A method for constructing a high-resolution remote sensing interpretation sample dataset

Abstract

The present invention provides a method for constructing a high-resolution remote sensing interpretation sample dataset, comprising the following steps: S101, acquiring high-resolution remote sensing image data using satellite remote sensing technology; S102, performing preprocessing operations on the high-resolution image data; S103, performing feature extraction on the preprocessed high-resolution image data; S104, performing image segmentation processing based on the feature-extracted high-resolution image data; S105, performing image interpretation based on the segmented high-resolution image data and constructing a sample dataset; S106, performing sample quality inspection, sample quantity inspection, and sample accuracy inspection on the sample dataset; and S107, establishing a multi-user sample database based on PostgreSQL to store and manage the sample dataset. The present invention realizes the construction of a high-resolution remote sensing image sample dataset to improve the accuracy of automatic interpretation of high-resolution image data.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing image interpretation, and in particular to a method for constructing a high-resolution remote sensing interpretation sample data set. Background Art

[0002] Traditional remote sensing image survey methods rely on manual delineation of various image data from high-resolution remote sensing imagery. This method requires high-level expertise and technical skills from the delineator and is inefficient. Given the vast survey areas, massive amounts of data, and the real-world demands of dynamic monitoring, there is an urgent need to develop efficient information extraction methods based on high-resolution remote sensing imagery. However, traditional high-resolution remote sensing image automatic interpretation methods are weak in extracting and interpreting visual features. They generally require manual feature design based on extensive prior knowledge, and feature completeness cannot be guaranteed. Intelligent methods, such as deep learning, can automatically extract complex features from high-resolution remote sensing imagery and significantly improve the accuracy and efficiency of image interpretation. However, these methods rely on large-scale, high-quality sample datasets for training and optimization. However, the current sample dataset construction process still requires significant human and material investment, and data labeling is cumbersome and time-consuming, making it difficult to meet the rapidly evolving needs of remote sensing intelligent interpretation. Summary of the Invention

[0003] In view of this, an object of the present invention is to provide a method for constructing a high-resolution remote sensing interpretation sample dataset to solve or at least partially solve the above-mentioned problems existing in the prior art.

[0004] To achieve the above-mentioned object, the present invention provides a method for constructing a high-resolution remote sensing interpretation sample dataset, the method comprising the following steps:

[0005] S101. Use satellite remote sensing technology to obtain high-resolution remote sensing image data;

[0006] S102, performing pre-processing operations on high-resolution image data;

[0007] S103, performing feature extraction on the high-resolution image data after preprocessing;

[0008] S104, performing image segmentation processing based on the high-resolution image data after feature extraction;

[0009] S105, performing image interpretation based on the high-resolution image data after image segmentation processing, and constructing a sample data set;

[0010] S106, performing sample quality inspection, sample quantity inspection, and sample accuracy inspection on the sample data set;

[0011] S107. Establish a multi-user sample database based on PostgreSQL to store and manage the sample data set.

[0012] Furthermore, the pre-processing operation includes the following steps:

[0013] S31, radiometric calibration: converting the brightness grayscale value of the acquired high-resolution remote sensing image data into radiometric brightness value;

[0014] S32, atmospheric correction: convert the above-mentioned radiance value into the actual reflectivity of the surface;

[0015] S33, geometric correction: eliminate the distortion error of the high-resolution remote sensing image data after S33 preprocessing, perform geographic coordinate positioning on the high-resolution remote sensing image data, and obtain the real coordinate information;

[0016] S34, registration and mosaicking: Based on steps S31-S32, image registration and image mosaicking are performed on the high-resolution remote sensing image data.

[0017] Furthermore, feature extraction is performed on the pre-processed high-resolution image data, including:

[0018] Use image mean, image variance and entropy to extract features from high-resolution image data;

[0019] The image average value is used to measure the average brightness of the image data texture;

[0020] The image variance is used to measure the average contrast of the image data texture;

[0021] The entropy is used to describe the measure of randomness of image data.

[0022] Furthermore, the image segmentation process includes the following steps:

[0023] S41, performing image segmentation processing based on the features of the high-resolution image data to obtain a preliminary image segmentation result;

[0024] S42, optimizing the preliminary segmentation results based on the features of the high-resolution image data;

[0025] S43. Based on step S42, perform spot feature extraction on the high-resolution image data after optimizing the segmentation result.

[0026] Furthermore, the image interpretation adopts a method combining deep learning and expert interpretation. The deep learning method extracts the boundaries of high-resolution image objects based on object-oriented segmentation and generates an automatic object recognition probability map.

[0027] The expert interpretation method manually interprets ground objects with low recognition probability based on the results of the deep learning method, and ultimately achieves accurate classification of ground object boundaries and types.

[0028] Furthermore, the sample quality inspection includes radiation quality inspection, geometric quality inspection, and information quality inspection;

[0029] The sample quantity test includes overall quantity test, category quantity test, and scale sample quantity test;

[0030] The sample accuracy test includes position accuracy test, shape accuracy test, category accuracy test and overall accuracy test.

[0031] Furthermore, the overall accuracy test includes:

[0032]

[0033] Among them, OA is the overall accuracy, N is the total number of categories, i is the category, TP i is the number of correctly classified categories i, C i is the true number of category i.

[0034] Furthermore, the multi-user sample database is used for multi-user registration and login, multi-user upload and download, multi-user query and retrieval, multi-user evaluation and feedback, and multi-user update and maintenance.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention improves the quality and availability of high-resolution image data by preprocessing the high-resolution image data; performs feature extraction on the preprocessed high-resolution image data and performs image segmentation based on the features of the high-resolution image data, thereby accurately identifying the features of the high-resolution image data; performs image interpretation on the high-resolution image data after image segmentation processing, thereby achieving accurate classification of the high-resolution image data and improving the accuracy of automatic interpretation of the high-resolution image data, and constructing a sample data set on this basis can save a lot of manpower; verifies the sample data set to ensure the accuracy and availability of the sample, and finally establishes a multi-user sample database to facilitate the storage and management of the sample data set. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only preferred embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 A flowchart of a method for constructing a high-resolution remote sensing interpretation sample dataset provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The principles and features of the present invention are described below with reference to the accompanying drawings. The enumerated embodiments are only used to explain the present invention and are not used to limit the scope of the present invention.

[0040] This embodiment provides a method for constructing a high-resolution remote sensing interpretation sample dataset, the method comprising the following steps:

[0041] like Figure 1 As shown, the present invention provides a method for constructing a high-resolution remote sensing interpretation sample dataset, the method comprising the following steps:

[0042] S101. Use satellite remote sensing technology to obtain high-resolution remote sensing image data.

[0043] S102: Preprocess the high-resolution image data. The preprocessing operation includes the following steps:

[0044] S31. Radiometric calibration: Convert the brightness grayscale value of the acquired high-resolution remote sensing image data into radiometric brightness value, or convert the recorded DN value (pixel brightness value of high-resolution remote sensing image data) into apparent reflectance. The conversion between DN value and radiometric brightness value is:

[0045] L λ =k·DN+c

[0046] Among them, L λ is the radiance value of band λ, k and c are gain and offset respectively. The conversion between radiance value and apparent reflectance is:

[0047]

[0048] Among them, ρ λ is the atmospheric apparent reflectivity, d is the average distance between the sun and the earth, ESUN λ is the solar irradiance and θ is the solar altitude angle.

[0049] S32. Atmospheric correction: The process of converting the above-mentioned radiation brightness value into the actual surface reflectivity, eliminating the radiation error caused by atmospheric images, and reflecting the true surface reflectivity of the surface.

[0050] S33, geometric correction: eliminate the distortion error of the high-resolution remote sensing image data after S33 preprocessing, perform geographic coordinate positioning on the high-resolution remote sensing image data, and obtain the real coordinate information;

[0051] S34, registration and mosaicking: Based on steps S31-S32, image registration and mosaicking are performed on the high-resolution remote sensing image data. The image registration is expressed as follows:

[0052] I2(x,y)=g(I1(f(x,y)))

[0053] Where I1(x, y) and I2(x, y) are the brightness values ​​(or other metric values) of the two images, g is a one-dimensional brightness or other metric value transformation, and f is a two-dimensional spatial coordinate transformation (such as an affine transformation). The image mosaicking uses the maximum brightness value of the two images to be mosaicked as the brightness value of the pixel point in the overlapping area. Let the number of rows in the overlapping area be x, y. The overlapping part of the two images is from row Z to row x+z-1, which is expressed as follows:

[0054] g(i,j)=max[g v (i+Z-1,j),g y (i,j)]

[0055] i=(1,2,...,x)

[0056] Among them, g(i,j) is the brightness value of the overlapped area after brightness adjustment, i is the number of rows in the overlapped area, j is the number of columns in the overlapped area, and g v (i,j) and g y (i, j) represents the brightness value of the v and y images respectively, and the overlapping part of the v image is from row 1 to row x.

[0057] S103, performing feature extraction on the high-resolution image data after preprocessing, specifically including:

[0058] After completing the preprocessing operation, the image mean, image variance, and entropy are used to extract features from the high-resolution image data, as shown below:

[0059] (1) Image average: used to measure the average brightness of image data texture, specifically expressed as follows:

[0060]

[0061] Among them, m is the image average, L is the total number of gray levels, z i is the i-th gray level, p(z i ) is z i The probability of gray levels in the image data;

[0062] (2) Image variance: used to measure the average contrast of image data texture, specifically expressed as follows:

[0063]

[0064] Where, σ is the image variance;

[0065] (3) Entropy: A measure used to describe the randomness of image data. A larger value indicates greater randomness and a greater amount of information. Conversely, a smaller value indicates greater certainty and a smaller amount of information. The specific expression is as follows:

[0066]

[0067] Where e is entropy.

[0068] S104: Perform image segmentation based on the high-resolution image data after feature extraction, specifically including:

[0069] S41. Perform image segmentation processing based on the features of the high-resolution image data to obtain a preliminary image segmentation result. The high-resolution image data after the image segmentation processing contains at least 2 objects.

[0070] S42. Optimize the preliminary segmentation results based on the features of the high-resolution image data. The optimized image segmentation process is expressed as follows:

[0071] F=g+MI·α

[0072] Among them, F is the optimized image segmentation processing, g is the smooth boundary, M is the hole filling coefficient, I is the support vector machine, and α is the patch clustering condition.

[0073] S43: Based on step S42, the high-resolution image data after the optimized segmentation result is subjected to spot feature extraction. According to the feature changes of different spots, abnormal information in the spots is identified, which is expressed as follows:

[0074]

[0075] Among them, Q is the feature information of the spot, β is the filtering parameter, and S is the number of pixels.

[0076] S105: Perform image interpretation based on the high-resolution image data after image segmentation processing and construct a sample data set, specifically including:

[0077] The image interpretation method uses a combination of deep learning and expert interpretation. The deep learning method extracts the boundaries of high-resolution image objects based on object-oriented segmentation and generates a probability map for automatic object recognition, automatically mapping the deep learning object recognition results to the high-resolution image data. The expert interpretation method manually interprets objects with low recognition probability based on the results of the deep learning method. Ultimately, accurate classification of object boundaries and types is achieved. The combination of deep learning and expert interpretation can automatically learn the characteristics of high-resolution image data, improve the accuracy of automatic interpretation of high-resolution image data, and finally, construct a data set based on the accurate classification results of object boundaries and types.

[0078] The method of combining deep learning and expert interpretation includes:

[0079] (1) Automatic segmentation of high-resolution image data based on object-oriented approach;

[0080] (2) Identify the objects on the segmentation results based on deep learning methods and generate an automatic recognition probability map;

[0081] (3) Using expert interpretation methods to perform manual visual interpretation and identification of ground objects with low recognition probability, more accurate land classification information can be obtained;

[0082] (4) Edit and extract the final interpretation results based on land type information.

[0083] S106. Perform sample quality inspection, sample quantity inspection, and sample accuracy inspection on the sample data set, specifically including:

[0084] (1) Sample quality inspection includes radiation quality inspection, geometric quality inspection, and information quality inspection;

[0085] Radiometric quality inspection: Check whether high-resolution image data contains interference factors such as clouds, fog, shadows, and clutter, and whether pre-processing operations such as radiometric calibration and atmospheric correction have been performed;

[0086] Geometric quality inspection: Check whether the high-resolution image data has errors such as distortion, misalignment, and overlap, and whether pre-processing operations such as geometric correction and registration mosaicking have been performed;

[0087] Information quality inspection: Check whether the high-resolution image data has sufficient resolution, number of bands, dynamic range and other parameters.

[0088] (2) Sample size test includes overall size test, category size test, and scale sample size test;

[0089] Overall quantity test: check whether the total number of samples reaches the expected size;

[0090] Category quantity test: Check whether the number of samples in each category is balanced and whether it can reflect the diversity and differences of high-resolution image data;

[0091] Scale sample number test: Check whether the sample numbers at different scales are reasonable and whether they can reflect the hierarchy and details of high-resolution image data.

[0092] (3) Sample accuracy test includes position accuracy test, shape accuracy test, category accuracy test, and overall accuracy test;

[0093] Position accuracy test: Check whether the sample is spatially consistent with the actual situation and whether it is consistent with other data sources (such as maps, GPS, etc.);

[0094] Shape accuracy test: Check whether the sample is consistent with the actual situation in terms of morphology and whether it is consistent with other data sources (such as texture, morphology, etc.);

[0095] Category accuracy test: Check whether the sample is consistent with other data sources (such as expert knowledge, rule base, etc.).

[0096] Overall accuracy test: refers to the ratio of the number of pixels with correctly detected shadows / shadow semantics (i.e., land cover information inside the shadow) to the number of categories set overall. It is mainly used to evaluate the overall accuracy of the sample dataset based on confusion evidence, and is expressed as follows:

[0097]

[0098] Among them, OA is the overall accuracy, N is the total number of categories, i is the category, TP i is the number of correctly classified categories i, C i is the true number of category i.

[0099] S107: Establish a multi-user sample database based on PostgreSQL to store and manage sample data sets. The multi-user sample database includes the following functions:

[0100] It supports multi-user registration and login to implement user identity authentication and permission control; supports multi-user upload and download to implement sample data set sharing and communication among users; supports multi-user query and retrieval to enable users to quickly query and filter sample data sets; supports multi-user evaluation and feedback to enable users to evaluate the quality of sample data sets and provide improvement suggestions; supports multi-user update and maintenance to enable users to add, delete, modify, and control the version of sample data sets.

[0101] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for constructing a high-resolution remote sensing interpretation sample dataset, characterized in that: The method comprises the following steps: S101. Use satellite remote sensing technology to obtain high-resolution remote sensing image data; S102: Preprocess the high-resolution image data. The preprocessing operation includes the following steps: S31, radiometric calibration: converting the brightness grayscale value of the acquired high-resolution remote sensing image data into radiometric brightness value; S32, atmospheric correction: converting the radiance value into actual surface reflectivity; S33, geometric correction: eliminate the distortion error of the high-resolution remote sensing image data after S32 preprocessing, perform geographic coordinate positioning on the high-resolution remote sensing image data, and obtain the real coordinate information; S34, registration and mosaicking: Based on steps S31-S32, image registration and image mosaicking are performed on the high-resolution remote sensing image data; S103, performing feature extraction on the high-resolution image data after preprocessing; S104, performing image segmentation processing based on the high-resolution image data after feature extraction; S105. Performing image interpretation based on the high-resolution image data after image segmentation processing and constructing a sample data set. The image interpretation adopts a method that combines deep learning and expert interpretation. The deep learning method extracts the boundaries of objects in the high-resolution image based on object-oriented segmentation and generates an automatic object recognition probability map. The expert interpretation method manually interprets objects with low recognition probability based on the results of the deep learning method, ultimately achieving accurate classification of object boundaries and types. S106: Perform sample quality inspection, sample quantity inspection, and sample accuracy inspection on the sample data set. The sample quality inspection includes radiation quality inspection, geometric quality inspection, and information quality inspection; the sample quantity inspection includes overall quantity inspection, category quantity inspection, and scale sample quantity inspection; the sample accuracy inspection includes position accuracy inspection, shape accuracy inspection, category accuracy inspection, and overall accuracy inspection; and the overall accuracy inspection includes: Among them, OA is the overall accuracy, N is the total number of categories, i is the category, TP i is the number of correctly classified categories i, C i is the true number of category i; S107. Establish a multi-user sample database based on PostgreSQL to store and manage the sample data set.

2. The method for constructing a high-resolution remote sensing interpretation sample dataset according to claim 1, characterized in that: Perform feature extraction on pre-processed high-resolution image data, including: Use image mean, image variance and entropy to extract features from high-resolution image data; The image average value is used to measure the average brightness of the image data texture; The image variance is used to measure the average contrast of the image data texture; The entropy is used to describe the measure of randomness of image data.

3. The method for constructing a high-resolution remote sensing interpretation sample dataset according to claim 1, characterized in that: In step S104, the image segmentation process includes the following steps: S41, performing image segmentation processing based on the features of the high-resolution image data to obtain a preliminary image segmentation result; S42, optimizing the preliminary segmentation results based on the features of the high-resolution image data; S43. Based on step S42, perform spot feature extraction on the high-resolution image data after optimizing the segmentation result.

4. The method for constructing a high-resolution remote sensing interpretation sample dataset according to claim 1, characterized in that: In step S107, the multi-user sample database is used for multi-user registration and login, multi-user upload and download, multi-user query and retrieval, multi-user evaluation and feedback, and multi-user update and maintenance.

Images