CN111047575A - Unmanned aerial vehicle power line patrol image quality blind evaluation method - Google Patents
Unmanned aerial vehicle power line patrol image quality blind evaluation method Download PDFInfo
- Publication number
- CN111047575A CN111047575A CN201911271651.3A CN201911271651A CN111047575A CN 111047575 A CN111047575 A CN 111047575A CN 201911271651 A CN201911271651 A CN 201911271651A CN 111047575 A CN111047575 A CN 111047575A
- Authority
- CN
- China
- Prior art keywords
- image
- quality
- power line
- line patrol
- aerial vehicle
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 15
- 238000007689 inspection Methods 0.000 claims abstract description 9
- 238000013507 mapping Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000003708 edge detection Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000000034 method Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a blind evaluation method for the quality of power line inspection images of an unmanned aerial vehicle, which comprises the following steps: s1, acquiring an electric power line patrol image transmitted back to the ground workstation by the unmanned aerial vehicle system, and preprocessing the electric power line patrol image; s2, layering the power line patrol image into a brightness image and a reflection image; s3, respectively calculating the quality scores of the brightness image and the reflection image; s4, respectively giving corresponding weights to the quality scores of the brightness image and the reflection image, and summing to obtain the comprehensive quality score of the power line patrol image; and S5, presetting a mapping relation between the comprehensive quality fraction and the quality grade, and obtaining the quality grade of the power line patrol image. The method can evaluate the quality of the unmanned aerial vehicle power line patrol image, and estimate the quality of the image according to brightness detection and ambiguity detection without a reference image.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a blind evaluation method for the quality of power line inspection images of an unmanned aerial vehicle.
Background
At present, the application of a multi-rotor unmanned aerial vehicle in fine routing inspection of a power transmission line is more and more extensive, the machine inspection picture is influenced by the experience of personnel, the data quality is uneven, the collected image often has the problems of inaccurate focusing, insufficient exposure or overexposure, unreasonable shooting angle, fuzzy pictures and the like, and the data collection quality is poor.
The quality of the image directly affects the subjective feeling of people and the information quantity acquisition, so the evaluation of the image quality is an important component of an unmanned aerial vehicle image system. In the unmanned aerial vehicle inspection image system, because reference images cannot be obtained for comparison, blind evaluation is often adopted for image evaluation.
Disclosure of Invention
The invention aims to provide a blind evaluation method for the quality of an unmanned aerial vehicle power line patrol image, which can evaluate the quality of the unmanned aerial vehicle power line patrol image without a reference image.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a blind evaluation method for the quality of power line inspection images of an unmanned aerial vehicle is characterized by comprising the following steps:
s1, acquiring an electric power line patrol image transmitted back to the ground workstation by the unmanned aerial vehicle system, and preprocessing the electric power line patrol image;
s2, layering the power line patrol image into a brightness image and a reflection image;
s3, respectively calculating the quality scores of the brightness image and the reflection image;
s4, respectively giving corresponding weights to the quality scores of the brightness image and the reflection image, and summing to obtain the comprehensive quality score of the power line patrol image;
and S5, presetting a mapping relation between the comprehensive quality fraction and the quality grade, and obtaining the quality grade of the power line patrol image.
Further, the step S2: and layering the power line patrol image by adopting a Retinex algorithm to obtain a brightness image and a reflection image.
Further, the calculating of the quality score of the luminance image in the step S3 includes: and obtaining a quality score model through a brightness threshold effect, and then calculating the quality score of the brightness image.
Further, the calculating of the quality score of the reflection image in the step S3 includes: and obtaining the edge width through a Canny edge detection algorithm, calculating the average edge width, and performing exponential operation on the average edge width to obtain the quality score of the reflection image.
The invention has the beneficial effects that: the method can evaluate the quality of the unmanned aerial vehicle power line patrol image, and estimate the quality of the image according to brightness detection and ambiguity detection without a reference image.
Drawings
Fig. 1 is a flowchart of a blind evaluation method for the quality of power line inspection images of an unmanned aerial vehicle in the embodiment.
Detailed Description
In order to better understand the present invention, the following embodiments are further described.
As shown in fig. 1, a blind evaluation method for the quality of power line inspection images of an unmanned aerial vehicle comprises the following steps:
s1, unmanned aerial vehicle power line patrol shooting image
And acquiring the electric power line patrol image transmitted back to the ground workstation by the unmanned aerial vehicle system, and preprocessing the electric power line patrol image.
S2, layering images
And layering the power line patrol image by adopting a Retinex algorithm to obtain a brightness image (incident component) and a reflection image (reflection component). According to Retinex theory, an image can be decomposed into an incident component (luminance image) and a reflected component (reflection image), wherein the incident component mainly represents visual perception information such as luminance and color of the image, and the reflected component mainly represents essential information such as texture and edge of the image.
S3, calculating the quality scores of the brightness image and the reflection image
And (3) carrying out brightness detection on the brightness image: calculating the mean value and the variance of the image on the gray level image, wherein when the brightness is abnormal, the mean value deviates from a mean value point, and the variance is smaller; by calculating the mean and variance of the gray scale map, it is possible to evaluate whether the image is over-exposed or under-exposed. And obtaining a quality score model LTEQ through a brightness threshold effect, and then calculating the brightness quality score of the brightness image.
And (3) carrying out ambiguity detection on the reflected image: and searching the edge width according to the edge walking direction by a Canny edge detection algorithm, obtaining the Canny edge width along gradient search, calculating the average edge width, and performing exponential operation on the average edge width to obtain the quality score of the ambiguity.
And S4, giving different weights to the brightness quality fraction of the brightness image and the fuzziness quality fraction of the reflection image, and summing to obtain the comprehensive quality fraction of the power line patrol image. And judging whether the image quality is good or not according to the obtained comprehensive quality score, wherein the obtained comprehensive quality score shows that the quality of the image is worse when the value is larger.
And S5, presetting a mapping relation between the comprehensive quality fraction and the quality grade of the image, substituting the obtained comprehensive quality fraction into the mapping relation, and obtaining the quality grade of the power line patrol image. And finally outputting a power line patrol image quality evaluation report.
The above description is only an application example of the present invention, and certainly, the present invention should not be limited by this application, and therefore, the present invention is still within the protection scope of the present invention by equivalent changes made in the claims of the present invention.
Claims (4)
1. A blind evaluation method for the quality of power line inspection images of an unmanned aerial vehicle is characterized by comprising the following steps:
s1, acquiring an electric power line patrol image transmitted back to the ground workstation by the unmanned aerial vehicle system, and preprocessing the electric power line patrol image;
s2, layering the power line patrol image into a brightness image and a reflection image;
s3, respectively calculating the quality scores of the brightness image and the reflection image;
s4, respectively giving corresponding weights to the quality scores of the brightness image and the reflection image, and summing to obtain the comprehensive quality score of the power line patrol image;
and S5, presetting a mapping relation between the comprehensive quality fraction and the quality grade, and obtaining the quality grade of the power line patrol image.
2. The unmanned aerial vehicle power line patrol image quality blind evaluation method according to claim 1, wherein the step S2: and layering the power line patrol image by adopting a Retinex algorithm to obtain a brightness image and a reflection image.
3. The unmanned aerial vehicle power patrol image quality blind evaluation method according to claim 1, wherein the calculating of the quality score of the luminance image in step S3 includes: and obtaining a quality score model through a brightness threshold effect, and then calculating the quality score of the brightness image.
4. The unmanned aerial vehicle power patrol image quality blind evaluation method according to claim 1 or 3, wherein the calculating of the quality score of the reflection image in the step S3 includes: and obtaining the edge width through a Canny edge detection algorithm, calculating the average edge width, and performing exponential operation on the average edge width to obtain the quality score of the reflection image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911271651.3A CN111047575A (en) | 2019-12-12 | 2019-12-12 | Unmanned aerial vehicle power line patrol image quality blind evaluation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911271651.3A CN111047575A (en) | 2019-12-12 | 2019-12-12 | Unmanned aerial vehicle power line patrol image quality blind evaluation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111047575A true CN111047575A (en) | 2020-04-21 |
Family
ID=70235835
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911271651.3A Pending CN111047575A (en) | 2019-12-12 | 2019-12-12 | Unmanned aerial vehicle power line patrol image quality blind evaluation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111047575A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112093034A (en) * | 2020-09-22 | 2020-12-18 | 青海奥珞威信息科技有限公司 | Rotor magnetomotive unmanned aerial vehicle undercarriage retraction system |
CN112215833A (en) * | 2020-10-22 | 2021-01-12 | 江苏云从曦和人工智能有限公司 | Image quality evaluation method, device and computer readable storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101370154A (en) * | 2008-10-15 | 2009-02-18 | 北京中星微电子有限公司 | Image quality evaluating method and device |
CN104200475A (en) * | 2014-09-05 | 2014-12-10 | 中国传媒大学 | Novel no-reference image blur degree estimation method |
CN104867128A (en) * | 2015-04-10 | 2015-08-26 | 浙江宇视科技有限公司 | Image blurring detection method and device |
CN109559310A (en) * | 2018-11-30 | 2019-04-02 | 国网山东省电力公司电力科学研究院 | Power transmission and transformation inspection image quality evaluating method and system based on conspicuousness detection |
CN110148147A (en) * | 2018-11-07 | 2019-08-20 | 腾讯大地通途(北京)科技有限公司 | Image detecting method, device, storage medium and electronic device |
-
2019
- 2019-12-12 CN CN201911271651.3A patent/CN111047575A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101370154A (en) * | 2008-10-15 | 2009-02-18 | 北京中星微电子有限公司 | Image quality evaluating method and device |
CN104200475A (en) * | 2014-09-05 | 2014-12-10 | 中国传媒大学 | Novel no-reference image blur degree estimation method |
CN104867128A (en) * | 2015-04-10 | 2015-08-26 | 浙江宇视科技有限公司 | Image blurring detection method and device |
CN110148147A (en) * | 2018-11-07 | 2019-08-20 | 腾讯大地通途(北京)科技有限公司 | Image detecting method, device, storage medium and electronic device |
CN109559310A (en) * | 2018-11-30 | 2019-04-02 | 国网山东省电力公司电力科学研究院 | Power transmission and transformation inspection image quality evaluating method and system based on conspicuousness detection |
Non-Patent Citations (5)
Title |
---|
E. ONG等: "A no-reference quality metric for measuring image blur", 《PROCEEDINGS OF THE7TH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS.NEW YORK,USA:IEEE》 * |
刘伟等: "基于边缘显著区域和结构相似度的图像视觉效果评价", 《微型机与应用》 * |
崔启亮: "《本地化项目管理》", 31 October 2017, 对外经济贸易大学出版社 * |
左博新等: "基于图像结构的无参考模糊图像及其复原图像质量评价方法", 《地理信息世界》 * |
邵雪等: "基于亮度阈值效应的无参考图像质量评价方法", 《包装工程》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112093034A (en) * | 2020-09-22 | 2020-12-18 | 青海奥珞威信息科技有限公司 | Rotor magnetomotive unmanned aerial vehicle undercarriage retraction system |
CN112215833A (en) * | 2020-10-22 | 2021-01-12 | 江苏云从曦和人工智能有限公司 | Image quality evaluation method, device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9773302B2 (en) | Three-dimensional object model tagging | |
TWI524734B (en) | Method and device for generating a depth map | |
CN111308448B (en) | External parameter determining method and device for image acquisition equipment and radar | |
CN111583198A (en) | Insulator picture defect detection method combining FasterR-CNN + ResNet101+ FPN | |
CN111340749B (en) | Image quality detection method, device, equipment and storage medium | |
CN111047575A (en) | Unmanned aerial vehicle power line patrol image quality blind evaluation method | |
CN110866889A (en) | Multi-camera data fusion method in monitoring system | |
CN116228780A (en) | Silicon wafer defect detection method and system based on computer vision | |
CN110913210A (en) | Automatic main viewing image quality evaluation method based on standard data acquisition | |
Asmare et al. | Image Enhancement by Fusion in Contourlet Transform. | |
CN102724541B (en) | Intelligent diagnosis and recovery method for monitoring images | |
CN116524196A (en) | Intelligent power transmission line detection system based on image recognition technology | |
CN117456371B (en) | Group string hot spot detection method, device, equipment and medium | |
CN115083008A (en) | Moving object detection method, device, equipment and storage medium | |
WO2024016632A1 (en) | Bright spot location method, bright spot location apparatus, electronic device and storage medium | |
CN116758447A (en) | Digital twinning-based substation equipment fault analysis system | |
CN116645418A (en) | Screen button detection method and device based on 2D and 3D cameras and relevant medium thereof | |
CN116665077A (en) | Power transmission line detection shooting method and system based on AI (advanced identification) recognition technology | |
CN112364693B (en) | Binocular vision-based obstacle recognition method, device, equipment and storage medium | |
CN115035175A (en) | Three-dimensional model construction data processing method and system | |
Rovid et al. | Gradient based synthesized multiple exposure time HDR image | |
CN104809712B (en) | A kind of image fast repairing method based on rough set | |
CN113888420A (en) | Underwater image restoration method and device based on correction model and storage medium | |
Haouassi et al. | An efficient image haze removal algorithm based on new accurate depth and light estimation algorithm | |
CN115713501B (en) | Detection processing method and system suitable for blurred pictures of camera |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220113 Address after: 430000 No. 36, building g, No. 241-1 Jiefang Avenue, Qiaokou District, Wuhan City, Hubei Province Applicant after: Wuhan shangruizhi Technology Co.,Ltd. Address before: 810000 8503, 5th floor, Naduo Hotel, Jiahua international complex building, 232 Xiadu street, Chengzhong District, Xining City, Qinghai Province Applicant before: Qinghai aoluowei Information Technology Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200421 |
|
RJ01 | Rejection of invention patent application after publication |