CN116758081A - Unmanned aerial vehicle road and bridge inspection image processing method - Google Patents
Unmanned aerial vehicle road and bridge inspection image processing method Download PDFInfo
- Publication number
- CN116758081A CN116758081A CN202311044142.3A CN202311044142A CN116758081A CN 116758081 A CN116758081 A CN 116758081A CN 202311044142 A CN202311044142 A CN 202311044142A CN 116758081 A CN116758081 A CN 116758081A
- Authority
- CN
- China
- Prior art keywords
- image
- target area
- area
- channel
- bridge
- 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.)
- Granted
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 72
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 238000011835 investigation Methods 0.000 claims abstract description 3
- 238000000034 method Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 4
- 230000000873 masking effect Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
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
- G06T7/11—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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
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)
Abstract
The invention relates to the technical field of image processing, in particular to an unmanned aerial vehicle road and bridge inspection image processing method, which comprises the following steps: obtaining an image set according to the inspection image; obtaining a target area, a background area and a plurality of connected areas in the target area of each image, and calculating the weight of each pixel point in the target area; calculating the difference degree between the background area and the target area of the image; and obtaining an optimal segmentation template according to the difference degree, obtaining a target area in the inspection image according to the optimal segmentation template, and performing quality detection and safety problem investigation on the road and bridge according to the target area in the inspection image. The invention ensures the accuracy of the inspection result of the road and bridge, finds the problems of the bridge in time, and eliminates the potential safety hazard.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an unmanned aerial vehicle road and bridge inspection image processing method.
Background
Because mountain area environment is complicated, patrol and examine road and bridge in the mountain area through the maintenance personnel on the spot extravagant manpower and materials, and can't guarantee ageing, can not in time discover the problem of road and bridge, get rid of the potential safety hazard. Therefore, images of roads and bridges in mountain areas are shot through the unmanned aerial vehicle and transmitted in real time, the roads and bridges are overhauled based on the real-time images, and time efficiency is guaranteed while manpower and material resources are saved.
In order to obtain the actual conditions of roads and bridges more accurately, the target areas belonging to the roads and bridges in the acquired images are required to be separated from the backgrounds belonging to forests, grasslands, hills, rivers and the like, the technology of extracting the roads and bridges in the gray level images is mature, but for mountain areas with complex environments, areas with relatively similar colors exist between the background areas and the target areas, so that the target areas belonging to the roads and bridges cannot be completely and accurately separated, the accuracy of the inspection results of the roads and bridges is further affected, the problems of the bridges cannot be found in time, and potential safety hazards are eliminated.
Disclosure of Invention
The invention provides an unmanned aerial vehicle road and bridge inspection image processing method, which aims to solve the existing problems.
The invention discloses an unmanned aerial vehicle road and bridge inspection image processing method which adopts the following technical scheme.
The invention provides a processing method of an unmanned aerial vehicle road and bridge inspection image, which comprises the following steps:
and collecting inspection images of roads and bridges, and obtaining an image set according to the inspection images.
And obtaining a target area, a background area and a plurality of connected areas in the target area of each image in the image set.
And calculating the weight of each pixel point in the target area according to the area ratio of the connected domain where the pixel point is located and the difference between the gray value of the pixel point and the whole gray value level of the target area.
And obtaining the weighted integral gray value level of the target area according to the weight and gray value of the pixel points in the target area, and calculating the difference degree between the background area and the target area of the image according to the weighted integral gray value level of the target area and the integral gray value level of the background area.
And obtaining an optimal segmentation template according to the difference degree, obtaining a target area in the inspection image according to the optimal segmentation template, and performing quality detection and safety problem investigation on the road and bridge according to the target area in the inspection image.
Further, the obtaining the connected areas of the target area and the background area of each image in the image set and the plurality of connected areas in the target area includes the following specific steps:
for any image in the image set, carrying out threshold segmentation on the image through an Ojin algorithm to obtain a binary image of the image, wherein white pixel points are pixel points with gray values larger than or equal to a threshold value, and black pixel points are pixel points with gray values smaller than the threshold value; the region composed of white pixels is referred to as a target region, and the region composed of black pixels is referred to as a background region.
And carrying out mask operation on the image according to the binary image of the image to obtain a target area and a background area of the image, and carrying out connected domain analysis on the target area to obtain a plurality of connected domains in the target area.
Further, the step of obtaining the weight of each pixel point in the target area of each image in the image set includes the following specific steps:
in the method, in the process of the invention,weights representing i pixels in the target area, +.>And->Respectively representing the ith image in the target areaPixel values of the pixel point and the jth pixel point, n representing the number of all pixel points in the target area,/->And->Respectively representing the areas of the connected areas where the ith pixel point and the jth pixel point in the target area are located.
For the target area, i.e. the whole gray value level of the road bridge,/->The area ratio of the connected domain where the pixel point is located.
Further, the calculating the difference degree between the background area and the target area of the image comprises the following specific steps:
where D represents the degree of difference in the images,weights representing i pixels in the target area, n represents the number of all pixels in the target area, +.>A pixel value representing the j-th pixel in the target area, m representing the number of all pixels in the background area,/for the j-th pixel>Representing the pixel value of the kth pixel point in the background region.
The weighted overall gray value level for the target region. />Is the overall gray value level of the background area.
Further, the obtaining the optimal segmentation template according to the difference degree, and obtaining the target area in the inspection image according to the optimal segmentation template comprises the following specific steps:
and (5) recording the binary image of the image with the largest difference degree in the image set as an optimal segmentation template.
And carrying out mask operation on the inspection image according to the optimal segmentation template to obtain a target area in the inspection image, and carrying out quality detection and safety problem inspection on the road and bridge according to the target area in the inspection image.
Further, the method for obtaining the image set according to the inspection image comprises the following specific steps:
the inspection image is an RGB image, gray scale processing is carried out on the inspection image, and the obtained gray scale image is respectively converted into a Lab image, an HSV image and a YCbCr image; taking an R channel, a G channel and a B channel of a patrol image, an L channel, an a channel and a B channel of a Lab image, an H channel, an S channel and a V channel of an HSV image and a Y channel, a Cb channel and a Cr channel of a YCbCr image as a channel image respectively, wherein the total number of the channel images is 12; the set of 12 channel images and gray scale images is denoted as an image set.
The technical scheme of the invention has the beneficial effects that: aiming at the problems that the complex environment of mountain areas cannot accurately separate the target areas belonging to roads and bridges from the background belonging to forests, grasslands, hills, rivers and the like, the accuracy of the inspection results of the roads and bridges is affected, and the problems of potential safety hazards cannot be found in time, the method comprises the steps of calculating the weight of each pixel point in the target area according to the area occupation ratio of the connected area where the pixel point is located and the difference between the gray value of the pixel point and the integral gray value level of the target area, obtaining the weighted integral gray value level of the target area according to the weight and the gray value of the pixel point in the target area, obtaining the difference degree between the background area and the target area of the image according to the weighted integral gray value level of the target area and the integral gray value level of the background area, masking the inspection image according to the binary image of the image with the largest difference degree between the target area and the background area, obtaining the target area in the inspection image, and the bridge quality inspection and safety problems are guaranteed according to the target area in the inspection image, and the accuracy of the road and the potential safety hazards of the bridges is found in time.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for processing an inspection image of a road and bridge of an unmanned aerial vehicle.
Fig. 2 is a gray scale image of the inspection image of the present invention.
Fig. 3 is a b-channel image of a patrol image of the present invention.
Fig. 4 is an H-channel image of a patrol image of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a method for processing an unmanned aerial vehicle road and bridge inspection image according to the invention, which is specific to the implementation, structure, characteristics and effects thereof, with reference to the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of an unmanned aerial vehicle road and bridge inspection image processing method, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a method flowchart of a data transmission module of an unmanned aerial vehicle road and bridge inspection image processing method according to an embodiment of the invention is shown, and the method includes:
s001, collecting inspection images of roads and bridges, and obtaining an image set according to the inspection images.
In order to detect the road and bridge to be inspected, it is necessary to accurately divide the background area belonging to forests, grasslands, hills, rivers and the like and the target area belonging to the road and bridge in the inspection image, and the accurate division of the background area and the target area is based on the color difference between the target area and the background area in the acquired inspection image, so that the more obvious the difference is, the better the division effect is.
It should be further noted that, in different channel images, the difference degree between the target area and the background area is different, for example, in a G channel image, the difference between the target area and the background area may be more obvious; in the B channel image, the difference exists between the yellow elements in the target area and the background area, and the difference also exists between the target area and the background; therefore, the background area and the target area are segmented according to the channel image with the most obvious difference between the target area and the background area, so that the bridge and the road in the inspection image can be accurately segmented, the most accurate inspection result of the road and the bridge is obtained, the problems of the bridge are found in time, and the potential safety hazard is eliminated.
Specifically, an unmanned aerial vehicle shoots a patrol image above a road and bridge to be patrol, the obtained patrol image is an RGB image, and gray scale processing is carried out on the patrol image to obtain a gray scale image.
Further, the inspection image is an RGB image, and the inspection image is converted into a Lab image, an HSV image and a YCbCr image respectively; taking an R channel, a G channel and a B channel of a patrol image, an L channel, an a channel and a B channel of a Lab image, an H channel, an S channel and a V channel of an HSV image and a Y channel, a Cb channel and a Cr channel of a YCbCr image as a channel image respectively, wherein the total number of the channel images is 12; the set of 12 channel images and gray scale images is denoted as an image set.
S002, obtaining a target area and a background area of each image in the image set and a plurality of connected areas in the target area, obtaining the weight of each pixel point in the target area of each image in the image set, and calculating the difference degree of the background area and the target area of each image in the image set.
1. And obtaining a target area and a background area of each image in the image set and a plurality of connected areas in the target area.
It should be noted that, for any one image in the image set, although the pixel values of most of the pixels belonging to the background areas such as forests, grasslands, hills, and rivers are large, and the pixel values of most of the pixels belonging to the target areas of roads and bridges are relatively small, the difference between the pixel values of some of the pixels belonging to the background areas such as forests, grasslands, hills, and the like and the pixel values of the pixels belonging to the target areas of roads and bridges is not obvious, so that the effect of dividing the image into the background areas and the target areas by threshold segmentation is not good, and the segmented target areas include not only the pixels of the roads and bridges themselves, but also a lot of pixels belonging to noise, rivers, and developed mountains; therefore, it is necessary to find an image in which the difference between the pixel values of the pixels in the background region and the target region is more significant, so as to extract the target region.
Specifically, for any image in the image set, performing threshold segmentation on the image through an Ojin algorithm to obtain a binary image of the image, wherein white pixels are pixels with gray values larger than or equal to a threshold value, and black pixels are pixels with gray values smaller than the threshold value; the region composed of white pixels is referred to as a target region, and the region composed of black pixels is referred to as a background region.
Further, masking operation is carried out on the image according to the binary image of the image, a target area and a background area of the image are obtained, connected domain analysis is carried out on the target area, and a plurality of connected domains in the target area are obtained.
2. A weight is obtained for each pixel point in the target area of each image in the set of images.
It should be noted that, the difference and the degree of difference between the target area and the background area in the different channel images are different, please refer to fig. 2, which shows a gray image, please refer to fig. 3, which shows a b-channel image, which shows that there is a more obvious difference between the road in the target area and the river in the background area in the b-channel image compared to the gray image, please refer to fig. 4, which shows an H-channel image, which shows that the difference between the whole of the target area and the background area in the H-channel is more obvious compared to the gray image, but the difference between the road in the target area and the river in the background area is not obvious, so that it is necessary to find an image with more obvious difference between the pixel values of the pixels of the background area and the target area to extract the target area.
It should be further noted that the degree of difference in the image is calculated from the difference in pixel values between the background region and the target region, and thus the image with the most obvious degree of difference is obtained. However, in the target region, the probability that some pixels belong to the road is large, and the probability that some pixels belong to the road is small, so when the degree of difference between the background region and the target region in the image is calculated, it is necessary to combine the weights of the respective pixels.
It should be further noted that, in practice, the target area belonging to the road and bridge should be a connected area, and has a certain area, but due to the wrong segmentation of a part of the pixel points, the target area belonging to the road and bridge is segmented into a plurality of connected areas, where the smaller the area, the smaller the probability that the connected area belongs to the road and bridge, and the larger the area, the larger the probability that the connected area belongs to the road and bridge, so the weight of the pixel point can be calculated by combining the areas of the connected areas where the pixel point is located. In addition, in the image, the gray values of the pixel points belonging to the road and bridge are mostly gray, and the average gray value of all the pixel points of the target area represents the whole gray value level of the road and bridge, so that the closer the gray value of the pixel point is to the gray value of the target area, the larger the probability that the pixel point belongs to the road and bridge is, and the weight of the pixel point can be calculated by combining the difference of the average gray values of the pixel point and the target area.
Specifically, according to the area occupation ratio of the connected domain where the pixel points are located and the difference between the gray value of the pixel points and the overall gray value level of the target area, the weight of each pixel point in the target area is calculated, and a specific calculation formula is as follows:
in the method, in the process of the invention,weights representing i pixels in the target area, +.>And->Respectively representing pixel values of an ith pixel point and a jth pixel point in the target area, and n represents the number of all pixel points in the target area, < +.>And->Respectively representing the areas of the connected areas where the ith pixel point and the jth pixel point in the target area are located.
For the average gray value of all pixel points of the target area, the whole gray value level of the target area, namely the road and bridge is represented, and the gray value is +.>Representing the difference between the gray value of the pixel point and the overall gray value level of the target area, the smaller the differenceThe closer the gray value of the pixel point is to the gray value of the target area, the larger the probability that the pixel point belongs to a road bridge, the larger the weight of the pixel point; />Representing the area occupation ratio of the connected domain where the pixel points are located, wherein the larger the area is, the larger the probability that the connected domain belongs to a road bridge is, and the larger the weight of the pixel points is; />And->For normalization.
3. The degree of difference between the background area and the target area of each image in the image set is calculated.
It should be noted that, the target area in the image is the area corresponding to the road and bridge, and the road and bridge are all made of cement materials, so the pixel values of the target area in each channel image are relatively close, and therefore, the weighted average value of the pixel values of all the pixel points in the target area in the image can be used for representing the whole gray value level of the target area. The background area in the image is the area corresponding to forests, grasslands, hills and rivers, and the pixel values of the local areas are relatively close, so that the average degree of the pixel values of the background area can be used for representing the approximate pixel values of the background area. Therefore, the average value of the pixel values of the target area and the average value of the pixel values of all the pixel points in the background area are used for representing the whole gray value level of the background area; the degree of difference between the background region and the target region is represented by the difference between the overall gray value levels of the background region and the target region.
Specifically, the weighted whole gray value level of the target area is obtained according to the weight and gray value of the pixel point in the target area, and the difference degree between the background area and the target area of the image is calculated according to the weighted whole gray value level of the target area and the whole gray value level of the background area, wherein the specific calculation formula is as follows:
where D represents the degree of difference in the images,weights representing i pixels in the target area, n represents the number of all pixels in the target area, +.>A pixel value representing the j-th pixel in the target area, m representing the number of all pixels in the background area,/for the j-th pixel>Representing the pixel value of the kth pixel point in the background region.
For the average weighted gray value of all pixel points of the target area, the weighted whole gray value level of the target area, namely the road and bridge, is represented by +.>The average gray value of all pixel points of the background area represents the overall gray value level of the background area; />The greater the value is for the difference in weighted overall gray value level of the target region and overall gray value level of the background region, the greater the degree of difference between the target region and the background region.
S003, obtaining an optimal segmentation template according to the difference degree, obtaining a target area in the inspection image according to the optimal segmentation template, and further performing inspection.
By the above process, the difference degree between the pixel values of the target area and the background area is obtained, the target area in the inspection image is extracted according to the binary image of the image with more obvious difference between the pixel values of the pixel points of the background area and the target area, and the bridge and the road in the inspection image can be accurately segmented, so that the most accurate inspection result of the road and the bridge is obtained, the problems of the bridge are found in time, and the potential safety hazard is eliminated.
Specifically, the binary image of the image with the largest difference degree in the image set is recorded as an optimal segmentation template, masking operation is carried out on the inspection image according to the optimal segmentation template, a target area in the inspection image, namely an area corresponding to the road and the bridge, is obtained, and quality detection and safety problem inspection are carried out on the road and the bridge according to the target area in the inspection image.
Aiming at the problems that the complex environment of mountain areas cannot accurately separate the target areas belonging to roads and bridges from the background belonging to forests, grasslands, hills, rivers and the like, the accuracy of the inspection results of the roads and bridges is affected, and the problems of potential safety hazards cannot be found in time, the method comprises the steps of calculating the weight of each pixel point in the target area according to the area occupation ratio of the connected area where the pixel point is located and the difference between the gray value of the pixel point and the integral gray value level of the target area, obtaining the weighted integral gray value level of the target area according to the weight and the gray value of the pixel point in the target area, obtaining the difference degree between the background area and the target area of the image according to the weighted integral gray value level of the target area and the integral gray value level of the background area, masking the inspection image according to the binary image of the image with the largest difference degree between the target area and the background area, obtaining the target area in the inspection image, and the bridge quality inspection and safety problems are guaranteed according to the target area in the inspection image, and the accuracy of the road and the potential safety hazards of the bridges is found in time.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. The unmanned aerial vehicle road and bridge inspection image processing method is characterized by comprising the following steps of:
collecting a patrol image of a road and bridge, and obtaining an image set according to the patrol image;
obtaining a target area, a background area and a plurality of connected areas in the target area of each image in the image set;
calculating the weight of each pixel point in the target area according to the area occupation ratio of the connected domain where the pixel point is located and the difference between the gray value of the pixel point and the whole gray value level of the target area;
obtaining a weighted integral gray value level of the target area according to the weight and the gray value of the pixel point in the target area, and calculating the difference degree between the background area and the target area of the image according to the weighted integral gray value level of the target area and the integral gray value level of the background area;
and obtaining an optimal segmentation template according to the difference degree, obtaining a target area in the inspection image according to the optimal segmentation template, and performing quality detection and safety problem investigation on the road and bridge according to the target area in the inspection image.
2. The method for processing the unmanned aerial vehicle road and bridge inspection image according to claim 1, wherein the steps of obtaining the target area and the background area of each image in the image set and a plurality of connected areas in the target area comprise the following specific steps:
for any image in the image set, carrying out threshold segmentation on the image through an Ojin algorithm to obtain a binary image of the image, wherein white pixel points are pixel points with gray values larger than or equal to a threshold value, and black pixel points are pixel points with gray values smaller than the threshold value; the region formed by the white pixel points is marked as a target region, and the region formed by the black pixel points is marked as a background region;
and carrying out mask operation on the image according to the binary image of the image to obtain a target area and a background area of the image, and carrying out connected domain analysis on the target area to obtain a plurality of connected domains in the target area.
3. The unmanned aerial vehicle road and bridge inspection image processing method according to claim 1, wherein the obtaining the weight of each pixel point in the target area of each image in the image set comprises the following specific steps:
in the method, in the process of the invention,weights representing i pixels in the target area, +.>And->Respectively representing pixel values of an ith pixel point and a jth pixel point in the target area, and n represents the number of all pixel points in the target area, < +.>And->Respectively representing the areas of the connected domains where the ith pixel point and the jth pixel point in the target area are located;
for the target area, i.e. the whole gray value level of the road bridge,/->The area ratio of the connected domain where the pixel point is located.
4. The unmanned aerial vehicle road and bridge inspection image processing method according to claim 1, wherein the calculating the difference degree between the background area and the target area of the image comprises the following specific steps:
where D represents the degree of difference in the images,weights representing i pixels in the target area, n represents the number of all pixels in the target area, +.>A pixel value representing the j-th pixel in the target area, m representing the number of all pixels in the background area,/for the j-th pixel>A pixel value representing a kth pixel point in the background region;
for the weighted overall gray value level of the target area, is>Is the overall gray value level of the background area.
5. The method for processing the inspection image of the unmanned aerial vehicle road and bridge according to claim 1, wherein the steps of obtaining the optimal segmentation template according to the difference degree and obtaining the target area in the inspection image according to the optimal segmentation template comprise the following specific steps:
the binary image of the image with the largest difference degree in the image set is recorded as an optimal segmentation template;
and carrying out mask operation on the inspection image according to the optimal segmentation template to obtain a target area in the inspection image, and carrying out quality detection and safety problem inspection on the road and bridge according to the target area in the inspection image.
6. The method for processing the inspection image of the road and bridge of the unmanned aerial vehicle according to claim 1, wherein the step of obtaining the image set according to the inspection image comprises the following specific steps:
the inspection image is an RGB image, gray scale processing is carried out on the inspection image, and the obtained gray scale image is respectively converted into a Lab image, an HSV image and a YCbCr image; taking an R channel, a G channel and a B channel of a patrol image, an L channel, an a channel and a B channel of a Lab image, an H channel, an S channel and a V channel of an HSV image and a Y channel, a Cb channel and a Cr channel of a YCbCr image as a channel image respectively, wherein the total number of the channel images is 12; the set of 12 channel images and gray scale images is denoted as an image set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311044142.3A CN116758081B (en) | 2023-08-18 | 2023-08-18 | Unmanned aerial vehicle road and bridge inspection image processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311044142.3A CN116758081B (en) | 2023-08-18 | 2023-08-18 | Unmanned aerial vehicle road and bridge inspection image processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116758081A true CN116758081A (en) | 2023-09-15 |
| CN116758081B CN116758081B (en) | 2023-11-17 |
Family
ID=87953700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311044142.3A Active CN116758081B (en) | 2023-08-18 | 2023-08-18 | Unmanned aerial vehicle road and bridge inspection image processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116758081B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152163A (en) * | 2023-11-01 | 2023-12-01 | 安徽乾劲企业管理有限公司 | Bridge construction quality visual detection method |
| CN117557784A (en) * | 2024-01-09 | 2024-02-13 | 腾讯科技（深圳）有限公司 | Target detection method, target detection device, electronic equipment and storage medium |
Citations (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040239762A1 (en) * | 2003-05-21 | 2004-12-02 | Porikli Fatih M. | Adaptive background image updating |
| CN101261681A (en) * | 2008-03-31 | 2008-09-10 | 北京中星微电子有限公司 | Road image extraction method and device in intelligent video monitoring |
| US20080273800A1 (en) * | 2005-01-11 | 2008-11-06 | Nec Corporation | Template Matching Method, Template Matching Apparatus, And Recording Medium That Records Program For It |
| US20100098331A1 (en) * | 2008-09-26 | 2010-04-22 | Sony Corporation | System and method for segmenting foreground and background in a video |
| JP2010123114A (en) * | 2008-10-24 | 2010-06-03 | Hiroshima Univ | Image segmentation device and image segmentation method |
| US20100271393A1 (en) * | 2009-04-22 | 2010-10-28 | Qualcomm Incorporated | Image selection and combination method and device |
| JP2015207280A (en) * | 2014-04-18 | 2015-11-19 | 株式会社リコー | target identification method and target identification device |
| US20160086031A1 (en) * | 2013-06-17 | 2016-03-24 | Fujitsu Limited | Image processing apparatus, image processing method, and storage medium |
| CN107292896A (en) * | 2017-08-15 | 2017-10-24 | 电子科技大学 | Contour extraction method based on Snake models |
| CN107633503A (en) * | 2017-08-01 | 2018-01-26 | 南京航空航天大学 | The image processing method of stalk is remained in a kind of automatic detection grain |
| CN108010050A (en) * | 2017-11-27 | 2018-05-08 | 电子科技大学 | A kind of foreground detection method based on adaptive RTS threshold adjustment and selective context update |
| US20180137612A1 (en) * | 2015-04-27 | 2018-05-17 | Wuhan Wuda Zoyon Science And Technology Co., Ltd. | A stepwise refinement detection method for pavement cracks |
| CN108286948A (en) * | 2017-01-09 | 2018-07-17 | 南京理工大学 | A kind of deflection of bridge span detection method based on image procossing |
| US20180330615A1 (en) * | 2017-05-12 | 2018-11-15 | Toyota Jidosha Kabushiki Kaisha | Road obstacle detection device, method, and program |
| CN109472259A (en) * | 2018-10-30 | 2019-03-15 | 河北工业大学 | Conspicuousness detection method is cooperateed with based on energy-optimised image |
| CN109859220A (en) * | 2019-03-06 | 2019-06-07 | 山东浪潮通软信息科技有限公司 | A kind of linear image partition method |
| CN110517311A (en) * | 2019-08-30 | 2019-11-29 | 北京麦飞科技有限公司 | Pest and disease monitoring method based on leaf spot lesion area |
| WO2020248515A1 (en) * | 2019-06-13 | 2020-12-17 | 苏州玖物互通智能科技有限公司 | Vehicle and pedestrian detection and recognition method combining inter-frame difference and bayes classifier |
| US20210019892A1 (en) * | 2019-07-15 | 2021-01-21 | Google Llc | Video Background Substraction Using Depth |
| CN112767295A (en) * | 2021-01-14 | 2021-05-07 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, storage medium, and electronic device |
| US20210406538A1 (en) * | 2020-06-25 | 2021-12-30 | Geosat Aerospace & Technology Inc. | Apparatus and method for image-guided agriculture |
| WO2022016563A1 (en) * | 2020-07-23 | 2022-01-27 | 南京科沃信息技术有限公司 | Ground monitoring system for plant-protection unmanned aerial vehicle, and monitoring method for same |
| US11238775B1 (en) * | 2020-12-18 | 2022-02-01 | Novatek Microelectronics Corp. | Image adjustment device and image adjustment method suitable for light-emitting diode display |
| CN114511770A (en) * | 2021-12-21 | 2022-05-17 | 武汉光谷卓越科技股份有限公司 | Road sign plate identification method |
| CN115082773A (en) * | 2022-07-21 | 2022-09-20 | 海门王巢家具制造有限公司 | Solid wood floor sorting method and system |
| CN115170839A (en) * | 2022-07-19 | 2022-10-11 | 北京理工大学 | Image data enhancement method and system |
| CN115170907A (en) * | 2022-07-06 | 2022-10-11 | 杭州海康威视数字技术股份有限公司 | Sample image generation method and device and automatic driving device |
| CN115311289A (en) * | 2022-10-12 | 2022-11-08 | 南通甜享纺织品有限公司 | Method for detecting oil stain defects of plain-color cloth |
| CN115526837A (en) * | 2022-08-31 | 2022-12-27 | 南京慧尔视智能科技有限公司 | Abnormal driving detection method and device, electronic equipment and medium |
| WO2023046112A1 (en) * | 2021-09-26 | 2023-03-30 | 维沃移动通信有限公司 | Document image enhancement method and apparatus, and electronic device |
-
2023
- 2023-08-18 CN CN202311044142.3A patent/CN116758081B/en active Active
Patent Citations (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040239762A1 (en) * | 2003-05-21 | 2004-12-02 | Porikli Fatih M. | Adaptive background image updating |
| US20080273800A1 (en) * | 2005-01-11 | 2008-11-06 | Nec Corporation | Template Matching Method, Template Matching Apparatus, And Recording Medium That Records Program For It |
| CN101261681A (en) * | 2008-03-31 | 2008-09-10 | 北京中星微电子有限公司 | Road image extraction method and device in intelligent video monitoring |
| US20100098331A1 (en) * | 2008-09-26 | 2010-04-22 | Sony Corporation | System and method for segmenting foreground and background in a video |
| JP2010123114A (en) * | 2008-10-24 | 2010-06-03 | Hiroshima Univ | Image segmentation device and image segmentation method |
| US20100271393A1 (en) * | 2009-04-22 | 2010-10-28 | Qualcomm Incorporated | Image selection and combination method and device |
| US20160086031A1 (en) * | 2013-06-17 | 2016-03-24 | Fujitsu Limited | Image processing apparatus, image processing method, and storage medium |
| JP2015207280A (en) * | 2014-04-18 | 2015-11-19 | 株式会社リコー | target identification method and target identification device |
| US20180137612A1 (en) * | 2015-04-27 | 2018-05-17 | Wuhan Wuda Zoyon Science And Technology Co., Ltd. | A stepwise refinement detection method for pavement cracks |
| CN108286948A (en) * | 2017-01-09 | 2018-07-17 | 南京理工大学 | A kind of deflection of bridge span detection method based on image procossing |
| US20180330615A1 (en) * | 2017-05-12 | 2018-11-15 | Toyota Jidosha Kabushiki Kaisha | Road obstacle detection device, method, and program |
| CN107633503A (en) * | 2017-08-01 | 2018-01-26 | 南京航空航天大学 | The image processing method of stalk is remained in a kind of automatic detection grain |
| CN107292896A (en) * | 2017-08-15 | 2017-10-24 | 电子科技大学 | Contour extraction method based on Snake models |
| CN108010050A (en) * | 2017-11-27 | 2018-05-08 | 电子科技大学 | A kind of foreground detection method based on adaptive RTS threshold adjustment and selective context update |
| CN109472259A (en) * | 2018-10-30 | 2019-03-15 | 河北工业大学 | Conspicuousness detection method is cooperateed with based on energy-optimised image |
| CN109859220A (en) * | 2019-03-06 | 2019-06-07 | 山东浪潮通软信息科技有限公司 | A kind of linear image partition method |
| WO2020248515A1 (en) * | 2019-06-13 | 2020-12-17 | 苏州玖物互通智能科技有限公司 | Vehicle and pedestrian detection and recognition method combining inter-frame difference and bayes classifier |
| US20210019892A1 (en) * | 2019-07-15 | 2021-01-21 | Google Llc | Video Background Substraction Using Depth |
| CN110517311A (en) * | 2019-08-30 | 2019-11-29 | 北京麦飞科技有限公司 | Pest and disease monitoring method based on leaf spot lesion area |
| US20210406538A1 (en) * | 2020-06-25 | 2021-12-30 | Geosat Aerospace & Technology Inc. | Apparatus and method for image-guided agriculture |
| WO2022016563A1 (en) * | 2020-07-23 | 2022-01-27 | 南京科沃信息技术有限公司 | Ground monitoring system for plant-protection unmanned aerial vehicle, and monitoring method for same |
| US11238775B1 (en) * | 2020-12-18 | 2022-02-01 | Novatek Microelectronics Corp. | Image adjustment device and image adjustment method suitable for light-emitting diode display |
| CN112767295A (en) * | 2021-01-14 | 2021-05-07 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, storage medium, and electronic device |
| WO2023046112A1 (en) * | 2021-09-26 | 2023-03-30 | 维沃移动通信有限公司 | Document image enhancement method and apparatus, and electronic device |
| CN114511770A (en) * | 2021-12-21 | 2022-05-17 | 武汉光谷卓越科技股份有限公司 | Road sign plate identification method |
| CN115170907A (en) * | 2022-07-06 | 2022-10-11 | 杭州海康威视数字技术股份有限公司 | Sample image generation method and device and automatic driving device |
| CN115170839A (en) * | 2022-07-19 | 2022-10-11 | 北京理工大学 | Image data enhancement method and system |
| CN115082773A (en) * | 2022-07-21 | 2022-09-20 | 海门王巢家具制造有限公司 | Solid wood floor sorting method and system |
| CN115526837A (en) * | 2022-08-31 | 2022-12-27 | 南京慧尔视智能科技有限公司 | Abnormal driving detection method and device, electronic equipment and medium |
| CN115311289A (en) * | 2022-10-12 | 2022-11-08 | 南通甜享纺织品有限公司 | Method for detecting oil stain defects of plain-color cloth |
Non-Patent Citations (1)
| Title |
|---|
| 黄鑫娟;周洁敏;刘伯扬;: "自适应混合高斯背景模型的运动目标检测方法", 计算机应用, no. 01 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152163A (en) * | 2023-11-01 | 2023-12-01 | 安徽乾劲企业管理有限公司 | Bridge construction quality visual detection method |
| CN117152163B (en) * | 2023-11-01 | 2024-02-27 | 安徽乾劲企业管理有限公司 | Bridge construction quality visual detection method |
| CN117557784A (en) * | 2024-01-09 | 2024-02-13 | 腾讯科技（深圳）有限公司 | Target detection method, target detection device, electronic equipment and storage medium |
| CN117557784B (en) * | 2024-01-09 | 2024-04-26 | 腾讯科技（深圳）有限公司 | Target detection method, target detection device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116758081B (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116758081B (en) | Unmanned aerial vehicle road and bridge inspection image processing method | |
| CN109977812B (en) | Vehicle-mounted video target detection method based on deep learning | |
| CN112365462B (en) | Image-based change detection method | |
| CN110659649A (en) | Image processing and character recognition algorithm based on near infrared light imaging | |
| CN110726725A (en) | Transmission line hardware corrosion detection method and device | |
| CN107705254B (en) | City environment assessment method based on street view | |
| CN106408025B (en) | Aerial Images insulator classifying identification method based on image procossing | |
| CN103177456A (en) | Method for detecting moving target of video image | |
| CN113435407B (en) | Small target identification method and device for power transmission system | |
| CN115661720B (en) | Target tracking and identifying method and system for shielded vehicle | |
| CN109886146B (en) | Flood information remote sensing intelligent acquisition method and device based on machine vision detection | |
| CN106951863B (en) | Method for detecting change of infrared image of substation equipment based on random forest | |
| CN113255590A (en) | Defect detection model training method, defect detection method, device and system | |
| CN105740844A (en) | Insulator cracking fault detection method based on image identification technology | |
| CN110570462A (en) | flood inundation range automatic extraction method based on polarized radar remote sensing image | |
| CN111291818B (en) | Non-uniform class sample equalization method for cloud mask | |
| CN115131747A (en) | Knowledge distillation-based power transmission channel engineering vehicle target detection method and system | |
| CN116342894A (en) | GIS infrared feature recognition system and method based on improved YOLOv5 | |
| CN114037650B (en) | Ground target visible light damage image processing method for change detection and target detection | |
| CN117079197B (en) | Intelligent building site management method and system | |
| CN116563774B (en) | Automatic identification method and system for illegal mining of cultivated land in China | |
| CN116703787A (en) | Building construction safety risk early warning method and system | |
| CN109658405B (en) | Image data quality control method and system in crop live-action observation | |
| CN116228790A (en) | Cloud and sky segmentation method and device, terminal equipment and storage medium | |
| CN114120061A (en) | Small target defect detection method and system for power inspection scene |
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 |