carried out subsequently2, i.e. S1＞ S2。
Step 5: the target image after processing the closed operation obtained in step 4 uses wavelet transformation, by
Spatial domain, to frequency domain, carries out two grades of decomposition, obtains multi-level wavelet coefficient, and carry out small echo inversion
Change；
Wavelet transformation two grades decomposition: target image first carries out wavelet decomposition, and to obtain horizontal low frequencies vertical
Low-frequency information LL1, horizontal low frequencies vertical high-frequency information LH1, vertical low-frequency information HL of horizontal high-frequent1、
Horizontal high-frequent vertical high-frequency information HH1。LL1Low frequency component subgraph embodies the principal character of image, choosing
Determine threshold value, make to be set to zero less than the high-frequency sub-band coefficient of threshold value；Afterwards, to LL1Carry out the little wavelength-division of secondary
Solve after twice decomposition shown in the image such as Fig. 3 (a), Fig. 3 (b) corresponding to coefficient matrix, Fig. 3 (c),
After using wavelet transformation two grades to decompose shown in scene photo such as Fig. 4 (a), Fig. 4 (b), Fig. 4 (c).
Employing channel sub-band encodes, input picture Y2, export wavelet coefficient c, 2D wavelet transform
The single approximation coefficient of jth layer is decomposed into four components of jth+1 layer: approximation coefficient cAj+1With three
The detail coefficients in direction i.e. horizontal directionVertical directionWith diagonally opposed2D conversion and
Shown in its inverse transformation such as Fig. 5 (a) and Fig. 5 (b).In figure, symbol col ↓ 2 represent row down-sampling, i.e.
Only retain the row of even number sequence；Symbol row ↓ 2 represent row down-sampling, the most only retain the row of even number sequence；Symbol
Col ↑ 2 represent row up-sampling, insert 0 on odd numbered sequences；Symbol row ↑ 2 represent row up-sampling, very
0 is inserted on Number Sequence.
Step 6: using the image that obtains after step 5 wavelet inverse transformation as the background image of original image, will
The gray level image Y that step 3 obtains, divided by background image, the composograph after being divided by, observes and closes
Become the definition of image, if the definition of composograph does not improves the m of original image definition
(m=70%), then forwarding step 4 to, if improve m, then--icing insulator image enhaucament terminates,
Wherein,
A kind of--icing insulator image enchancing method based on wavelet transformation of the present invention, it is not necessary to set up complexity
Mathematical model, only just can need to obtain severe nature ring accurately by image procossing and simple calculating
Enhancing image under border, process is easy and result is accurate.
Claims (7)
1. a--icing insulator image enchancing method based on wavelet transformation, it is characterised in that specifically press
Implement according to following steps:
Step 1: gather transmission line of electricity video image by the monopod video camera being arranged on electric power pylon and believe
Number, then in the way of video flowing, real-time online sends back Surveillance center；
Step 2: in Surveillance center, the numeral transmitted from video flowing in real-time intercepting step 1
Image, obtains target image to be identified；
Step 3: the target image to be identified obtained in step 2 is carried out gray processing process, obtains gray scale
Change image Y；
Step 4: the gray level image Y obtained in step 3 is used at mathematical morphology closed operation
Reason；
Step 5: the target image after processing the closed operation obtained in step 4 uses wavelet transformation, enters
Row two grades decomposition, obtains multi-level wavelet coefficient, and carries out wavelet inverse transformation；
Step 6: using the image that obtains after step 5 wavelet inverse transformation as the background image of original image, will
The gray level image Y that step 3 obtains, divided by background image, the composograph after being divided by, observes and closes
Become the definition of image, if the definition of composograph does not improves the m of original image definition, then turn
To step 4, if improve m, then--icing insulator image enhaucament terminates.
A kind of--icing insulator image enhaucament side based on wavelet transformation the most according to claim 1
Method, it is characterised in that described step 3 particularly as follows:
In rgb space, the gray value of point corresponding to certain color is:
Wherein, (r, g, b) represent certain color coordinate vector in color space, and (255,255,255) represent face
Vector corresponding to diagonal in the colour space, | | represent vector field homoemorphism,
Through vector calculus, formula (1) abbreviation is:
Y is the gray level image after gray processing processes.
A kind of--icing insulator image enhaucament side based on wavelet transformation the most according to claim 2
Method, it is characterised in that described step 4 particularly as follows:
Step 4.1: read in the pending image Y after step 3 gray processing processes；
Step 4.2: choice structure element S1And S2；
Step 4.3: use structural element S1Image Y is carried out dilation operation and obtains image
Step 4.4: use structural element S2To image Y1Carry out erosion operation and obtain image
A kind of--icing insulator image enhaucament side based on wavelet transformation the most according to claim 3
Method, it is characterised in that for making target resolution improve, makes the S used in twice gray scale computing1、S2For
Different structural elements, and the S that dilation operation uses1The S used more than the erosion operation carried out subsequently2,
I.e. S1＞ S2。
A kind of--icing insulator image enhaucament side based on wavelet transformation the most according to claim 3
Method, it is characterised in that wavelet transformation in described step 5 particularly as follows:
Employing channel sub-band encodes, input picture Y2, export wavelet coefficient c, 2D wavelet transform
The single approximation coefficient of jth layer is decomposed into four components of jth+1 layer: approximation coefficient cAj+1With three
The detail coefficients in direction i.e. horizontal directionVertical directionWith diagonally opposed
A kind of--icing insulator image enhaucament side based on wavelet transformation the most according to claim 1
Method, it is characterised in that in described step 6
A kind of--icing insulator image enhaucament side based on wavelet transformation the most according to claim 1
Method, it is characterised in that m=70% in described step 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610230775.7A CN105931198A (en) | 2016-04-14 | 2016-04-14 | Icing insulator image enhancement method based on wavelet transformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610230775.7A CN105931198A (en) | 2016-04-14 | 2016-04-14 | Icing insulator image enhancement method based on wavelet transformation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105931198A true CN105931198A (en) | 2016-09-07 |
Family
ID=56838093
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610230775.7A Pending CN105931198A (en) | 2016-04-14 | 2016-04-14 | Icing insulator image enhancement method based on wavelet transformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105931198A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709892A (en) * | 2016-11-15 | 2017-05-24 | 昂纳自动化技术（深圳）有限公司 | Rapid region expansion algorithm and device of any structure element based on stroke coding |
| CN106780438A (en) * | 2016-11-11 | 2017-05-31 | 广东电网有限责任公司清远供电局 | Defects of insulator detection method and system based on image procossing |
| CN109359593A (en) * | 2018-10-17 | 2019-02-19 | 安徽超远信息技术有限公司 | A kind of sleet environment fuzzy pictures monitoring and pre-alarming method based on image local grid |
| CN112270327A (en) * | 2020-10-19 | 2021-01-26 | 西安工程大学 | Power transmission conductor icing classification method based on local fusion frequency domain characteristics |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101882304A (en) * | 2010-06-24 | 2010-11-10 | 西北工业大学 | Self-adaptive de-noising and characteristic enhancing method of SAR (Synthetic Aperture Radar) image |
| CN103020915A (en) * | 2012-12-21 | 2013-04-03 | 清华大学 | Video data based objective image enhancement method |
| CN103514580A (en) * | 2013-09-26 | 2014-01-15 | 香港应用科技研究院有限公司 | Method and system used for obtaining super-resolution images with optimized visual experience |
| CN105426837A (en) * | 2015-11-17 | 2016-03-23 | 南京大学 | Haze detection system based on mobile network vision |
-
2016
- 2016-04-14 CN CN201610230775.7A patent/CN105931198A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101882304A (en) * | 2010-06-24 | 2010-11-10 | 西北工业大学 | Self-adaptive de-noising and characteristic enhancing method of SAR (Synthetic Aperture Radar) image |
| CN103020915A (en) * | 2012-12-21 | 2013-04-03 | 清华大学 | Video data based objective image enhancement method |
| CN103514580A (en) * | 2013-09-26 | 2014-01-15 | 香港应用科技研究院有限公司 | Method and system used for obtaining super-resolution images with optimized visual experience |
| CN105426837A (en) * | 2015-11-17 | 2016-03-23 | 南京大学 | Haze detection system based on mobile network vision |
Non-Patent Citations (10)
| Title |
|---|
| 周金和 等: "一种有选择的图像灰度化方法", 《计算机工程》 * |
| 孙嫣 等: "基于数学形态学的练级手写字符识别去噪方法", 《计算机科学》 * |
| 张惊雷 等: "基于大气散射模型和曲波变换的交通图像增强研究", 《河北工业大学学报》 * |
| 王小明: "可变光照下人脸检测与识别研究", 《中国博士学位论文全文数据库信息科技辑》 * |
| 王明吉 等: "基于边缘算子和数学形态学的光纤面板暗影检测", 《光学仪器》 * |
| 赵侠: "一种基于非线性扩散方程的SAR图像相干斑抑制方法", 《激光杂志》 * |
| 赵春晖: "数字形态滤波器理论及其算法研究", 《数字形态滤波器理论及其算法研究》 * |
| 郑雪莲: "基于CB形态学的输电线路覆冰厚度检测", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 陈丽安 等: "基于形态小波的低压系统短路故障早期检测", 《中国电机工程学报》 * |
| 顾桂梅 等: "基于自适应多尺度积阈值的钢轨裂纹红外图像增强", 《铁道学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780438A (en) * | 2016-11-11 | 2017-05-31 | 广东电网有限责任公司清远供电局 | Defects of insulator detection method and system based on image procossing |
| CN106780438B (en) * | 2016-11-11 | 2020-09-25 | 广东电网有限责任公司清远供电局 | Insulator defect detection method and system based on image processing |
| CN106709892A (en) * | 2016-11-15 | 2017-05-24 | 昂纳自动化技术（深圳）有限公司 | Rapid region expansion algorithm and device of any structure element based on stroke coding |
| CN109359593A (en) * | 2018-10-17 | 2019-02-19 | 安徽超远信息技术有限公司 | A kind of sleet environment fuzzy pictures monitoring and pre-alarming method based on image local grid |
| CN109359593B (en) * | 2018-10-17 | 2020-07-31 | 安徽超远信息技术有限公司 | Rain and snow environment picture fuzzy monitoring and early warning method based on image local grid |
| CN112270327A (en) * | 2020-10-19 | 2021-01-26 | 西安工程大学 | Power transmission conductor icing classification method based on local fusion frequency domain characteristics |
| CN112270327B (en) * | 2020-10-19 | 2023-03-14 | 西安工程大学 | Power transmission conductor icing classification method based on local fusion frequency domain characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10269138B2 (en) | UAV inspection method for power line based on human visual system | |
| CN101303764B (en) | Method for self-adaption amalgamation of multi-sensor image based on non-lower sampling profile wave | |
| JP2020527785A (en) | Ship detection methods and systems based on multidimensional features of the scene | |
| CN109685716B (en) | Image super-resolution reconstruction method for generating countermeasure network based on Gaussian coding feedback | |
| CN105931198A (en) | Icing insulator image enhancement method based on wavelet transformation | |
| CN105023013B (en) | The object detection method converted based on Local standard deviation and Radon | |
| CN104268847A (en) | Infrared light image and visible light image fusion method based on interactive non-local average filtering | |
| CN107330871A (en) | The image enchancing method of insulator automatic identification is run under bad weather condition | |
| CN107563397A (en) | Cloud cluster method for calculation motion vector in a kind of satellite cloud picture | |
| CN103617630A (en) | Infrared image dividing method and system for power system equipment based on wavelet analysis | |
| CN110288623B (en) | Data compression method for unmanned aerial vehicle maritime net cage culture inspection image | |
| CN104933403A (en) | Method for monitoring conductor galloping based on spacer recognition | |
| CN113947555A (en) | Infrared and visible light fused visual system and method based on deep neural network | |
| CN103544488A (en) | Face recognition method and device | |
| CN104574301A (en) | Terahertz image reconstruction method and system | |
| CN102496144A (en) | NSCT (nonsubsampled contourlet transform) sonar image enhancement method based on HSV (hue, saturation and value) color space | |
| Zhao et al. | An adaptation of CNN for small target detection in the infrared | |
| CN102722879A (en) | SAR (synthetic aperture radar) image despeckle method based on target extraction and three-dimensional block matching denoising | |
| CN104463822A (en) | Multi-focus image fusing method and device based on multi-scale overall filtering | |
| CN104299197A (en) | Single image defogging method by means of 2D CCA | |
| CN102298768B (en) | High-resolution image reconstruction method based on sparse samples | |
| Jia et al. | A wavelet-based approach to improve foggy image clarity | |
| CN105118025A (en) | Fast image super resolution method based on soft threshold coding | |
| Jiang et al. | Haze relevant feature attention network for single image dehazing | |
| CN116485885A (en) | Method for removing dynamic feature points at front end of visual SLAM based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160907 |
|
| RJ01 | Rejection of invention patent application after publication |