CN115601655A - Water body information identification method and device based on satellite remote sensing and readable medium - Google Patents
Water body information identification method and device based on satellite remote sensing and readable medium Download PDFInfo
- Publication number
- CN115601655A CN115601655A CN202211242050.1A CN202211242050A CN115601655A CN 115601655 A CN115601655 A CN 115601655A CN 202211242050 A CN202211242050 A CN 202211242050A CN 115601655 A CN115601655 A CN 115601655A
- Authority
- CN
- China
- Prior art keywords
- water body
- remote sensing
- determining
- target
- buffer area
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 209
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000011218 segmentation Effects 0.000 claims abstract description 59
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 16
- 238000003708 edge detection Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 230000002194 synthesizing effect Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 description 10
- 230000003287 optical effect Effects 0.000 description 5
- 210000000746 body region Anatomy 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- HQHACWYQWDKBOZ-UHFFFAOYSA-N 1-nitroso-azacyclotridecane Chemical compound O=NN1CCCCCCCCCCCC1 HQHACWYQWDKBOZ-UHFFFAOYSA-N 0.000 description 1
- 238000004177 carbon cycle Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000010840 domestic wastewater Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000010419 fine particle Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000010842 industrial wastewater Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 150000003568 thioethers Chemical class 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
Abstract
The application discloses a water body information identification method, a water body information identification device and a readable medium based on satellite remote sensing, and a target remote sensing image corresponding to a target area in a preset time period is obtained. And determining an edge buffer area in the target remote sensing image, and determining water body index data corresponding to pixels in the edge buffer area. And determining a target segmentation threshold according to the water body index data corresponding to the pixels in the edge buffer area. And carrying out water body identification on the target remote sensing image based on the target segmentation threshold. By setting the target segmentation threshold to: the method comprises the steps of determining or updating a biaxial of water body index data of an edge buffer area based on a set floating point type step length, and enabling a determined target segmentation threshold value to be suitable for classification of floating point type numerical values through the biaxial when the inter-class difference between different types of data obtained by segmenting the water body index data of the edge buffer area meets a difference condition based on the determined or updated biaxial, so that the water body information identification precision based on the remote sensing image can be further improved.
Description
Technical Field
The application belongs to the technical field of remote sensing image processing, and particularly relates to a water body information identification method and device based on satellite remote sensing.
Background
At present, in the aspect of identification and extraction of remote sensing water bodies, two methods, namely supervised classification and unsupervised classification, are generally available. The supervised classification method can only match the spectrum class and the ground feature class by selecting a sample point, requires long time and cannot meet the service requirement of calculating the classification result in real time and quickly. The spectrum type and the ground feature type obtained by the unsupervised classification method are not necessarily matched, so that the accuracy of the remote sensing water body image obtained from the open-source remote sensing image database is insufficient, and finally the accuracy of water body information identification based on the remote sensing image is insufficient.
Disclosure of Invention
In view of the above, the present application provides a method, an apparatus, and a computer readable medium for identifying water body information based on satellite remote sensing, so as to solve the problem that the accuracy of identifying water body information based on a sample selected by depending on and a remote sensing image is low.
In order to solve the problems, the application provides the following water body information identification scheme based on satellite remote sensing:
a water body information identification method based on satellite remote sensing comprises the following steps:
acquiring a target remote sensing image corresponding to a target area within a preset time period;
determining an edge buffer area in the target remote sensing image, and determining water body index data corresponding to pixels in the edge buffer area;
determining a target segmentation threshold according to water body index data corresponding to pixels in the edge buffer area; wherein the target segmentation threshold is: determining or updating a biaxial of the water body index data of the edge buffer area based on the set floating point type step length, and determining or updating a biaxial corresponding to the biaxial when the inter-class difference between different classes of data obtained by dividing the water body index data of the edge buffer area based on the determined or updated biaxial meets a difference condition;
and carrying out water body identification on the target remote sensing image based on the target segmentation threshold value.
Optionally, the obtaining of the target remote sensing image corresponding to the target area in the preset time period includes:
acquiring a plurality of corresponding remote sensing images of a target area within a preset time period;
and synthesizing the plurality of remote sensing images to obtain a target remote sensing image.
Optionally, the determining an edge buffer area in the target remote sensing image includes:
performing edge detection on the target remote sensing image to obtain an edge area;
and performing pixel expansion on each pixel in the edge area according to a preset proportion to obtain an edge buffer area in the target remote sensing image.
Optionally, the determining water body index data corresponding to the pixels in the edge buffer includes:
determining a reflection wave band corresponding to the pixel according to the gray value of the pixel in the edge buffer area in the target remote sensing image;
and determining water body index data corresponding to the pixels in the edge buffer area according to the reflection wave bands corresponding to the pixels in the edge buffer area.
Optionally, the determining a target segmentation threshold according to water body index data corresponding to a pixel in the edge buffer includes:
sequencing the water body index data corresponding to each pixel in the edge buffer area respectively to obtain a sequencing sequence of the water body indexes;
determining a two-axis of the sorting sequence according to the maximum value and the minimum value in the sorting sequence and a preset floating point type step length; the floating point type step length is a step length set based on the required classification precision;
dividing the sorted sequence into two categories based on the bisection axis;
determining the inter-class variance of the two obtained classes;
updating the binary axis based on the step length, and determining whether the updated binary axis is the maximum value of the sorting sequence; if not, the step of dividing the sorting sequence into two categories based on the binary axis is circulated until the updated binary axis is the maximum value of the sorting sequence;
and taking the corresponding binary axis with the largest inter-class variance as the target segmentation threshold.
Optionally, the performing, on the basis of the target segmentation threshold, water body identification on the target remote sensing image includes:
and performing image dichotomy processing on the target remote sensing image according to the target segmentation threshold value, and identifying the part in the image, which accords with the water body index characteristic, as a water body area.
Optionally, the method further includes:
and determining whether the water body corresponding to the identified water body area is a polluted water body.
Optionally, the determining whether the water body corresponding to the identified water body area is a polluted water body includes:
respectively determining the distances from the water body indexes of the pixels in the identified water body area to a preset reference according to various different distance algorithms to obtain distance determination results respectively corresponding to the different distance algorithms; the preset reference is water body characteristics of a non-polluted water body extracted in advance, and the water body characteristics comprise: determining characteristics according to the water body index of each pixel in the remote sensing image information of the non-polluted water body;
and determining whether the water body corresponding to the identified water body area is a polluted water body according to the distance determination results respectively corresponding to different distance algorithms.
A water body information identification device based on satellite remote sensing comprises:
the target remote sensing image acquisition unit is used for acquiring a target remote sensing image corresponding to a target area within a preset time period;
the first determining unit is used for determining an edge buffer area in the target remote sensing image and determining water body index data corresponding to pixels in the edge buffer area;
the second determining unit is used for determining a target segmentation threshold according to the water body index data corresponding to the pixels in the edge buffer area; wherein the target segmentation threshold is: determining or updating a biaxial of the water body index data of the edge buffer area based on the set floating point type step length, and determining or updating a biaxial corresponding to the biaxial when the inter-class difference between different classes of data obtained by dividing the water body index data of the edge buffer area meets a difference condition based on the determined or updated biaxial;
and the water body identification unit is used for carrying out water body identification on the target remote sensing image based on the target segmentation threshold value.
A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, can be used for implementing the method for identifying water body information based on satellite remote sensing as described in any one of the above.
According to the scheme, the method, the device and the computer readable medium for identifying the water body information based on the satellite remote sensing acquire the target remote sensing image corresponding to the target area within the preset time period. And determining an edge buffer area in the target remote sensing image, and determining water body index data corresponding to pixels in the edge buffer area. Determining a target segmentation threshold according to water body index data corresponding to pixels in the edge buffer area; wherein the target segmentation threshold is: and determining or updating a binary axis of the water body index data of the edge buffer area based on the set floating point type step length, and determining or updating a binary axis corresponding to the binary axis when the inter-class difference between different classes of data obtained by dividing the water body index data of the edge buffer area meets the difference condition based on the determined or updated binary axis. And carrying out water body identification on the target remote sensing image based on the target segmentation threshold value. The present application sets a target segmentation threshold to: the method comprises the steps of determining or updating a biaxial of water body index data of an edge buffer area based on a set floating point type step length, and determining or updating a biaxial corresponding to the determined or updated biaxial when the inter-class difference between different types of data obtained by segmenting the water body index data of the edge buffer area meets a difference condition based on the determined or updated biaxial, so that the determined target segmentation threshold value can be suitable for the classification of floating point type numerical values, and the water body information identification precision based on the remote sensing image can be further improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only the embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a water body information identification method based on satellite remote sensing provided by the present application;
FIG. 2 is another schematic flow chart of a water body information identification method based on satellite remote sensing provided by the application;
FIG. 3 is a diagram of the computational process of the improved Otsu method provided by the present application;
FIG. 4 is another schematic flow chart of a water body information identification method based on satellite remote sensing provided by the application;
FIG. 5 is a flowchart of an application example of image water body information identification based on satellite remote sensing provided by the present application;
fig. 6 is a structural diagram of a water body information recognition device based on satellite remote sensing according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The application discloses a method and a device for identifying water body information through satellite remote sensing and a computer readable medium.
In recent years, remote sensing technology has been widely applied in many aspects of various fields due to the characteristics of all weather, large scale and the like, for example, field investigation before loan is replaced by calculating the agricultural land area through vegetation monitoring, the loan period can be effectively shortened, and remote sensing monitoring is applied in post-loan wind control, and the like. Recently, with the development of wave and green financial carbon cycle policies of digital transformation, more and more ecological problems are coming into public view, wherein the existence of polluted water damages the surrounding environment and affects the survival of surrounding organisms, so that it is very necessary to perform water body information identification such as polluted water body identification in the field. The embodiment of the application aims at identifying water body information based on satellite remote sensing.
Referring to a flow schematic diagram of a water body information identification method based on satellite remote sensing shown in fig. 1, the water body information identification method based on satellite remote sensing provided by the application comprises the following flows:
Wherein, the target area is a designated area needing water body identification. The method comprises the steps of firstly obtaining a plurality of remote sensing images corresponding to a target area in a preset time period, and then carrying out synthesis processing on the obtained remote sensing images to obtain a target remote sensing image. The preset time period may be, but is not limited to, any one of a year, a half year, a quarter, a month, a half month, and a few days.
Optionally, multiple remote sensing images corresponding to the designated area are acquired through the open source image database, quality evaluation is performed on the images, the images with low cloud amount are screened to form an image data set to be processed, and the cloud in the images corresponding to the designated area can be removed by using a cloud removing algorithm but not limited to the cloud removing algorithm on the basis. Then, a plurality of remote sensing images in the image data set are synthesized to obtain a target remote sensing image, for example, satellite remote sensing images of a certain city at a month interval within a half year are selected to obtain a remote sensing image set, the remote sensing images in the remote sensing image set are subjected to cloud elimination by using a cloud elimination algorithm, and then the remote sensing images are synthesized according to median, wherein for pixels in an overlapping area in each remote sensing image, the median of corresponding gray values of the pixels in different remote sensing images is taken as the gray value of the synthesized pixel, concretely, the six remote sensing images are obtained, if three pixels are overlapped at the pixel X, the gray value of the synthesized pixel X is the median of the gray values of the X in the three images, if one pixel in a certain remote sensing image is not overlapped with other remote sensing images, the gray value of the pixel is directly taken as the gray value of the pixel in the synthesized image, and the remote sensing image of the certain city is obtained after image synthesis.
And 102, determining an edge buffer area in the target remote sensing image, and determining water body index data corresponding to pixels in the edge buffer area.
And then, carrying out edge detection on the obtained target remote sensing image to obtain an edge area. The edge detection is a common algorithm for extracting image features in image processing and computer vision, and is based on the characteristic that the image gradient can obtain a maximum value at an edge pixel point, and the edge contour line of a target area in a target remote sensing image is detected, so that the image information can be simplified, and the edge line is used for representing the information carried in the image. In the process, in order to remove the influence of other irrelevant objects in the target area on the result, the Canny algorithm can be used for edge detection to obtain an edge area corresponding to the target area.
And then, performing pixel expansion on each pixel in the edge area according to a preset proportion to obtain an edge buffer area in the target remote sensing image.
And finally, according to pixel gray values corresponding to all pixels in an edge buffer area in the target remote sensing image, determining reflection wave bands corresponding to all pixels respectively, and further according to the reflection wave bands corresponding to all pixels in the edge buffer area, determining water body indexes corresponding to all pixels in the edge buffer area respectively, so as to obtain water body index data corresponding to the pixels in the edge buffer area.
Further, the water body index of each pixel in the edge buffer area of the target remote sensing image can be subjected to normalization calculation to obtain the normalized water body index (NDMI) of each pixel, and the water body index is a model capable of extracting the water body according to ratio operation among the wave bands.
And 103, determining a target segmentation threshold according to the water body index data corresponding to the pixels in the edge buffer area.
In the scientific research of utilizing the remote sensing technology, water body index data plays an important role, and in the method, threshold selection can influence the classification precision of remote sensing images. In the known technology, the feature information is generally identified and extracted through the feature spectrum, and the principle is to utilize the characteristic that different objects reflect or absorb different wavelengths of visible light. The main methods comprise a single-waveband threshold value method, an inter-spectral relationship method and an exponential model method, and the three methods all depend on threshold value segmentation strongly and belong to a threshold value classification method. The Otsu method, as a commonly used automated threshold segmentation algorithm in the field of image processing, has a defect that it is difficult to adapt to remote sensing image processing, specifically, the Otsu method in the prior art only supports RGB color brightness values, such as {0,1,2, \8230;, 255}, while remote sensing images are usually floating point type data and cannot be adapted.
Therefore, the application provides an improved Dajin algorithm which can be suitable for remote sensing images of planar floating point data and can obtain more accurate target segmentation threshold values, wherein the target segmentation threshold values are as follows: and determining or updating a binary axis of the water body index data of the edge buffer area based on the set floating point type step length, and determining or updating a binary axis corresponding to the binary axis when the inter-class difference between different types of data obtained by dividing the water body index data of the edge buffer area meets the difference condition based on the determined or updated binary axis.
The detailed steps of the process of obtaining the target segmentation threshold are shown in fig. 2, fig. 2 shows the overall process of obtaining the target segmentation threshold by using the improved universe method, see the calculation process diagram of the improved universe method shown in fig. 3, the calculation process of fig. 3 corresponds to the steps in fig. 2 one-to-one, and the detailed steps are as follows:
Specifically, the water body index data of the edge buffer area is read into the memory in an array form, and the array form is arranged in order to obtain a one-dimensional ordered array.
Specifically, the maximum value and the minimum value in the one-dimensional ordered array are taken and recorded as min and max, respectively, and the step size step is set according to the target precision, for example, if the precision of 0.1 is required, the step size is set to 0.1, and if the precision of 0.01 is required, the step size is set to 0.01. Here, the i-th biaxial is pivot (i) = min + (i + 1) × step.
And 303, dividing the sorting sequence into two categories based on the binary axis.
Dividing the one-dimensional ordered array into two classes by taking a biaxial pivot as an axis, respectively marking the two classes as class1 (min < class1< = pivot) and class2 (pivot < class2< = max), counting the number of points falling on class1 and class2 as probabilities p1 and p2, and calculating the mean value of the two classes as mean1 and mean2.
The inter-class variance represents the discrete degree of two sides of the threshold, and the larger the inter-class variance is, the larger the difference between classes is, and the more obvious the binarization effect is.
After derivation, the inter-class variance formula delta is obtained 2 i ＝p1*p2*(mean1-mean2) 2 . Storing the inter-class variance into the hash table map [ pivot ]]= between-class variance.
Specifically, the binary axis is increased by one step based on the above steps, that is, pivot (i + 1) = min + ((i + 1) + 1) × step, and it is determined whether the binary axis is less than or equal to the maximum value max, if so, step 303 and step 304 are performed with a new binary axis, and if not, the iteration is ended.
And step 306, taking the binary axis with the maximum inter-class variance as the target segmentation threshold.
In the hash table, the two-axis corresponding to the maximum value of the inter-class variance is the target segmentation threshold.
In the improved Otsu method, floating point type step length setting is added, that is, the step length is set to be a floating point value smaller than 1, so that the partition granularity of the two split axes is more refined and is refined to the required floating point precision, and accordingly, the determined threshold can be used for classifying floating point type numerical values and is suitable for processing floating point type data. The precision is embodied by the step length, the higher the precision requirement is, the smaller the step length is, for example, the precision of 0.1 is required, the step length is set to be 0.1, the precision of 0.01 is required, and the step length is set to be 0.01. The method solves the defect that the Otsu method in the prior art cannot be applied to processing of remote sensing images, and can enable the target segmentation threshold value to be more accurate through continuous iteration until the condition is met according to the floating point type step length setting based on the precision requirement, so that the precision of image segmentation is improved.
And 104, performing water body identification on the target remote sensing image based on the target segmentation threshold value.
And then, performing image dichotomy processing on the target remote sensing image according to the target segmentation threshold, and identifying the part, which accords with the water body index characteristic, in the target remote sensing image as a water body area based on the dichotomy processing.
Optionally, after the water body region is identified, the gray value of the obtained water body region may be further fused to the corresponding region of the corresponding RGB image, that is, the water body region is superimposed on the corresponding color composite image, so that the display effect of the water body region is more obvious.
In summary, the water body information identification method based on satellite remote sensing disclosed by the application obtains the target remote sensing image corresponding to the target area within the preset time period. And determining an edge buffer area in the target remote sensing image, and determining water body index data corresponding to pixels in the edge buffer area. Determining a target segmentation threshold according to water body index data corresponding to pixels in the edge buffer area; wherein the target segmentation threshold is: and determining or updating a binary axis of the water body index data of the edge buffer area based on the set floating point type step length, and determining or updating a binary axis corresponding to the binary axis when the inter-class difference between different types of data obtained by dividing the water body index data of the edge buffer area meets the difference condition based on the determined or updated binary axis. And carrying out water body identification on the target remote sensing image based on the target segmentation threshold.
This application has increased floating point type step length setting through modified Otsu method, sets up the step length to be less than 1 floating point value for the partition granularity of binary axis is more meticulous, and meticulous to required floating point precision, corresponding threshold value that makes the determination can be used for the classification of floating point type numerical value, is adapted to the processing of floating point type data. The present application sets the target segmentation threshold to: the method comprises the steps of determining or updating a biaxial of water body index data of an edge buffer area based on a set floating point type step length, and determining or updating a biaxial corresponding to the determined or updated biaxial when the inter-class difference between different types of data obtained by segmenting the water body index data of the edge buffer area meets a difference condition based on the determined or updated biaxial, so that the determined target segmentation threshold value can be suitable for the classification of floating point type numerical values, and the water body information identification precision based on the remote sensing image can be further improved.
Optionally, in an embodiment, referring to fig. 4, the method for identifying water body information based on satellite remote sensing provided by the present application may further include the following processing:
Here, the polluted water body can be domestic wastewater and industrial wastewater, the components of the polluted water body often contain a large amount of sulfides, and the polluted water body is generally black brown due to chemical reaction, so that the reflectivity curve of the polluted water body is obviously different from that of a normal water body.
Optionally, when it is determined whether the identified water body area is a polluted water body, the statistical characteristics of the non-polluted water body within a certain period of time (e.g., within a certain quarterly range) may be predetermined, and a determination criterion for determining the polluted water body may be set based on the determined statistical characteristics of the non-polluted water body, where the statistical characteristics may be statistical characteristics obtained by performing statistics on normalized water body indexes of each pixel in a remote sensing image of the non-polluted water body, and on this basis, the above criterion may be set to, but is not limited to: and (3) selecting the median of the normalized water body index corresponding to each pixel of the non-polluted water body remote sensing image in the selected time period.
On the basis, preferably, the distances from the normalized water body indexes of the pixels in the identified water body area to the set reference are calculated according to a plurality of different distance algorithms, and distance determination results corresponding to the different distance algorithms are obtained, wherein the heterogeneous distance algorithms are selected as much as possible, because the problems that the homogeneous algorithms are not accurate enough, the errors are large, and the reliability is low can be avoided by adopting the heterogeneous algorithms. And then, judging whether the identified water body area is polluted or not by using a voting method, and if the voting is more than half, determining that the water in the identified water body area is the polluted water body.
The method can judge whether the water body is polluted or not, trace the time of occurrence of the sewage, screen suspected polluted water bodies as a sample set, and trace the time points upwards in a layered manner step by step, wherein the time points can be divided into different fine particle sizes of tracing in years, seasons, months, half months and the like.
In summary, the embodiment performs image dichotomy processing on the target remote sensing image based on the floating point type target segmentation threshold obtained by improving Otsu method to identify the water body information, so that the water body information identification precision based on the remote sensing image is further improved, and the polluted water body is identified on the basis, so that the obtained result is more accurate and reliable.
Optionally, referring to fig. 5, a flow of an application example of the method of the present application is provided.
Firstly, data preprocessing is carried out, remote sensing images of a designated area are obtained through an open source image library, meanwhile, quality evaluation is carried out on the images, the images with low cloud amount are screened to form an image data set to be processed, and the cloud in the image set of the area is removed through a cloud removing algorithm on the basis. And synthesizing each image in the data set according to the median of the grey values of the pixels on the remote sensing image to obtain a synthesized image, and calculating the wave band of each pixel on the synthesized image according to the water body index model to obtain an NDWI result.
Then, generating a buffer area in order to remove the influence of other irrelevant background ground objects in the area on the result; and performing edge detection by using a Canny algorithm, and performing pixel expansion on the obtained pixels on the edge according to a certain proportion on the basis to obtain a buffer area, so that the OTSU (global threshold segmentation algorithm) can concentrate targets on the edge part, and the accuracy of threshold segmentation is improved.
Then, threshold segmentation is carried out, pixel information is counted on the edge buffer area, and an optimal segmentation threshold is calculated according to an improved Otsu method.
And finally, visualizing the image, carrying out image dichotomy processing on the optimal segmentation threshold determined in the previous step to obtain a water body area, selecting and overlaying the obtained water body on the true-color synthetic image, namely fusing the gray level of the water body to the corresponding area of the RGB image, so that the display effect of the water body area is more vivid, and the classification result is displayed conveniently.
In conclusion, the process provides the water body index threshold segmentation method based on the improved Otsu method, overcomes the defects of the prior art in a specific scene, avoids compressing high-precision floating point type data, and greatly improves the segmentation precision. The method is a complete water body dichotomy method based on the remote sensing image, has the characteristics of real-time performance, accuracy, rapidness, convenience and the like, and simultaneously achieves full automation.
For the water body information identification method based on satellite remote sensing, the application also provides a water body information identification device based on satellite remote sensing, and the structure of the device is shown in fig. 6.
And the target remote sensing image acquisition unit 10 is configured to acquire a target remote sensing image corresponding to the target area within a preset time period.
The first determining unit 20 is configured to determine an edge buffer area in the target remote sensing image, and determine water body index data corresponding to pixels in the edge buffer area.
The second determining unit 30 is configured to determine a target segmentation threshold according to water body index data corresponding to pixels in the edge buffer; wherein the target segmentation threshold is: determining or updating a binary axis of the water body index data of the edge buffer area based on the set floating point type step length, and enabling the inter-class difference between different classes of data obtained by dividing the water body index data of the edge buffer area to meet a difference condition based on the determined or updated binary axis.
And the water body identification unit 40 is used for carrying out water body identification on the target remote sensing image based on a target segmentation threshold value.
In an embodiment, the target remote sensing image obtaining unit 10 is specifically configured to:
acquiring a plurality of corresponding remote sensing images of a target area within a preset time period;
and synthesizing the plurality of remote sensing images to obtain a target remote sensing image.
In an embodiment, the first determining unit is specifically configured to:
and carrying out edge detection on the target remote sensing image to obtain an edge area.
And performing pixel expansion on each pixel in the edge area according to a preset proportion to obtain an edge buffer area in the target remote sensing image.
And determining a reflection wave band corresponding to the pixel according to the pixel gray value of the edge buffer area in the target remote sensing image.
And determining water body index data corresponding to the pixels in the edge buffer area according to the reflection wave bands corresponding to the pixels in the edge buffer area.
The second determining unit 30 is specifically configured to:
and sequencing the water body index data corresponding to each pixel in the edge buffer area respectively to obtain a sequencing sequence of the water body indexes.
Determining a binary axis of the sorting sequence according to the maximum value and the minimum value in the sorting sequence and a preset floating point type step length; the floating-point type step size is a step size set based on a required classification precision.
The sorted sequences are divided into two categories based on a bisection axis.
The resulting inter-class variance of the two classes is determined.
Updating the binary axis based on the step length, and determining whether the updated binary axis is the maximum value of the sorting sequence; if not, the step of dividing the sorting sequence into two categories based on the binary axis is circulated until the updated binary axis is the maximum value of the sorting sequence.
And taking the corresponding binary axis with the largest inter-class variance as the target segmentation threshold.
In an embodiment, the water body identification unit 40 is specifically configured to:
and performing image dichotomy processing on the target remote sensing image according to a target segmentation threshold value, and identifying a part in the image, which accords with the water body index characteristic, as a water body area.
In one embodiment, the apparatus further comprises:
and the third determining unit is used for determining whether the water body corresponding to the identified water body area is a polluted water body.
The method is specifically used for:
according to multiple different distance algorithms, respectively determining the distances from the water body indexes of the pixels in the identified water body area to a preset reference to obtain the distance determination results respectively corresponding to the different distance algorithms, wherein the preset reference is the water body characteristics of the non-polluted water body extracted in advance, and the water body characteristics comprise: and determining characteristics according to the water body index of each pixel in the remote sensing image information of the non-polluted water body.
And determining whether the water body corresponding to the identified water body area is a polluted water body according to the distance determination results respectively corresponding to different distance algorithms.
In addition, the embodiment of the application also provides a computer readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program can be used for realizing the steps in the water body information identification method based on satellite remote sensing.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
It should be noted that, in this specification, each embodiment is described in a progressive manner, and each embodiment focuses on differences from other embodiments, and portions that are the same as and similar to each other in each embodiment may be referred to.
For convenience of description, the above system or apparatus is described as being divided into various modules or units in terms of functions, respectively. Of course, the functionality of the various elements may be implemented in the same one or more pieces of software and/or hardware in the practice of the present application.
From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.
Finally, it is further noted that, herein, relational terms such as first, second, third, fourth, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is only a preferred embodiment of the present application and it should be noted that, as will be apparent to those skilled in the art, numerous modifications and adaptations can be made without departing from the principles of the present application and such modifications and adaptations are intended to be considered within the scope of the present application.
Claims (10)
1. A water body information identification method based on satellite remote sensing is characterized by comprising the following steps:
acquiring a target remote sensing image corresponding to a target area within a preset time period;
determining an edge buffer area in the target remote sensing image, and determining water body index data corresponding to pixels in the edge buffer area;
determining a target segmentation threshold according to water body index data corresponding to pixels in the edge buffer area; wherein the target segmentation threshold is: determining or updating a biaxial of the water body index data of the edge buffer area based on the set floating point type step length, and determining or updating a biaxial corresponding to the biaxial when the inter-class difference between different classes of data obtained by dividing the water body index data of the edge buffer area meets a difference condition based on the determined or updated biaxial;
and carrying out water body identification on the target remote sensing image based on the target segmentation threshold value.
2. The method according to claim 1, wherein the obtaining of the target remote sensing image corresponding to the target area in the preset time period comprises:
acquiring a plurality of corresponding remote sensing images of a target area within a preset time period;
and synthesizing the plurality of remote sensing images to obtain a target remote sensing image.
3. The method of claim 1, wherein the determining an edge buffer in the target remote sensing image comprises:
performing edge detection on the target remote sensing image to obtain an edge area;
and performing pixel expansion on each pixel in the edge area according to a preset proportion to obtain an edge buffer area in the target remote sensing image.
4. The method of claim 1, wherein determining water body index data corresponding to pels in the edge buffer comprises:
determining a reflection wave band corresponding to a pixel according to the pixel gray value of an edge buffer area in the target remote sensing image;
and determining water body index data corresponding to the pixels in the edge buffer area according to the reflection wave bands corresponding to the pixels in the edge buffer area.
5. The method of claim 1, wherein determining the target segmentation threshold according to the water body index data corresponding to the pixels in the edge buffer comprises:
sequencing the water body index data corresponding to each pixel in the edge buffer area respectively to obtain a sequencing sequence of the water body indexes;
determining a biaxial of the sorting sequence according to the maximum value and the minimum value in the sorting sequence and a preset floating point type step length; the floating point type step length is a step length set based on the required classification precision;
classifying the sorted sequence into two categories based on the bisection axis;
determining the inter-class variance of the two obtained classes;
updating the binary axis based on the step length, and determining whether the updated binary axis is the maximum value of the sorting sequence; if not, the step of dividing the sorting sequence into two categories based on the binary axis is circulated until the updated binary axis is the maximum value of the sorting sequence;
and taking the corresponding binary axis with the largest inter-class variance as the target segmentation threshold.
6. The method according to claim 1, wherein the performing water body identification on the target remote sensing image based on the target segmentation threshold comprises:
and performing image dichotomy processing on the target remote sensing image according to a target segmentation threshold value, and identifying a part in the image, which accords with the water body index characteristic, as a water body area.
7. The method of claim 1, further comprising:
and determining whether the water body corresponding to the identified water body area is a polluted water body.
8. The method of claim 7, wherein the determining whether the body of water corresponding to the identified body of water area is a contaminated body of water comprises:
respectively determining the distances from the water body indexes of the pixels in the identified water body area to a preset reference according to various different distance algorithms to obtain distance determination results respectively corresponding to the different distance algorithms;
the preset reference is water body characteristics of a non-polluted water body extracted in advance, and the water body characteristics comprise: determining characteristics according to water body indexes of pixels in remote sensing image information of the non-polluted water body;
and determining whether the water body corresponding to the identified water body area is a polluted water body according to the distance determination results respectively corresponding to different distance algorithms.
9. The utility model provides a water information recognition device based on satellite remote sensing which characterized in that includes:
the target remote sensing image acquisition unit is used for acquiring a target remote sensing image corresponding to a target area within a preset time period;
the first determining unit is used for determining an edge buffer area in the target remote sensing image and determining water body index data corresponding to pixels in the edge buffer area;
the second determining unit is used for determining a target segmentation threshold according to the water body index data corresponding to the pixels in the edge buffer area; wherein the target segmentation threshold is: determining or updating a biaxial of the water body index data of the edge buffer area based on the set floating point type step length, and determining or updating a biaxial corresponding to the biaxial when the inter-class difference between different classes of data obtained by dividing the water body index data of the edge buffer area meets a difference condition based on the determined or updated biaxial;
and the water body identification unit is used for carrying out water body identification on the target remote sensing image based on the target segmentation threshold value.
10. A computer-readable medium, on which a computer program is stored, wherein the computer program, when executed by a processor, is adapted to implement the method for identifying information about a body of water based on satellite remote sensing according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211242050.1A CN115601655A (en) | 2022-10-11 | 2022-10-11 | Water body information identification method and device based on satellite remote sensing and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211242050.1A CN115601655A (en) | 2022-10-11 | 2022-10-11 | Water body information identification method and device based on satellite remote sensing and readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115601655A true CN115601655A (en) | 2023-01-13 |
Family
ID=84847891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211242050.1A Pending CN115601655A (en) | 2022-10-11 | 2022-10-11 | Water body information identification method and device based on satellite remote sensing and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115601655A (en) |
-
2022
- 2022-10-11 CN CN202211242050.1A patent/CN115601655A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Wheat ear counting using K-means clustering segmentation and convolutional neural network | |
| CN110148130B (en) | Method and device for detecting part defects | |
| CN109740639B (en) | Wind cloud satellite remote sensing image cloud detection method and system and electronic equipment | |
| CN111398176B (en) | Water body water color abnormity remote sensing identification method and device based on pixel scale characteristics | |
| CN110781756A (en) | Urban road extraction method and device based on remote sensing image | |
| EP3844668A1 (en) | System and method for training a damage identification model | |
| CN116188475B (en) | Intelligent control method, system and medium for automatic optical detection of appearance defects | |
| CN114758249B (en) | Target object monitoring method, device, equipment and medium based on field night environment | |
| CN115223063B (en) | Deep learning-based unmanned aerial vehicle remote sensing wheat new variety lodging area extraction method and system | |
| CN111598827A (en) | Appearance flaw detection method, electronic device and storage medium | |
| CN115131283A (en) | Defect detection and model training method, device, equipment and medium for target object | |
| CN114169381A (en) | Image annotation method and device, terminal equipment and storage medium | |
| WO2020047316A1 (en) | System and method for training a damage identification model | |
| CN113255580A (en) | Method and device for identifying sprinkled objects and vehicle sprinkling and leaking | |
| CN117392042A (en) | Defect detection method, defect detection apparatus, and storage medium | |
| CN110866931A (en) | Image segmentation model training method and classification-based enhanced image segmentation method | |
| CN111178405A (en) | Similar object identification method fusing multiple neural networks | |
| CN111931721B (en) | Method and device for detecting color and number of annual inspection label and electronic equipment | |
| CN113723467A (en) | Sample collection method, device and equipment for defect detection | |
| CN116229336B (en) | Video moving target identification method, system, storage medium and computer | |
| CN112348750A (en) | SAR image change detection method based on threshold fusion and neighborhood voting | |
| CN115984786A (en) | Vehicle damage detection method and device, terminal and storage medium | |
| CN115601655A (en) | Water body information identification method and device based on satellite remote sensing and readable medium | |
| CN111507177B (en) | Identification method and device for metering turnover cabinet | |
| Yao et al. | An adaptive and quantitative rubber nutrient status analyzing system by digital foliar 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 |