CN112883892A - Soil type remote sensing classification identification method, device, equipment and storage medium - Google Patents
Soil type remote sensing classification identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112883892A CN112883892A CN202110235195.8A CN202110235195A CN112883892A CN 112883892 A CN112883892 A CN 112883892A CN 202110235195 A CN202110235195 A CN 202110235195A CN 112883892 A CN112883892 A CN 112883892A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- classification
- soil
- preset
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Abstract
The invention is suitable for the technical field of computers, and provides a soil type remote sensing classification identification method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring a remote sensing image of soil to be identified; extracting texture features of the remote sensing image under a preset scale; fusing the texture features with the remote sensing image to generate a remote sensing classified image fused with the texture features; and processing the remote sensing classified image to determine a classification recognition result of the soil to be recognized. The soil type remote sensing classification and identification method provided by the invention extracts the textural features which can be used for describing the soil spatial structure and geometric form information in the remote sensing image, fuses with the remote sensing image, and utilizes abundant spatial structure and geometric information contained in the textural features to assist classification and identification, thereby overcoming the problem of insufficient spectral information in the prior art which is caused by the fact that spectral features are used for classification and identification only, improving the classification precision and further ensuring the remote sensing classification and identification effect of the soil type.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a method, a device, equipment and a storage medium for remote sensing classification and identification of soil types.
Background
The spatial distribution of soil types is an important basis for precision agriculture and land resource management. Traditional soil type mapping is mainly completed through field investigation and indoor transfer drawing, and is widely applied for many years. However, the traditional method is long in period, high in cost, complex in procedure, strong in subjectivity and low in final soil map precision. Digital mapping techniques are proposed for fast and convenient updating of soil data. With the development of remote sensing technology, obtaining soil attribute and soil type data by using remote sensing images has become a new way and method for digital soil mapping.
However, most of the variable indexes extracted by the remote sensing technology reflect the spectral characteristics of the soil type, and for the soil types with the same spectral characteristics, the spectral characteristics are difficult to identify respectively, so that the existing remote sensing technology is low in classification precision and poor in classification effect.
Therefore, the existing remote sensing technology for classifying and identifying the soil types also has the technical problems of low classification precision and poor classification effect.
Disclosure of Invention
The embodiment of the invention aims to provide a soil type remote sensing classification and identification method, and aims to solve the technical problems of low classification precision and poor classification effect of the existing remote sensing technology for classifying and identifying soil types.
The embodiment of the invention is realized in such a way that a soil type remote sensing classification and identification method comprises the following steps:
acquiring a remote sensing image of soil to be identified;
extracting the texture features of the remote sensing image under a preset scale according to a preset texture feature extraction rule; the texture features at least comprise one of mean value, variance, homogeneity, contrast, similarity, information entropy, second moment and correlation;
fusing the texture features with the remote sensing image to generate a remote sensing classified image fused with the texture features;
and processing the remote sensing classified image according to a preset classification and identification rule to determine a classification and identification result of the soil to be identified.
Another object of an embodiment of the present invention is to provide a soil type remote sensing classification and identification device, including:
the remote sensing image acquisition unit is used for acquiring a remote sensing image of the soil to be identified;
the texture feature extraction unit is used for extracting the texture features of the remote sensing image under the preset scale according to a preset texture feature extraction rule; the texture features at least comprise one of mean value, variance, homogeneity, contrast, similarity, information entropy, second moment and correlation;
the fusion unit is used for fusing the texture features with the remote sensing image to generate a remote sensing classified image fused with the texture features;
a classification recognition unit for processing the remote sensing classification image according to a preset classification recognition rule to determine a classification recognition result of the soil to be recognized
It is a further object of an embodiment of the present invention to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to execute the steps of the remote sensing classification and identification method for soil types as described above.
It is a further object of an embodiment of the present invention to provide a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, causes the processor to execute the steps of the remote sensing classification and identification method for soil types as described above.
According to the soil type remote sensing classification and identification method provided by the invention, the textural features which can be used for describing the soil spatial structure and geometric form information in the remote sensing image are extracted, and are fused with the original spectral features contained in the remote sensing image to obtain the remote sensing classification image fused with the textural features, so that in the process of classifying and identifying the remote sensing classification image, the classification and identification can be carried out by utilizing the abundant spatial structure and geometric information contained in the textural features, the problem of insufficient spectral information in the prior art that the classification and identification are carried out by simply using the spectral features is solved, the classification precision is improved, and the remote sensing classification and identification effect of the soil type is ensured.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for remote sensing classification and identification of soil types according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating steps of another soil type remote sensing classification and identification method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating steps of another soil type remote sensing classification and identification method according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating steps of a further method for remote sensing classification and identification of soil types according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating steps of a further method for remote sensing classification and identification of soil types according to an embodiment of the present invention;
FIGS. 6(a) to 6(c) are schematic diagrams of classification and identification effects obtained by three different soil type remote sensing classification and identification methods;
fig. 7 is a schematic structural diagram of a soil type remote sensing classification and identification device according to an embodiment of the present invention;
fig. 8 is an internal structural diagram of a computer device for executing the remote sensing classification and identification method for soil types according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Fig. 1 is a flowchart illustrating steps of a method for remote sensing classification and identification of soil types according to an embodiment of the present invention, which specifically includes the following steps:
and S102, acquiring a remote sensing image of the soil to be identified.
In the embodiment of the present invention, the remote sensing image is generally composed of a panchromatic band (band 8: 0.50-0.68 m) with a resolution of 15 m and 10 multispectral bands with a resolution of 30m, and the first seven visible spectrum bands are usually selected as research objects for simplifying operations.
And step S104, extracting the texture features of the remote sensing image under the preset scale according to a preset texture feature extraction rule.
In an embodiment of the present invention, the texture feature is a feature expressing spatial structure and geometric information, and the texture feature includes at least one of a mean, a variance, homogeneity, contrast, similarity, information entropy, a second moment, and correlation.
As a preferred embodiment of the present invention, the texture feature is referred to as information entropy. And the information entropy is selected as the texture feature, so that the subsequent classification effect is better.
In the embodiments of the present invention, there are many methods for extracting texture features at a predetermined scale, and the present invention is not specifically described herein, and a preferred implementation is described with reference to fig. 4 and the description thereof.
And S106, fusing the texture features and the remote sensing image to generate a remote sensing classified image fused with the texture features.
In the embodiment of the invention, the textural features and the remote sensing image are fused to generate the remote sensing classified image fused with the textural features, wherein the textural features describe the spatial structure and the geometric form information of the soil, and the remote sensing image contains the spectral information of the soil, so that the remote sensing classified image fused with the textural features contains the spatial structure and the geometric form information of the soil and the spectral information of the soil.
And S108, processing the remote sensing classified image according to a preset classification and recognition rule to determine a classification and recognition result of the soil to be recognized.
In the embodiment of the invention, the remote sensing classification images containing the spatial structure, the geometric form information and the spectral information of the soil are further classified and recognized, so that the types of all the pieces of soil in the area can be determined according to the remote sensing classification images, and the classification and recognition results of the soil to be recognized are obtained.
According to the soil type remote sensing classification and identification method provided by the invention, the textural features which can be used for describing the soil spatial structure and geometric form information in the remote sensing image are extracted, and are fused with the original spectral features contained in the remote sensing image to obtain the remote sensing classification image fused with the textural features, so that in the process of classifying and identifying the remote sensing classification image, the classification and identification can be carried out by utilizing the abundant spatial structure and geometric information contained in the textural features, the problem of insufficient spectral information in the prior art that the classification and identification are carried out by simply using the spectral features is solved, the classification precision is improved, and the remote sensing classification and identification effect of the soil type is ensured.
As shown in fig. 2, a flowchart of steps of another soil type remote sensing classification and identification method provided by the embodiment of the present invention is described in detail as follows.
In the embodiment of the present invention, the difference from the step flow chart of the remote sensing classification and identification method for soil types shown in fig. 1 is that the step S104 specifically is:
and S204, extracting the texture features of the remote sensing image under a plurality of preset scales according to a preset texture feature extraction rule.
In the embodiment of the invention, the spatial structure and the geometric form information contained in different texture features under different scales are considered to be different, so that the spatial structure and the geometric form information contained in different extracted texture features under a specific scale can be comprehensively ensured to be the most by acquiring the texture features under multiple scales, and the subsequent classification effect is further improved.
As a preferred embodiment of the present invention, the predetermined scale is at least one of a 5 × 5 scale, a 15 × 15 scale, a 21 × 21 scale and a 23 × 23 scale, and the 5 × 5 scale, the 15 × 15 scale, the 21 × 21 scale and the 23 × 23 scale are optimally selected, at which the texture features achieve an optimal classification effect for different soil types.
As shown in fig. 3, a flowchart of steps of another soil type remote sensing classification and identification method provided by the embodiment of the present invention is described in detail as follows.
In the embodiment of the present invention, the difference from the step flow chart of the remote sensing classification and identification method for soil types shown in fig. 1 is that after step S102, the method further includes:
and step S302, performing radiation correction and geometric correction processing on the remote sensing image to generate a processed remote sensing image.
In the embodiment of the present invention, the radiation correction and the geometric correction may be understood as preprocessing of the remote sensing image, which may also improve the subsequent classification effect, and the present invention is not specifically described.
Fig. 4 is a flowchart illustrating steps of a further remote sensing classification and identification method for soil types according to an embodiment of the present invention, which is described in detail below.
In the embodiment of the present invention, the difference from the step flow chart of the remote sensing classification and identification method for soil types shown in fig. 1 is that the step S104 specifically is:
and S402, extracting texture features of the remote sensing image under a preset scale based on the gray level co-occurrence matrix.
In the embodiment of the invention, the texture features are extracted through the gray level co-occurrence matrix, specifically, the gray level co-occurrence matrix is a list of relative frequencies of pixel pairs which are calculated based on the space co-occurrence matrix and are separated by a certain distance in a given direction, the occurrence times of different pixel pairs are recorded, and meanwhile, the relative positions and the space information of the pixels are also recorded, so that the extracted texture features have better effect.
As shown in fig. 5, a flowchart of steps of a soil type remote sensing classification and identification method provided by an embodiment of the present invention is described in detail as follows.
In the embodiment of the present invention, the difference from the step flow chart of the remote sensing classification and identification method for soil types shown in fig. 1 is that the step S108 specifically includes:
and S502, processing the remote sensing classified image based on a maximum likelihood classification method to determine a classification recognition result of the soil to be recognized.
In the embodiment of the invention, the classification method uses a maximum likelihood classification method, and the classification method can classify previously unidentified pixels into a class with the highest similarity probability in all classes according to statistical information such as the mean value, standard deviation and the like of soil types in remote sensing data.
In order to further understand the technical solution provided by the present invention, the principle of the soil type remote sensing classification and identification method provided by the present invention will be described below with reference to a specific experimental process, which is detailed below.
1. Determining the study area:
considering that the flatness city is a typical plain hilly area of the Jiaodong peninsula, the soil types are rich, and better conditions are provided for soil classification research. Therefore, we selected the eastern province of Shandong province as the research area. It is located between 36 degrees 28 '15' -37 degrees 02 '46' of north latitude, between 119 degrees 31 '30' -120 degrees 19 '13' of east longitude, and total area 3175.63 km2, which is the largest county-level city in Shandong province. The city of the flatness belongs to continental climate in a warm zone east Asia semi-humid monsoon region, and the climate in the interior is clear in four seasons. The average annual air temperature is 11.9 ℃, the average annual precipitation is 680 mm, and the sunshine hours are about 2700 hours. Its topography is generally north high, south low. The research area has thirteen soil subclasses from the mountain area to the plain, which are respectively eluviated brown soil, coastal saline soil, neutral stone soil, neutral coarse bone soil, brown soil, moist brown soil, moist soil, moist soil and sand ginger black soil (classified according to the occurrence of Chinese soil). The three types of soil are sand ginger black soil, brown soil and moist soil, and have the largest area and the most extensive distribution.
2. Collecting and preprocessing remote sensing data:
to cover the entire study area, 2 shots of Landsat8 OLI satellite images were acquired. The image consists of a 15 m resolution panchromatic band (band 8: 0.50-0.68 m) and 10 30m resolution multispectral bands. To simplify the calculation, the first seven visible spectral bands were selected for study.
And performing radiation correction and geometric correction on the acquired Landsat8 OLI image data, and then splicing the two images through histogram matching. Finally, an image in a research area with the spatial resolution of 30m, namely a remote sensing image of the soil to be identified, is obtained through ArcGIS10.2 cutting.
3. Extracting texture features of remote sensing images
And extracting texture features by selecting a gray level co-occurrence matrix method. The gray level co-occurrence matrix is a list of relative frequencies of pixel pairs separated by a certain distance in a given direction, records the occurrence times of different pixel pairs, and simultaneously considers the relative position and spatial information of the pixels.
To avoid the repeatability of the represented information between texture features, the following texture features are considered: mean, variance, homogeneity, contrast, similarity, entropy, second moment, and correlation. Different texture features reflect different image information, so that proper texture features need to be selected according to the actual classification needs to ensure that the texture features involved in the classification can effectively improve the separability of the soil type. And processing the extracted 8 texture features to respectively generate respective texture mean value curves, then performing descriptive statistical analysis, and selecting the texture features with higher separability for each soil type by comparing the curve characteristics with the descriptive statistical features. The remaining texture features have a classification effect, but the effect is weaker than homogeneity, information entropy, second moment and correlation. Therefore, the subsequent experiment adopts the information entropy as the texture feature to perform fusion classification.
4. Determining window size for optimal scale information entropy for soil type
12 different windows (odd windows from 3 x 3 to 25 x 25) are used to extract texture features, i.e. information entropy. Each window size will be fused with the spectral data to create a new image data.
In order to quantitatively research the gradeability between soil types under the texture characteristics of different window sizes, a Jeffries-Matusita distance method is adopted to carry out gradeability analysis on the training samples. The J-M distance is a measure of the statistical separability between class pairs, and the average difference between the density functions of the two classes is calculated. The method calculates the degree of separability between two classes in a band combination based on a set of statistical features such as mean, variance and covariance matrices. The J-M distance ranges from 0 to 2, with larger values indicating higher separability between soil types. If this value is between 1.9 and 2, there is better separability between the two classes, and the resulting classes will be accurately separated. If the value is between 1.7 and 1.9, the separability between the two classes is good; if less than 1.7, the separability is poor.
And obtaining a J-M analysis result by counting the separability of the soil training samples in the spectral data and the texture characteristic images of different windows. The average separability of each soil type gradually increases with the increase of the texture feature window, but the increase gradually decreases with the increase of the window. When the information entropy window is 21 × 21, the average divisibility reaches the maximum value respectively, and remains unchanged. On the basis, a window with the texture feature information entropy of 21 × 21 is selected as the optimal single-scale texture feature for soil classification.
Although the overall accuracy and the Kappa coefficient respectively reach the highest values when the windows of the texture features are respectively 21 × 21, each soil type cannot reach the highest accuracy at the same time, and therefore, the optimal information entropy extraction window of each soil type is determined by using a posterior probability method, namely, the optimal extraction window is determined by performing the soil type identification result through the information entropies of different windows. The result shows that when the classification accuracy of each soil type reaches the highest accuracy, the corresponding window sizes are respectively 5 × 5 (moisture soil), 15 × 15 (sand ginger black soil, brown soil), 21 × 21 (wet moisture soil, brown soil) and 23 × 23 (brown soil), so that the multi-scale windows of the information entropy characteristic parameter combination are 5 × 5, 15 × 15, 21 × 21 and 23 × 23 scales, but the number of the input variables is obviously increased by considering the number of the added texture characteristics, so that the calculation time is increased, and in practice, any appropriate scale can be selected from the scales according to the actual situation to extract the texture characteristics, so as to ensure the calculation effect and the calculation efficiency.
5. Optimal window fused multi-scale texture feature parameter soil remote sensing classification
And selecting the information entropies extracted by 5 × 5, 15 × 15, 21 × 21 and 23 × 23 windows, combining the information entropies, and fusing new remote sensing data to classify the soil. And classifying the previously unidentified pixels into a class with the highest similarity probability in all classes according to a maximum likelihood classification method, namely according to statistical information such as the mean value, standard deviation and the like of the soil type in the remote sensing data.
In order to embody the difference of the soil type remote sensing classification and identification method provided by the invention relative to the prior art, the classification and identification effect schematic diagrams obtained by adopting the remote sensing image spectral data single classification, the single-scale texture feature and remote sensing image spectral data fusion classification and the multi-scale texture feature and remote sensing image spectral data fusion classification are drawn as follows, and are particularly shown in fig. 6(a) to 6 (c).
Fig. 6(a) is a schematic diagram of an effect of individual classification of remote sensing image spectral data, fig. 6(b) is a schematic diagram of an effect of fusion classification of single-scale texture features and remote sensing image spectral data, and fig. 6(c) is a schematic diagram of an effect of fusion classification of multi-scale texture features and remote sensing image spectral data.
Comparing the classified effect diagram with the real data, it can be found that the individual classification accuracy based on the remote sensing image spectrum data is 40.99%, and high-quality results cannot be obtained. In the process of fusion and classification of the single-scale textural features and the remote sensing image spectral data, the selected single-scale window is 21 multiplied by 21, the textural features select information entropy, and the classification precision is 63.46% at the moment, which is 22.47% higher than the classification precision of the spectral data, because the textural features are fused into the spectral data, the abundant spatial structure and geometric feature information of the textural features can be utilized, the problem of insufficient image spectral information is solved, and the classification precision of soil types is improved. Furthermore, in the process of fusion and classification of the multi-scale textural features and the remote sensing image spectral data, the selected multi-scale is 5 × 5, 15 × 15, 21 × 21 and 23 × 23, the textural features also select information entropy, and the classification precision reaches 74.32%, which is 10.96% higher than the information entropy classification result extracted by the optimal single-scale window, because the multi-scale textural features are fused to identify the soil types with the same spectral features but different properties, therefore, the multi-scale fusion method of the optimal textural feature parameters of each soil type can improve the classification precision of the remote sensing image better than the multi-scale fusion method of the optimal single-scale textural feature parameters of each soil type.
As shown in fig. 7, a schematic structural diagram of a soil type remote sensing classification and identification device provided in an embodiment of the present invention specifically includes the following units:
and the remote sensing image acquisition unit 710 is used for acquiring a remote sensing image of the soil to be identified.
In the embodiment of the present invention, the remote sensing image is generally composed of a panchromatic band (band 8: 0.50-0.68 m) with a resolution of 15 m and 10 multispectral bands with a resolution of 30m, and the first seven visible spectrum bands are usually selected as research objects for simplifying operations.
And the textural feature extraction unit 720 is configured to extract textural features of the remote sensing image in a preset scale according to a preset textural feature extraction rule.
In an embodiment of the present invention, the texture feature is a feature expressing spatial structure and geometric information, and the texture feature includes at least one of a mean, a variance, homogeneity, contrast, similarity, information entropy, a second moment, and correlation.
As a preferred embodiment of the present invention, the texture feature is referred to as information entropy. And the information entropy is selected as the texture feature, so that the subsequent classification effect is better.
In the embodiments of the present invention, there are many methods for extracting texture features at a predetermined scale, and the present invention is not specifically described herein, and a preferred implementation is described with reference to fig. 4 and the description thereof.
And the fusion unit 730 is used for fusing the texture features and the remote sensing image to generate a remote sensing classified image fused with the texture features.
In the embodiment of the invention, the textural features and the remote sensing image are fused to generate the remote sensing classified image fused with the textural features, wherein the textural features describe the spatial structure and the geometric form information of the soil, and the remote sensing image contains the spectral information of the soil, so that the remote sensing classified image fused with the textural features contains the spatial structure and the geometric form information of the soil and the spectral information of the soil.
And the classification recognition unit 740 is configured to process the remote sensing classification image according to a preset classification recognition rule to determine a classification recognition result of the soil to be recognized.
In the embodiment of the invention, the remote sensing classification images containing the spatial structure, the geometric form information and the spectral information of the soil are further classified and recognized, so that the types of all the pieces of soil in the area can be determined according to the remote sensing classification images, and the classification and recognition results of the soil to be recognized are obtained.
According to the soil type remote sensing classification and identification device provided by the invention, the textural features which can be used for describing the soil spatial structure and geometric form information in the remote sensing image are extracted and are fused with the original spectral features contained in the remote sensing image to obtain the remote sensing classification image fused with the textural features, so that in the process of classifying and identifying the remote sensing classification image, the classification and identification can be carried out by utilizing the abundant spatial structure and geometric information contained in the textural features, the problem of insufficient spectral information in the prior art that the classification and identification are carried out by simply using the spectral features is solved, the classification precision is improved, and the remote sensing classification and identification effect of the soil type is ensured.
FIG. 8 is a diagram illustrating an internal structure of a computer device in one embodiment. As shown in fig. 8, the computer apparatus includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and also stores a computer program, and when the computer program is executed by the processor, the computer program can enable the processor to realize the remote sensing classification and identification method of the soil type. The internal memory may also have a computer program stored therein, which when executed by the processor, causes the processor to perform a method for remote sensing classification and identification of soil types. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the remote sensing classification and identification device for soil types provided by the present application can be implemented in the form of a computer program, and the computer program can be run on a computer device as shown in fig. 8. The memory of the computer device may store various program modules constituting the soil type remote sensing classification and identification device, such as the remote sensing image acquisition unit 710, the texture feature extraction unit 720, the fusion unit 730, and the classification and identification unit 740 shown in fig. 7. The computer program formed by the program modules enables the processor to execute the steps of the remote sensing classification and identification method for soil types of the embodiments of the application described in the specification.
For example, the computer device shown in fig. 8 may execute step S102 through the remote sensing image acquisition unit 710 in the remote sensing classification and identification device for soil type shown in fig. 7; the computer device may perform step S104 by the texture feature extraction unit 720; the computer device may perform step S106 through the fusion unit 730.
In one embodiment, a computer device is proposed, the computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring a remote sensing image of soil to be identified;
extracting the texture features of the remote sensing image under a preset scale according to a preset texture feature extraction rule; the texture features at least comprise one of mean value, variance, homogeneity, contrast, similarity, information entropy, second moment and correlation;
fusing the texture features with the remote sensing image to generate a remote sensing classified image fused with the texture features;
and processing the remote sensing classified image according to a preset classification and identification rule to determine a classification and identification result of the soil to be identified.
In one embodiment, a computer readable storage medium is provided, having a computer program stored thereon, which, when executed by a processor, causes the processor to perform the steps of:
acquiring a remote sensing image of soil to be identified;
extracting the texture features of the remote sensing image under a preset scale according to a preset texture feature extraction rule; the texture features at least comprise one of mean value, variance, homogeneity, contrast, similarity, information entropy, second moment and correlation;
fusing the texture features with the remote sensing image to generate a remote sensing classified image fused with the texture features;
and processing the remote sensing classified image according to a preset classification and identification rule to determine a classification and identification result of the soil to be identified.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A soil type remote sensing classification and identification method is characterized by comprising the following steps:
acquiring a remote sensing image of soil to be identified;
extracting the texture features of the remote sensing image under a preset scale according to a preset texture feature extraction rule; the texture features at least comprise one of mean value, variance, homogeneity, contrast, similarity, information entropy, second moment and correlation;
fusing the texture features with the remote sensing image to generate a remote sensing classified image fused with the texture features;
and processing the remote sensing classified image according to a preset classification and identification rule to determine a classification and identification result of the soil to be identified.
2. The remote sensing classification and identification method for soil types according to claim 1, wherein the step of extracting the texture features of the remote sensing image under a preset scale according to a preset texture feature extraction rule specifically comprises:
and extracting the texture features of the remote sensing image under multiple preset scales according to a preset texture feature extraction rule.
3. The remote sensing, classifying and identifying method for soil types according to claim 1, characterized in that after the step of obtaining remote sensing images of the soil to be identified, the method further comprises:
and carrying out radiation correction and geometric correction processing on the remote sensing image to generate a processed remote sensing image.
4. The remote sensing classification and identification method for soil types according to claim 1, wherein the step of extracting the texture features of the remote sensing image under a preset scale according to a preset texture feature extraction rule specifically comprises:
and extracting texture features of the remote sensing image under a preset scale based on the gray level co-occurrence matrix.
5. The remote sensing classification and identification method for soil types according to claim 1, wherein the step of processing the remote sensing classification image according to a preset classification and identification rule to determine a classification and identification result of the soil to be identified specifically comprises:
and processing the remote sensing classified image based on a maximum likelihood classification method to determine a classification recognition result of the soil to be recognized.
6. The remote sensing classification and identification method for soil types according to claim 1, wherein the textural features are information entropy.
7. The remote sensing classification and identification method for soil types according to claim 1, wherein in the step of extracting the texture features of the remote sensing image under the preset scale according to the preset texture feature extraction rule, the preset scale is at least one of a 5 × 5 scale, a 15 × 15 scale, a 21 × 21 scale and a 23 × 23 scale.
8. A soil type remote sensing classification recognition device, characterized by, includes:
the remote sensing image acquisition unit is used for acquiring a remote sensing image of the soil to be identified;
the texture feature extraction unit is used for extracting the texture features of the remote sensing image under the preset scale according to a preset texture feature extraction rule; the texture features at least comprise one of mean value, variance, homogeneity, contrast, similarity, information entropy, second moment and correlation;
the fusion unit is used for fusing the texture features with the remote sensing image to generate a remote sensing classified image fused with the texture features;
and the classification recognition unit is used for processing the remote sensing classification image according to a preset classification recognition rule to determine a classification recognition result of the soil to be recognized.
9. A computer device comprising a memory and a processor, the memory having stored thereon a computer program which, when executed by the processor, causes the processor to carry out the steps of the remote soil type classification method according to any one of claims 1 to 7.
10. A computer-readable storage medium, having a computer program stored thereon, which, when being executed by a processor, causes the processor to carry out the steps of the remote soil type classification and identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110235195.8A CN112883892A (en) | 2021-03-03 | 2021-03-03 | Soil type remote sensing classification identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110235195.8A CN112883892A (en) | 2021-03-03 | 2021-03-03 | Soil type remote sensing classification identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112883892A true CN112883892A (en) | 2021-06-01 |
Family
ID=76055306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110235195.8A Pending CN112883892A (en) | 2021-03-03 | 2021-03-03 | Soil type remote sensing classification identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112883892A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114993965A (en) * | 2022-05-13 | 2022-09-02 | 中煤嘉沣(湖南)环保科技有限责任公司 | Automatic pollution source identification method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020649A (en) * | 2013-01-16 | 2013-04-03 | 东北林业大学 | Forest type identification method based on texture information |
| CN111144250A (en) * | 2019-12-15 | 2020-05-12 | 东南大学 | Land coverage classification method fusing radar and optical remote sensing data |
| CN111814563A (en) * | 2020-06-09 | 2020-10-23 | 河南工业大学 | Method and device for classifying planting structures |
-
2021
- 2021-03-03 CN CN202110235195.8A patent/CN112883892A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020649A (en) * | 2013-01-16 | 2013-04-03 | 东北林业大学 | Forest type identification method based on texture information |
| CN111144250A (en) * | 2019-12-15 | 2020-05-12 | 东南大学 | Land coverage classification method fusing radar and optical remote sensing data |
| CN111814563A (en) * | 2020-06-09 | 2020-10-23 | 河南工业大学 | Method and device for classifying planting structures |
Non-Patent Citations (1)
| Title |
|---|
| 宋翠玉等: "运用多尺度图像纹理进行城市扩展变化检测", 《国土资源遥感》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114993965A (en) * | 2022-05-13 | 2022-09-02 | 中煤嘉沣(湖南)环保科技有限责任公司 | Automatic pollution source identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110321963B (en) | Hyperspectral image classification method based on fusion of multi-scale and multi-dimensional space spectrum features | |
| CN107358260B (en) | Multispectral image classification method based on surface wave CNN | |
| AU2021102192A4 (en) | Remote sensing classification and identification method, device, equipment and storage medium for soil types | |
| Lin et al. | Effects of atmospheric correction and pansharpening on LULC classification accuracy using WorldView-2 imagery | |
| Lin et al. | Radiometric normalization and cloud detection of optical satellite images using invariant pixels | |
| Zhang et al. | Cloud detection in high-resolution remote sensing images using multi-features of ground objects | |
| CN109472199B (en) | Image fusion classification method and device | |
| CN106339674A (en) | Hyperspectral image classification method based on edge preservation and graph cut model | |
| Chen et al. | The application of the tasseled cap transformation and feature knowledge for the extraction of coastline information from remote sensing images | |
| Peng et al. | Object-based change detection from satellite imagery by segmentation optimization and multi-features fusion | |
| Zhao et al. | A systematic extraction approach for mapping glacial lakes in high mountain regions of Asia | |
| CN111639587B (en) | Hyperspectral image classification method based on multi-scale spectrum space convolution neural network | |
| CN104850822B (en) | Leaf identification method under simple background based on multi-feature fusion | |
| Shahi et al. | Road condition assessment by OBIA and feature selection techniques using very high-resolution WorldView-2 imagery | |
| Chen et al. | A landslide extraction method of channel attention mechanism U-Net network based on Sentinel-2A remote sensing images | |
| CN114841947A (en) | Method and device for multi-scale feature extraction and prognosis analysis of H & E staining pathological image tumor region | |
| CN116310510A (en) | Hyperspectral image classification method based on small sample deep learning | |
| Dibs et al. | Multi-fusion algorithms for detecting land surface pattern changes using multi-high spatial resolution images and remote sensing analysis | |
| CN115497010A (en) | Deep learning-based geographic information identification method and system | |
| Khatriker et al. | Building footprint extraction from high resolution satellite imagery using segmentation | |
| CN114049566B (en) | Method and device for detecting cloud and cloud shadow of land satellite image in step-by-step refinement manner | |
| Luo et al. | Extraction of bridges over water from IKONOS panchromatic data | |
| Zhang et al. | Multi-feature embedded learning SVM for cloud detection in remote sensing images | |
| CN112883892A (en) | Soil type remote sensing classification identification method, device, equipment and storage medium | |
| Wu et al. | Improved mask R-CNN-based cloud masking method for remote sensing images |
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 |