CN118279183B - Unmanned aerial vehicle remote sensing mapping image enhancement method and system - Google Patents
- ️Tue Aug 06 2024
Info
-
Publication number
- CN118279183B CN118279183B CN202410714076.4A CN202410714076A CN118279183B CN 118279183 B CN118279183 B CN 118279183B CN 202410714076 A CN202410714076 A CN 202410714076A CN 118279183 B CN118279183 B CN 118279183B Authority
- CN
- China Prior art keywords
- image
- remote sensing
- sensing mapping
- image enhancement
- enhanced Prior art date
- 2024-06-04 Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013507 mapping Methods 0.000 title claims abstract description 150
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 130
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000011156 evaluation Methods 0.000 claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000001914 filtration Methods 0.000 description 12
- 238000012937 correction Methods 0.000 description 4
- 108010068977 Golgi membrane glycoproteins Proteins 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000003313 weakening effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an unmanned aerial vehicle remote sensing mapping image enhancement method and system, which relate to the technical field of image enhancement, and comprise the steps of numbering preprocessed remote sensing mapping images according to the acquisition time sequence, analyzing the mean square error MSE of the remote sensing mapping images, and dividing all the remote sensing mapping images into corresponding enhancement image data sets; calculating to obtain an image enhancement evaluation coefficient, and determining a first image enhancement algorithm of an enhanced image data set corresponding to the current remote sensing mapping image; generating all image enhancement algorithm arrangements, calculating to obtain a final image enhancement evaluation coefficient, determining the optimal image enhancement algorithm arrangement of an enhanced image dataset corresponding to the current remote sensing mapping image, and carrying out batch enhancement processing output on all remote sensing mapping images in the enhanced image dataset. The method can ensure that the optimal enhancement flow aiming at the current remote sensing mapping image data set is found, so that the quality of the image can be improved, and time and calculation resources are saved in batch enhancement processing.
Description
Technical Field
The invention relates to the technical field of image enhancement, in particular to an unmanned aerial vehicle remote sensing mapping image enhancement method and system.
Background
With the rapid development of unmanned aerial vehicle technology, unmanned aerial vehicle remote sensing mapping technology has become one of important means for obtaining geographic information. The unmanned plane has the advantages of high flexibility, low cost, high response speed and the like, and is widely applied to the fields of homeland resource investigation, urban planning, environment monitoring, disaster emergency and the like. However, the quality of unmanned aerial vehicle remote sensing survey images directly affects the accuracy of subsequent data analysis and application. Therefore, how to effectively enhance the unmanned aerial vehicle remote sensing mapping image and improve the definition, contrast and information quantity of the unmanned aerial vehicle remote sensing mapping image becomes a problem to be solved urgently.
In the chinese application of application publication No. CN113781361a, an unmanned aerial vehicle remote sensing mapping image enhancement processing method is disclosed, which includes a low-pass filtering module, a high-pass filtering module and an image integration module, where the low-pass filtering module is used for blocking or weakening a high-frequency signal exceeding a set critical value, and the high-pass filtering module is used for blocking or weakening a high-frequency signal lower than the set critical value, and the steps are as follows: step one: the acquired images are equally divided into a plurality of interval images. In the scheme, the images are split first, the images are enhanced one by one, then, when the images are required to be subjected to low-pass filtering according to the content of the images, the low-pass filtering module is utilized to carry out low-pass filtering on the images, edges and noise are effectively removed, and the middle part is clearer.
In the application of the invention, the images are split and enhanced one by one, then when the images are required to be subjected to low-pass filtering according to the content of the images, the low-pass filtering module (i.e. the low-pass filter) is utilized to carry out low-pass filtering on the images, so that the edges and noise are effectively removed, the middle part is clearer, and similarly, the images important for the edge images can be subjected to high-pass filtering, the edges of the images are highlighted, but the images are enhanced and analyzed one by one, so that time and resources are very consumed, and only the processing method of filtering is used, then the images can not be effectively processed for all types of remote sensing mapping images, especially when the images have obvious differences in brightness, contrast, noise level and the like, and even if a plurality of enhancement algorithms are used, the image enhancement results are influenced by different sequences, so that the images can not be flexibly adapted to different application scenes and requirements.
Therefore, the invention provides an unmanned aerial vehicle remote sensing mapping image enhancement method and system.
Disclosure of Invention
(One) solving the technical problems
Aiming at the defects of the prior art, the invention provides the unmanned aerial vehicle remote sensing mapping image enhancement method and system, and the first image enhancement algorithm and the optimal image enhancement algorithm of each enhancement image data set are determined to be arranged by dividing the similar remote sensing mapping image into the corresponding enhancement image data sets, so that the optimal enhancement flow aiming at the current remote sensing mapping image data set can be ensured to be found, the quality of the image can be improved, and the time and the calculation resources are saved in batch enhancement processing, thereby solving the technical problems recorded in the background art.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme: an unmanned aerial vehicle remote sensing mapping image enhancement method comprises the following steps:
numbering the preprocessed remote sensing mapping images according to the acquisition time sequence, analyzing the mean square error MSE of the remote sensing mapping images, and dividing all the remote sensing mapping images into corresponding enhanced image data sets;
Randomly extracting a remote sensing mapping image from each enhanced image data set, introducing different image enhancement algorithms to carry out enhancement processing, and obtaining peak signal-to-noise ratios of enhanced images output by the different image enhancement algorithms And structural similarityCalculating to obtain image enhancement evaluation coefficientsDetermining a first image enhancement algorithm of an enhanced image dataset corresponding to a current remote sensing mapping image;
Generating all image enhancement algorithm arrangements, producing a final enhanced remote sensing mapping image according to the image enhancement algorithm arrangements, and calculating to obtain a final image enhancement evaluation coefficient And determining the optimal image enhancement algorithm arrangement of the enhanced image dataset corresponding to the current remote sensing mapping image, and carrying out batch enhancement processing output on all the remote sensing mapping images in the enhanced image dataset.
Furthermore, the ground image data is acquired through a high-definition camera or other remote sensing equipment carried by the unmanned aerial vehicle, and the acquired image data is transmitted to a ground station in real time for preprocessing, and the method comprises the steps of denoising, geometric correction, radiation correction and the like.
Further, the preprocessed remote sensing mapping images are numbered according to the acquisition time sequence, and mean square errors MSE of two pictures are analyzed by comparing the No. 2 remote sensing mapping images with the No.1 remote sensing mapping images in sequence, and are marked as MSE (1, 2), MSE (1, 3) to MSE (1, m).
The mean square error (Mean Squared Error, MSE) is the difference between the pixels of two pictures, and the squares of these differences are summed and finally divided by the number of pixels to give the MSE, the smaller the MSE value, the more similar the pictures. The mean square error (Mean Squared Error, MSE) may be obtained by an MSE computation function in image processing software, including AdobePhotoshop, GIMP, lightroom, etc.
Further, MSE (1, 2) is obtained, MSE (1, 3) -MSE (1, m), and the mean square error average value of the previous m images is calculatedWhen MSE (1, m) exceeds 2When the method is used, the No.1 to m-1 remote sensing mapping images are marked into a first enhanced image data set, and mean square errors MSE of two pictures are analyzed by comparing the No.1 to m-1 remote sensing mapping images in sequence from the m+1 remote sensing mapping images, wherein the MSE is marked as MSE (m, m+1), MSE (m, m+2) -MSE (m, m+n) until MSE (m, m+n) exceeds 2When the second enhanced image data set is included, the remote sensing mapping images from the m number to the m+n-1 number are marked in the second enhanced image data set; repeating the operation until all the remote sensing mapping images are divided into corresponding enhanced image data sets.
Further, a remote sensing mapping image is randomly extracted from each enhanced image data set, different image enhancement algorithms are introduced for enhancement processing, and after enhancement, an image processing library (such as OpenCV, PIL and the like) is used for calculating the peak signal-to-noise ratio (PSNR) and the Structural Similarity (SSIM) of the enhanced image output by the different image enhancement algorithms, which are recorded asAnd。
The image enhancement algorithm comprises histogram equalization, wavelet transformation image enhancement, partial differential equation image enhancement, fractional differential equation enhancement algorithm, retinex image enhancement algorithm and image enhancement algorithm based on deep learning.
Peak signal-to-noise ratio (PSNR) is an objective indicator of the distortion or noise level of an image. The higher the PSNR value, the closer the enhanced image is to the original image, and the less distortion or noise. Typical peak signal-to-noise values are typically between 30dB and 50dB, with PSNR approaching 50dB, representing only a small Xu Feichang error in the compressed image; when PSNR is more than 30dB, the human eye hardly perceives the difference between the compressed image and the original image; when PSNR is between 20dB and 30dB, the human eye can perceive the difference of the images; when PSNR is between 10dB and 20dB, the human eye can see the original structure of the image with naked eyes, and the two images can be intuitively judged that no great difference exists; when the PSNR is lower than 10dB, it is difficult for a human being to judge whether or not two images are identical with the naked eye, and whether or not one image is a compression result of the other image.
Structural Similarity (SSIM) is an indicator of the degree of similarity between two images. The closer the SSIM value is to 1, the more structurally similar the enhanced image is to the original image.
Further, the peak signal-to-noise ratio of the enhanced image output by different image enhancement algorithms is obtainedAnd structural similarityAfter linear normalization processing, calculating to obtain an image enhancement evaluation coefficient：
Where a represents the sequential numbering of the different image enhancement algorithms.
Further, obtaining an image enhancement evaluation coefficient of each remote sensing mapping imageWill beThe image enhancement algorithm corresponding to the sequence number is determined to be the first image enhancement algorithm of the enhanced image dataset corresponding to the current remote sensing mapping image.
Remote sensing mapping images have a variety of characteristics, such as spectral characteristics, spatial resolution, and the like. Therefore, in selecting an image enhancement technique, it is necessary to select an appropriate enhancement technique according to specific characteristics of an image.
Further, obtaining an image enhancement evaluation coefficient of each remote sensing mapping imageWill be divided intoImage enhancement evaluation coefficients other than the image enhancement algorithm corresponding to the sequence numberAnd (3) extracting the image enhancement algorithm with the size larger than 1, renumbering, generating all possible image enhancement algorithm arrangements by using a recursion algorithm, and numbering the image enhancement algorithm arrangements.
Further, the remote sensing mapping images processed by the first image enhancement algorithm are sequentially imported into corresponding image enhancement algorithm processing according to the image enhancement algorithm arrangement sequence, and the remote sensing mapping images processed by all the image enhancement algorithms in the algorithm arrangement are output and recorded as final enhanced remote sensing mapping images.
Further, obtaining final enhanced remote sensing mapping images output under different image enhancement algorithm arrangements, and calculating to obtain final image enhancement evaluation coefficientsWill beAnd determining the image enhancement algorithm arrangement corresponding to the sequence number as the optimal image enhancement algorithm arrangement of the enhanced image dataset corresponding to the current remote sensing mapping image.
An unmanned aerial vehicle remote sensing survey image enhancement system, comprising:
the image data acquisition module acquires the image data of the ground through a high-definition camera carried by the unmanned aerial vehicle, and transmits the acquired image data to the ground station in real time for preprocessing;
The mean square error analysis module is used for carrying out mean square error MSE analysis on the preprocessed remote sensing mapping image from the image data acquisition module;
the image data set dividing module is used for analyzing the mean square error MSE from the mean square error analyzing module and dividing the remote sensing mapping images in batches;
The first image enhancement algorithm determining module randomly extracts a remote sensing mapping image from each enhanced image data set, and introduces different image enhancement algorithms to carry out enhancement processing to obtain peak signal-to-noise ratios of enhanced images output by different image enhancement algorithms And structural similarityCalculating to obtain image enhancement evaluation coefficientsDetermining a first image enhancement algorithm of an enhanced image dataset corresponding to a current remote sensing mapping image;
The optimal arrangement determining module generates all image enhancement algorithm arrangements, generates final enhanced remote sensing mapping images according to the image enhancement algorithm arrangements, and calculates to obtain final image enhancement evaluation coefficients Determining the optimal image enhancement algorithm arrangement of an enhanced image dataset corresponding to the current remote sensing mapping image, and carrying out batch enhancement processing output on all remote sensing mapping images in the enhanced image dataset;
(III) beneficial effects
The invention provides an unmanned aerial vehicle remote sensing mapping image enhancement method and system, which have the following beneficial effects:
1. The preprocessed remote sensing mapping images are numbered according to the acquisition time sequence, the mean square error MSE of the remote sensing mapping images is analyzed, all the remote sensing mapping images are divided into corresponding enhanced image data sets, and only partial images in each data set can be enhanced and analyzed by dividing similar remote sensing mapping images into corresponding enhanced image data sets, so that calculation resources are saved, and processing efficiency is improved.
2. Randomly extracting a remote sensing mapping image from each enhanced image data set, introducing different image enhancement algorithms to carry out enhancement processing, and obtaining peak signal-to-noise ratios of enhanced images output by the different image enhancement algorithmsAnd structural similarityCalculating to obtain image enhancement evaluation coefficientsThe first image enhancement algorithm of the enhanced image data set corresponding to the current remote sensing mapping image is determined, and the optimal enhancement strategy of each data set can be determined by comparing the performances of different algorithms on each data set, so that the overall processing effect of the remote sensing mapping image is improved.
3. Generating all possible image enhancement algorithm arrangements, producing a final enhanced remote sensing mapping image according to the image enhancement algorithm arrangements, and calculating to obtain a final image enhancement evaluation coefficientThe optimal image enhancement algorithm arrangement of the enhanced image dataset corresponding to the current remote sensing mapping image is determined, and batch enhancement processing output is carried out on all the remote sensing mapping images in the enhanced image dataset, so that the optimal enhancement flow aiming at the current remote sensing mapping image dataset can be ensured to be found, the quality of the image can be improved, and the time and the computing resources are saved in batch enhancement processing.
Drawings
FIG. 1 is a schematic flow chart of an unmanned aerial vehicle remote sensing mapping image enhancement method;
fig. 2 is a schematic structural diagram of an unmanned aerial vehicle remote sensing mapping image enhancement system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides an unmanned aerial vehicle remote sensing mapping image enhancement method, which comprises the following steps:
step one, numbering the preprocessed remote sensing mapping images according to the acquisition time sequence, analyzing the mean square error MSE of the remote sensing mapping images, and dividing all the remote sensing mapping images into corresponding enhanced image data sets.
The first step comprises the following steps:
Step 101, acquiring ground image data through a high-definition camera or other remote sensing equipment carried by the unmanned aerial vehicle, and transmitting the acquired image data to a ground station in real time for preprocessing, wherein the steps comprise denoising, geometric correction, radiation correction and the like.
And 102, numbering the preprocessed remote sensing mapping images according to the acquisition time sequence, and comparing and analyzing the mean square error MSE of the two pictures with the No. 1 remote sensing mapping image sequentially from the No. 2 remote sensing mapping image, wherein the MSE is marked as MSE (1, 2), MSE (1, 3) to MSE (1, m).
The mean square error (Mean Squared Error, MSE) is the difference between the pixels of two pictures, and the squares of these differences are summed and finally divided by the number of pixels to give the MSE, the smaller the MSE value, the more similar the pictures. The mean square error (Mean Squared Error, MSE) may be obtained by an MSE computation function in image processing software, including AdobePhotoshop, GIMP, lightroom, etc.
Step 103, obtaining MSE (1, 2), MSE (1, 3) -MSE (1, m), calculating and obtaining mean square error mean value of the previous m imagesWhen MSE (1, m) exceeds 2When the method is used, the No.1 to m-1 remote sensing mapping images are marked into a first enhanced image data set, and mean square errors MSE of two pictures are analyzed by comparing the No.1 to m-1 remote sensing mapping images in sequence from the m+1 remote sensing mapping images, wherein the MSE is marked as MSE (m, m+1), MSE (m, m+2) -MSE (m, m+n) until MSE (m, m+n) exceeds 2And (3) when the remote sensing mapping images from the m numbers to the m+n-1 numbers are marked into a second enhanced image data set. Repeating the operation until all the remote sensing mapping images are divided into corresponding enhanced image data sets.
In use, the contents of steps 101 to 103 are combined:
the preprocessed remote sensing mapping images are numbered according to the acquisition time sequence, the mean square error MSE of the remote sensing mapping images is analyzed, all the remote sensing mapping images are divided into corresponding enhanced image data sets, and only partial images in each data set can be enhanced and analyzed by dividing similar remote sensing mapping images into corresponding enhanced image data sets, so that calculation resources are saved, and processing efficiency is improved.
Step two, randomly extracting a remote sensing mapping image from each enhanced image data set, leading in different image enhancement algorithms to carry out enhancement processing, and obtaining peak signal-to-noise ratios of enhanced images output by the different image enhancement algorithmsAnd structural similarityCalculating to obtain image enhancement evaluation coefficientsA first image enhancement algorithm of an enhanced image dataset corresponding to a current remote sensing mapping image is determined.
The second step comprises the following steps:
Step 201, randomly extracting a remote sensing mapping image from each enhanced image data set, introducing different image enhancement algorithms to perform enhancement processing, and calculating peak signal to noise ratio (PSNR) and Structural Similarity (SSIM) of the enhanced image output by the different image enhancement algorithms by using an image processing library (such as OpenCV, PIL, etc.), which is recorded as And。
The image enhancement algorithm comprises histogram equalization, wavelet transformation image enhancement, partial differential equation image enhancement, fractional differential equation enhancement algorithm, retinex image enhancement algorithm and image enhancement algorithm based on deep learning.
Peak signal-to-noise ratio (PSNR) is an objective indicator of the distortion or noise level of an image. The higher the PSNR value, the closer the enhanced image is to the original image, and the less distortion or noise. Typical peak signal-to-noise values are typically between 30dB and 50dB, with PSNR approaching 50dB, representing only a small Xu Feichang error in the compressed image; when PSNR is more than 30dB, the human eye hardly perceives the difference between the compressed image and the original image; when PSNR is between 20dB and 30dB, the human eye can perceive the difference of the images; when PSNR is between 10dB and 20dB, the human eye can see the original structure of the image with naked eyes, and the two images can be intuitively judged that no great difference exists; when the PSNR is lower than 10dB, it is difficult for a human being to judge whether or not two images are identical with the naked eye, and whether or not one image is a compression result of the other image.
Structural Similarity (SSIM) is an indicator of the degree of similarity between two images. The closer the SSIM value is to 1, the more structurally similar the enhanced image is to the original image.
Step 202, obtaining peak signal-to-noise ratio of enhanced images output by different image enhancement algorithmsAnd structural similarityAfter linear normalization processing, calculating to obtain an image enhancement evaluation coefficient：
Where a represents the sequential numbering of the different image enhancement algorithms.
Step 203, obtaining an image enhancement evaluation coefficient of each remote sensing mapping imageWill beThe image enhancement algorithm corresponding to the sequence number is determined to be the first image enhancement algorithm of the enhanced image dataset corresponding to the current remote sensing mapping image.
Remote sensing mapping images have a variety of characteristics, such as spectral characteristics, spatial resolution, and the like. Therefore, in selecting an image enhancement technique, it is necessary to select an appropriate enhancement technique according to specific characteristics of an image.
In use, the contents of steps 201 to 203 are combined:
Randomly extracting a remote sensing mapping image from each enhanced image data set, introducing different image enhancement algorithms to carry out enhancement processing, and obtaining peak signal-to-noise ratios of enhanced images output by the different image enhancement algorithms And structural similarityCalculating to obtain image enhancement evaluation coefficientsThe first image enhancement algorithm of the enhanced image data set corresponding to the current remote sensing mapping image is determined, and the optimal enhancement strategy of each data set can be determined by comparing the performances of different algorithms on each data set, so that the overall processing effect of the remote sensing mapping image is improved.
Generating all image enhancement algorithm arrangements, producing a final enhanced remote sensing mapping image according to the image enhancement algorithm arrangements, and calculating to obtain a final image enhancement evaluation coefficientAnd determining the optimal image enhancement algorithm arrangement of the enhanced image dataset corresponding to the current remote sensing mapping image, and carrying out batch enhancement processing output on all the remote sensing mapping images in the enhanced image dataset.
The third step comprises the following steps:
step 301, obtaining an image enhancement evaluation coefficient of each remote sensing mapping image Will be divided intoImage enhancement evaluation coefficients other than the image enhancement algorithm corresponding to the sequence numberAnd (3) extracting the image enhancement algorithm with the size larger than 1, renumbering, generating all possible image enhancement algorithm arrangements by using a recursion algorithm, and numbering the image enhancement algorithm arrangements.
Step 302, the remote sensing mapping images processed by the first image enhancement algorithm are sequentially imported into corresponding image enhancement algorithm processing according to the image enhancement algorithm arrangement sequence, and the remote sensing mapping images processed by all the image enhancement algorithms in the algorithm arrangement are output and recorded as final enhanced remote sensing mapping images.
It should be noted that, after the image is processed by the image enhancement algorithm with the image lead-in number of 1, the image is output, and is further processed by the image enhancement algorithm with the image lead-in number of 2, and the steps are repeated until the remote sensing mapping image is processed by all the image enhancement algorithms in the algorithm arrangement.
Step 303, obtaining the final enhanced remote sensing mapping image output under different image enhancement algorithm arrangements, and calculating to obtain the final image enhancement evaluation coefficientWill beAnd determining the image enhancement algorithm arrangement corresponding to the sequence number as the optimal image enhancement algorithm arrangement of the enhanced image dataset corresponding to the current remote sensing mapping image.
Wherein the final image enhancement evaluation coefficientsAnd image enhancement evaluation coefficientB represents the sequential numbering of the different image enhancement algorithm permutations.
Step 304, performing batch enhancement processing output on all remote sensing mapping images in each enhanced image data set according to the first image enhancement algorithm and the optimal image enhancement algorithm arrangement of each enhanced image data set.
In use, the contents of steps 301 to 304 are combined:
generating all possible image enhancement algorithm arrangements, producing a final enhanced remote sensing mapping image according to the image enhancement algorithm arrangements, and calculating to obtain a final image enhancement evaluation coefficient The optimal image enhancement algorithm arrangement of the enhanced image dataset corresponding to the current remote sensing mapping image is determined, and batch enhancement processing output is carried out on all the remote sensing mapping images in the enhanced image dataset, so that the optimal enhancement flow aiming at the current remote sensing mapping image dataset can be ensured to be found, the quality of the image can be improved, and the time and the computing resources are saved in batch enhancement processing.
Referring to fig. 2, the present invention provides an unmanned aerial vehicle remote sensing mapping image enhancement system, which includes:
And the image data acquisition module acquires the image data of the ground through a high-definition camera carried by the unmanned aerial vehicle, and transmits the acquired image data to the ground station in real time for preprocessing.
And the mean square error analysis module is used for carrying out mean square error MSE analysis on the preprocessed remote sensing mapping image from the image data acquisition module.
And the image data set dividing module is used for analyzing the mean square error MSE from the mean square error analyzing module and carrying out batch division on the remote sensing mapping images.
The first image enhancement algorithm determining module randomly extracts a remote sensing mapping image from each enhanced image data set, and introduces different image enhancement algorithms to carry out enhancement processing to obtain peak signal-to-noise ratios of enhanced images output by different image enhancement algorithmsAnd structural similarityCalculating to obtain image enhancement evaluation coefficientsA first image enhancement algorithm of an enhanced image dataset corresponding to a current remote sensing mapping image is determined.
The optimal arrangement determining module generates all image enhancement algorithm arrangements, generates final enhanced remote sensing mapping images according to the image enhancement algorithm arrangements, and calculates to obtain final image enhancement evaluation coefficientsAnd determining the optimal image enhancement algorithm arrangement of the enhanced image dataset corresponding to the current remote sensing mapping image, and carrying out batch enhancement processing output on all the remote sensing mapping images in the enhanced image dataset.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (2)
1. The unmanned aerial vehicle remote sensing mapping image enhancement method is characterized by comprising the following steps of: the method comprises the following steps:
numbering the preprocessed remote sensing mapping images according to the acquisition time sequence, analyzing the mean square error MSE of the remote sensing mapping images, and dividing all the remote sensing mapping images into corresponding enhanced image data sets;
numbering the preprocessed remote sensing mapping images according to the acquisition time sequence, and comparing and analyzing the mean square error MSE of two pictures with the No. 1 remote sensing mapping image sequentially from the No. 2 remote sensing mapping image, wherein the MSE is marked as MSE (1, 2), MSE (1, 3) to MSE (1, m);
obtaining MSE (1, 2), MSE (1, 3) -MSE (1, m), calculating and obtaining mean square error mean value of the previous m images When MSE (1, m) exceedsWhen the method is used, the No.1 to m-1 remote sensing mapping images are marked into a first enhanced image data set, and mean square errors MSE of two pictures are analyzed by comparing the No.1 to m-1 remote sensing mapping images in sequence from the m+1 remote sensing mapping images, wherein the MSE is marked as MSE (m, m+1), MSE (m, m+2) to MSE (m, m+n) until the MSE (m, m+n) exceedsWhen the second enhanced image data set is included, the remote sensing mapping images from the m number to the m+n-1 number are marked in the second enhanced image data set; repeating the operation until all the remote sensing mapping images are divided into corresponding enhanced image data sets;
Randomly extracting a remote sensing mapping image from each enhanced image data set, introducing different image enhancement algorithms to carry out enhancement processing to obtain peak signal-to-noise ratio PSNR a and structural similarity SSIM a of the enhanced images output by the different image enhancement algorithms, calculating to obtain an image enhancement evaluation coefficient Zp a, and determining a first image enhancement algorithm of the enhanced image data set corresponding to the current remote sensing mapping image;
The method comprises the steps of obtaining peak signal-to-noise ratio PSNR a and structural similarity SSIM a of enhanced images output by different image enhancement algorithms, and calculating to obtain an image enhancement evaluation coefficient Zp a after linear normalization processing:
wherein a represents the sequence number of different image enhancement algorithms;
Acquiring an image enhancement evaluation coefficient Zp a of each remote sensing mapping image, and determining an image enhancement algorithm corresponding to maxZp a sequence numbers as a first image enhancement algorithm of an enhanced image dataset corresponding to the current remote sensing mapping image;
Generating all image enhancement algorithm arrangements, producing a final enhanced remote sensing mapping image according to the image enhancement algorithm arrangements, calculating to obtain a final image enhancement evaluation coefficient Zp b, determining the optimal image enhancement algorithm arrangement of an enhanced image dataset corresponding to the current remote sensing mapping image, and carrying out batch enhancement processing output on all remote sensing mapping images in the enhanced image dataset;
acquiring an image enhancement evaluation coefficient Zp a of each remote sensing mapping image, extracting image enhancement algorithms with the image enhancement evaluation coefficient Zp a larger than 1 except for the image enhancement algorithm corresponding to maxZp a sequence numbering, and generating all possible image enhancement algorithm arrangements by using a recursion algorithm after renumbering, and numbering the image enhancement algorithm arrangements;
Sequentially importing the remote sensing mapping images processed by the first image enhancement algorithm into corresponding image enhancement algorithm processing according to the image enhancement algorithm arrangement sequence, outputting the remote sensing mapping images processed by all the image enhancement algorithms in the algorithm arrangement, and recording the remote sensing mapping images as final enhanced remote sensing mapping images;
And obtaining final enhanced remote sensing mapping images output under different image enhancement algorithm arrangements, calculating to obtain a final image enhancement evaluation coefficient Zp b, and determining the image enhancement algorithm arrangement corresponding to the maxZp b sequence number as the optimal image enhancement algorithm arrangement of the enhanced image dataset corresponding to the current remote sensing mapping image.
2. An unmanned aerial vehicle remote sensing mapping image enhancement system for implementing the method of claim 1, wherein: comprising the following steps:
the image data acquisition module acquires the image data of the ground through a high-definition camera carried by the unmanned aerial vehicle, and transmits the acquired image data to the ground station in real time for preprocessing;
The mean square error analysis module is used for carrying out mean square error MSE analysis on the preprocessed remote sensing mapping image from the image data acquisition module;
The image data set dividing module is used for analyzing the mean square error MSE from the mean square error analyzing module and dividing the remote sensing mapping images in batches;
the first image enhancement algorithm determining module randomly extracts a remote sensing mapping image from each enhanced image data set, introduces different image enhancement algorithms to carry out enhancement processing, obtains peak signal-to-noise ratio PSNR a and structural similarity SSIM a of the enhanced images output by the different image enhancement algorithms, calculates an obtained image enhancement evaluation coefficient Zp a, and determines a first image enhancement algorithm of an enhanced image data set corresponding to the current remote sensing mapping image;
The optimal arrangement determining module is used for generating all image enhancement algorithm arrangements, producing a final enhanced remote sensing mapping image according to the image enhancement algorithm arrangements, calculating to obtain a final image enhancement evaluation coefficient Zp b, determining the optimal image enhancement algorithm arrangements of an enhanced image dataset corresponding to the current remote sensing mapping image, and carrying out batch enhancement processing output on all remote sensing mapping images in the enhanced image dataset.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410714076.4A CN118279183B (en) | 2024-06-04 | 2024-06-04 | Unmanned aerial vehicle remote sensing mapping image enhancement method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410714076.4A CN118279183B (en) | 2024-06-04 | 2024-06-04 | Unmanned aerial vehicle remote sensing mapping image enhancement method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118279183A CN118279183A (en) | 2024-07-02 |
| CN118279183B true CN118279183B (en) | 2024-08-06 |
Family
ID=91638806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410714076.4A Active CN118279183B (en) | 2024-06-04 | 2024-06-04 | Unmanned aerial vehicle remote sensing mapping image enhancement method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118279183B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119006348B (en) * | 2024-08-07 | 2025-02-07 | 广州博瑞信息技术股份有限公司 | Mapping image enhancement system based on unmanned aerial vehicle remote sensing technology and implementation method thereof |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703739A (en) * | 2022-02-25 | 2023-09-05 | 索尼集团公司 | Image enhancement method and device |
| CN118071843A (en) * | 2023-11-20 | 2024-05-24 | 南京佳格耕耘科技有限公司 | Farmland mapping system based on remote sensing data |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2951528B1 (en) * | 2013-01-29 | 2018-07-25 | Andrew Robert Korb | Methods for analyzing and compressing multiple images |
| CN117291830A (en) * | 2019-10-01 | 2023-12-26 | 长沙微妙医疗科技有限公司 | System and method for image enhancement using self-focused deep learning |
| CN113781361A (en) * | 2021-09-27 | 2021-12-10 | 辽宁工程技术大学 | Unmanned aerial vehicle remote sensing mapping image enhancement processing method |
| CN115984134A (en) * | 2022-12-30 | 2023-04-18 | 黄河水利职业技术学院 | A Method for Intelligent Enhancement of Remote Sensing Mapping Image |
-
2024
- 2024-06-04 CN CN202410714076.4A patent/CN118279183B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703739A (en) * | 2022-02-25 | 2023-09-05 | 索尼集团公司 | Image enhancement method and device |
| CN118071843A (en) * | 2023-11-20 | 2024-05-24 | 南京佳格耕耘科技有限公司 | Farmland mapping system based on remote sensing data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118279183A (en) | 2024-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10902563B2 (en) | 2021-01-26 | Moran's / for impulse noise detection and removal in color images |
| EP4109392A1 (en) | 2022-12-28 | Image processing method and image processing device |
| CN112419151B (en) | 2023-07-21 | Image degradation processing method and device, storage medium and electronic equipment |
| Temel et al. | 2019 | Perceptual image quality assessment through spectral analysis of error representations |
| CN118279183B (en) | 2024-08-06 | Unmanned aerial vehicle remote sensing mapping image enhancement method and system |
| US9443286B2 (en) | 2016-09-13 | Gray image processing method and apparatus based on wavelet transformation |
| WO2012001982A1 (en) | 2012-01-05 | Stereo image processing apparatus and method of processing stereo image |
| CN115294035B (en) | 2023-11-10 | Bright spot positioning method, bright spot positioning device, electronic equipment and storage medium |
| Mahajan et al. | 2014 | A comparative analysis of different image fusion techniques |
| CN106991670B (en) | 2019-12-10 | no-reference noise image quality evaluation method and system |
| CN115326809A (en) | 2022-11-11 | Apparent crack detection method and detection device for tunnel lining |
| CN113850741A (en) | 2021-12-28 | Image noise reduction method and device, electronic equipment and storage medium |
| CN114266957A (en) | 2022-04-01 | A super-resolution restoration method for hyperspectral images based on data augmentation with multiple degradation methods |
| CN116109535A (en) | 2023-05-12 | Image fusion method, device and computer readable storage medium |
| CN110175963B (en) | 2021-02-09 | Dual-purpose image enhancement method and device suitable for underwater image and atmospheric dark image |
| Baljozović et al. | 2013 | Mixed noise removal filter for multi‐channel images based on halfspace deepest location |
| Yamaguchi et al. | 2019 | Image demosaicking via chrominance images with parallel convolutional neural networks |
| Li et al. | 2018 | A cascaded algorithm for image quality assessment and image denoising based on CNN for image security and authorization |
| US8897378B2 (en) | 2014-11-25 | Selective perceptual masking via scale separation in the spatial and temporal domains using intrinsic images for use in data compression |
| CN114359103B (en) | 2024-04-12 | Hyperspectral image defogging method, hyperspectral image defogging device, computer product and storage medium |
| CN112258413B (en) | 2024-11-29 | Image enhancement method, electronic device and storage medium |
| CN116385898A (en) | 2023-07-04 | Satellite image processing method and system |
| CN113554615B (en) | 2023-08-22 | Image refinement processing method and device, electronic equipment and storage medium |
| CN110580694B (en) | 2022-03-08 | Quadratic Histogram Equalization Dynamic Image Method |
| Temel et al. | 2016 | BLeSS: Bio-inspired low-level spatiochromatic similarity assisted image quality assessment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 2024-07-02 | PB01 | Publication | |
| 2024-07-19 | SE01 | Entry into force of request for substantive examination | |
| 2024-07-19 | SE01 | Entry into force of request for substantive examination | |
| 2024-08-06 | GR01 | Patent grant | |
| 2024-08-06 | GR01 | Patent grant |