CN117218552B - Estimation algorithm optimization method and device based on pixel change detection - Google Patents
Estimation algorithm optimization method and device based on pixel change detection Download PDFInfo
- Publication number
- CN117218552B CN117218552B CN202310981272.3A CN202310981272A CN117218552B CN 117218552 B CN117218552 B CN 117218552B CN 202310981272 A CN202310981272 A CN 202310981272A CN 117218552 B CN117218552 B CN 117218552B
- Authority
- CN
- China
- Prior art keywords
- pixel
- change
- pixels
- detected
- stable
- 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.)
- Active
Links
- 230000008859 change Effects 0.000 title claims abstract description 295
- 238000001514 detection method Methods 0.000 title claims abstract description 94
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000005457 optimization Methods 0.000 title claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 100
- 238000002310 reflectometry Methods 0.000 claims abstract description 18
- 230000004931 aggregating effect Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 27
- 238000010801 machine learning Methods 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 7
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000000087 stabilizing effect Effects 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 description 17
- 238000003860 storage Methods 0.000 description 15
- 238000004590 computer program Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 12
- 238000011160 research Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000006872 improvement Effects 0.000 description 7
- 238000009826 distribution Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 239000002131 composite material Substances 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000012300 Sequence Analysis Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 241001414989 Thysanoptera Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 239000010908 plant waste Substances 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an estimation algorithm optimization method and device based on pixel change detection, wherein the method comprises the following steps: acquiring training sample images of a target surface area in a plurality of time periods; based on a pixel change recognition algorithm model, recognizing stable pixels and change to-be-detected pixels from the training sample images of the time periods; detecting a relatively stable pixel and a change pixel from the change pixel to be detected based on a pixel change period detection algorithm model; aggregating the band reflectivity information of all the stable pixels and the relatively stable pixels and the corresponding stable time periods to obtain a stable training database; and aggregating the band reflectivity information of all the change pixels in the same change time period to obtain a change training database. Therefore, the invention can fully utilize the change characteristics of different pixels to screen different training data sets, so that a model capable of being pertinently predicted can be obtained through subsequent training, and the accuracy of model estimation is improved.
Description
Technical Field
The invention relates to the technical field of remote sensing data processing, in particular to an estimation algorithm optimization method and device based on pixel change detection.
Background
With the vast population, urban construction land is rapidly expanding, resulting in significant land surface changes. This process has a significant impact on the urban environment. The geospatial pattern of urban areas is complex and highly heterogeneous. The traditional remote sensing image monitoring and analyzing method is difficult to meet the environment monitoring requirement of a rapid urban area.
The impermeable water surface is a typical land coverage type of urban areas and is also a key index of urban ecological environment, and an irreplaceable sub-pixel level research view is provided for monitoring and analyzing urbanization and ecological environment effects thereof. An accurate and efficient remote sensing image information extraction method is the basis of watertight surface related research, and is continuously paid attention to by a plurality of researchers in recent years. However, in the existing multi-timing monitoring research, composite errors are generated by the accumulation of systematic errors and random errors of the sub-pixel method, so that monitoring results are greatly affected in the aspects of time consistency, time resolution and the like, and the real process of surface change is difficult to accurately reflect. It can be seen that the prior art has defects and needs to be solved.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an estimation algorithm optimization method and device based on pixel change detection, which can fully utilize the change characteristics of different pixels to screen different training data sets so as to facilitate subsequent training to obtain a model capable of being used for specifically predicting, and effectively improve the accuracy of model estimation.
In order to solve the technical problem, a first aspect of the present invention discloses an estimation algorithm optimization method based on pixel change detection, the method comprising:
acquiring training sample images of a target surface area in a plurality of time periods;
Based on a pixel change recognition algorithm model, recognizing stable pixels and change to-be-detected pixels from the training sample images of the time periods;
Detecting a relatively stable pixel and a change pixel from the change pixel to be detected based on a pixel change period detection algorithm model;
aggregating the band reflectivity information of all the stable pixels and the relatively stable pixels and the corresponding stable time periods to obtain a stable training database; the stability training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the stability period;
The wave band reflectivity information of all the change pixels in the same change time period is aggregated to obtain a change training database; the change training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the corresponding change time period.
As an optional implementation manner, in the first aspect of the present invention, the identifying, based on the pixel change identification algorithm model, stable pixels and change pixels to be detected from the training sample images in the multiple time periods includes:
inputting the training sample images of the time periods into a trained stable pixel identification machine learning model to obtain identified stable pixels; the stable pixel identification machine learning model is obtained through training a training data set comprising a plurality of training images and corresponding visual change marks;
and determining the pixels except the stable pixels in the training sample image as pixels to be detected to be changed.
As an optional implementation manner, in the first aspect of the present invention, the detecting, based on the pixel change period detection algorithm model, a relatively stable pixel and a change pixel from the change to-be-detected pixel includes:
for any of the change detection pixels, calculating remote sensing index parameters of the change detection pixels;
Judging whether the remote sensing index parameter of the pixel to be measured is changed within a preset time period or not;
If not, determining the pixel to be detected to be changed as a relatively stable pixel;
If yes, determining the number of the change periods of the pixels to be detected in the period of the time period;
and determining the pixel to be detected to be a relatively stable pixel or a change pixel according to the change period number and a preset land coverage type change detection method.
As an optional implementation manner, in the first aspect of the present invention, the calculating the remote sensing index parameter of the pixel to be measured includes:
Calculating NDISI indexes of the pixels to be detected;
Calculating the green degree component of the thysancap transformation of the pixel to be measured;
And carrying out normalization processing on the NDISI indexes and the greenness components of the pixels to be detected to obtain remote sensing index parameters of the pixels to be detected.
In a first aspect of the present invention, the determining whether the remote sensing index parameter of the pixel to be measured changes within a preset period of time includes:
dividing the remote sensing index parameter into a plurality of levels;
Judging whether the level of the remote sensing index parameter of the pixel to be detected is changed in a preset time period or not.
As an optional implementation manner, in the first aspect of the present invention, the determining the number of change periods of the change pixel to be measured in the period of the time period includes:
and determining the number of time periods when the level of the remote sensing index parameter of the pixel to be detected changes in the time period, and obtaining the number of change periods of the pixel to be detected.
In a first aspect of the present invention, according to the number of the change periods and a preset land coverage type change detection method, the determining that the change pixel to be detected is a relatively stable pixel or a change pixel includes:
judging whether the number of the change periods is 1, if not, determining the change pixel to be detected as a change pixel;
If so, determining the pixel to be detected as a relatively stable pixel or a change pixel based on a preset land coverage type change detection method.
As an optional implementation manner, in the first aspect of the present invention, the method for detecting a change based on a preset land coverage type, determining the change pixel to be detected as a relatively stable pixel or a change pixel, includes:
Acquiring land coverage data of the first and last two periods in the period of time corresponding to the target surface area;
Detecting the types of the land cover data in the first period and the last period by using 3*3 moving windows, and judging whether the types of the pixels to be detected in the change in the land cover data are changed in the change period or not;
If yes, determining the pixel to be detected as a change pixel;
otherwise, determining the pixel to be detected to be a relatively stable pixel.
The second aspect of the invention discloses an estimation algorithm optimizing device based on pixel change detection, which comprises:
the acquisition module is used for acquiring training sample images of a plurality of time periods of the target surface area;
The identification module is used for identifying stable pixels and pixels to be tested in a change mode from training sample images of the time periods based on a pixel change identification algorithm model;
The detection module is used for detecting a relatively stable pixel and a change pixel from the change pixel to be detected based on a pixel change period detection algorithm model;
The first aggregation module is used for aggregating the band reflectivity information of all the stable pixels and the relatively stable pixels and the corresponding stable time periods to obtain a stable training database; the stability training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the stability period;
The second aggregation module is used for aggregating the band reflectivity information of all the change pixels in the same change time period to obtain a change training database; the change training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the corresponding change time period.
In a second aspect of the present invention, the specific manner of identifying the stable pixel and the changing pixel from the training sample images of the multiple time periods based on the pixel change identification algorithm model includes:
inputting the training sample images of the time periods into a trained stable pixel identification machine learning model to obtain identified stable pixels; the stable pixel identification machine learning model is obtained through training a training data set comprising a plurality of training images and corresponding visual change marks;
and determining the pixels except the stable pixels in the training sample image as pixels to be detected to be changed.
As an optional implementation manner, in the second aspect of the present invention, the specific manner of detecting the relatively stable pixel and the changed pixel from the changed pixels to be detected by the detection module based on the pixel change period detection algorithm model includes:
for any of the change detection pixels, calculating remote sensing index parameters of the change detection pixels;
Judging whether the remote sensing index parameter of the pixel to be measured is changed within a preset time period or not;
If not, determining the pixel to be detected to be changed as a relatively stable pixel;
If yes, determining the number of the change periods of the pixels to be detected in the period of the time period;
and determining the pixel to be detected to be a relatively stable pixel or a change pixel according to the change period number and a preset land coverage type change detection method.
As an optional implementation manner, in the second aspect of the present invention, a specific manner of calculating the remote sensing index parameter of the change pixel to be measured by the detection module includes:
Calculating NDISI indexes of the pixels to be detected;
Calculating the green degree component of the thysancap transformation of the pixel to be measured;
And carrying out normalization processing on the NDISI indexes and the greenness components of the pixels to be detected to obtain remote sensing index parameters of the pixels to be detected.
In a second aspect of the present invention, the specific way for the detection module to determine whether the remote sensing index parameter of the pixel to be detected changes within a preset period of time includes:
dividing the remote sensing index parameter into a plurality of levels;
Judging whether the level of the remote sensing index parameter of the pixel to be detected is changed in a preset time period or not.
As an optional implementation manner, in the second aspect of the present invention, the specific manner of determining the number of change periods of the change pixel to be detected in the period of the time period by the detection module includes:
and determining the number of time periods when the level of the remote sensing index parameter of the pixel to be detected changes in the time period, and obtaining the number of change periods of the pixel to be detected.
In a second aspect of the present invention, the detecting module determines, according to the number of change periods and a preset land coverage type change detecting method, a specific manner in which the change pixel to be detected is a relatively stable pixel or a change pixel, including:
judging whether the number of the change periods is 1, if not, determining the change pixel to be detected as a change pixel;
If so, determining the pixel to be detected as a relatively stable pixel or a change pixel based on a preset land coverage type change detection method.
In a second aspect of the present invention, the detecting module determines, based on a preset land coverage type change detecting method, a specific manner in which the change to-be-detected pixel is a relatively stable pixel or a change pixel, including:
Acquiring land coverage data of the first and last two periods in the period of time corresponding to the target surface area;
Detecting the types of the land cover data in the first period and the last period by using 3*3 moving windows, and judging whether the types of the pixels to be detected in the change in the land cover data are changed in the change period or not;
If yes, determining the pixel to be detected as a change pixel;
otherwise, determining the pixel to be detected to be a relatively stable pixel.
The third aspect of the present invention discloses another estimation algorithm optimizing apparatus based on pixel change detection, the apparatus comprising:
A memory storing executable program code;
A processor coupled to the memory;
The processor invokes the executable program code stored in the memory to perform some or all of the steps in the method for optimizing an estimation algorithm based on pel change detection disclosed in the first aspect of the present invention.
The fourth aspect of the present invention discloses a portable terminal for customs distribution, comprising a graphic code scanning device and a data processing device, wherein the data processing device is used for executing part or all of the steps in the estimation algorithm optimization method based on pixel change detection disclosed in the first aspect of the present invention.
Compared with the prior art, the invention has the following beneficial effects:
Therefore, the embodiment of the invention can screen stable and unchanged pixels and changed pixels from the training sample image based on the pixel change detection algorithm, and aggregate different pixels to train different estimation models, so that different training data sets can be screened out by fully utilizing the change characteristics of different pixels, the model capable of being used for specifically predicting can be obtained through subsequent training, and the model estimation precision is effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an estimation algorithm optimization method based on pixel change detection according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an estimation algorithm optimizing apparatus based on pixel change detection according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of another estimation algorithm optimizing apparatus based on pixel change detection according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "second," "second," and the like in the description and in the claims and in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or elements but may, in the alternative, include other steps or elements not expressly listed or inherent to such process, method, article, or device.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses an estimation algorithm optimization method and device based on pixel change detection, which can screen stable unchanged pixels and changed pixels from a training sample image based on the pixel change detection algorithm, and aggregate different pixels to train different estimation models, so that different training data sets can be screened out by fully utilizing the change characteristics of different pixels, a model capable of being used for specifically predicting can be obtained through subsequent training, and the model estimation precision is effectively improved. The following will describe in detail.
Example 1
Referring to fig. 1, fig. 1 is a flowchart of an estimation algorithm optimization method based on pixel change detection according to an embodiment of the present invention. The estimation algorithm optimization method based on pixel change detection described in fig. 1 is applied to a data processing chip, a processing terminal or a processing server (wherein the processing server may be a local server or a cloud server). As shown in fig. 1, the method for optimizing an estimation algorithm based on pixel change detection may include the following operations:
101. training sample images of a target surface area for a plurality of time periods are acquired.
102. Based on the pixel change recognition algorithm model, stable pixels and change pixels to be detected are recognized from training sample images in a plurality of time periods.
103. Based on the pixel change period detection algorithm model, a relatively stable pixel and a change pixel are detected from the change pixel to be detected.
104. And aggregating the band reflectivity information of all the stable pixels and the relatively stable pixels and the corresponding stable time period to obtain a stable training database.
The stability training database is used to train an estimation algorithm model for estimating the watertight density parameters of the target surface area for the stability period.
105. And aggregating the band reflectivity information of all the change pixels in the same change time period to obtain a change training database.
The change training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the corresponding change period.
Therefore, the embodiment of the invention can screen stable and unchanged pixels and changed pixels from the training sample image based on the algorithm of pixel change detection, and aggregate different pixels to train different estimation models, so that different training data sets can be screened out by fully utilizing the change characteristics of different pixels, a model capable of being used for specifically predicting is conveniently obtained through subsequent training, and the model estimation precision is effectively improved.
As an optional embodiment, in the step, based on the pixel change recognition algorithm model, the method for recognizing the stable pixel and the change pixel to be detected from the training sample images in multiple time periods includes:
And inputting training sample images of a plurality of time periods into a trained stable pixel identification machine learning model to obtain identified stable pixels.
And determining the pixels except the stable pixels in the training sample image as the pixels to be detected to be changed.
Specifically, the stable pel recognition machine learning model is trained by a training data set comprising a plurality of training images and corresponding visual change labels.
Through the embodiment, the machine learning model can be utilized to automatically identify obvious stable pixels, and the efficiency and the precision of pixel classification are improved.
As an alternative embodiment, in the step, based on the pixel change period detection algorithm model, detecting the relatively stable pixel and the change pixel from the change pixel to be detected includes:
For any change pixel to be detected, calculating the remote sensing index parameter of the change pixel to be detected;
judging whether the remote sensing index parameter of the pixel to be measured is changed within a preset time period;
If not, determining the pixel to be detected to be changed as a relatively stable pixel;
if yes, determining the number of the change periods of the pixels to be detected in the period of the time period;
and determining the pixel to be detected to be a relatively stable pixel or a change pixel according to the number of the change periods and a preset land coverage type change detection method.
As an alternative embodiment, in the step, calculating the remote sensing index parameter of the pixel to be measured includes:
Calculating NDISI indexes of the pixels to be detected;
Calculating the green degree component of the thysancap transformation of the pixel to be measured;
And carrying out normalization processing on NDISI indexes and the greenness component of the pixel to be detected to obtain remote sensing index parameters of the pixel to be detected.
As an optional embodiment, in the step, determining whether the remote sensing index parameter of the pixel to be measured is changed within the preset period of time includes:
dividing the remote sensing index parameter into a plurality of levels;
Judging whether the level of the remote sensing index parameter of the pixel to be detected is changed in a preset time period.
As an alternative embodiment, in the step above, determining the number of changing periods of the pixel to be measured in the period of time includes:
And determining the number of time periods when the level of the remote sensing index parameter of the pixel to be detected changes in the time period, and obtaining the number of change periods of the pixel to be detected.
As an optional embodiment, in the step, according to the number of the change periods and a preset land coverage type change detection method, determining the change to be detected pixel as a relatively stable pixel or a change pixel includes:
Judging whether the number of the change periods is 1, if not, determining the change pixel to be detected as a change pixel;
If so, determining the pixel to be detected as a relatively stable pixel or a change pixel based on a preset land coverage type change detection method.
As an optional embodiment, in the step, based on a preset land coverage type change detection method, determining the change to be detected pixel as a relatively stable pixel or a change pixel includes:
Acquiring land coverage data of the first and the last periods in a period of time corresponding to a target surface area;
detecting the types of the land cover data in the first period and the last period by using 3*3 moving windows, and judging whether the types of the pixels to be detected in the change in the land cover data are changed in the change period or not;
If yes, determining the pixel to be detected as a change pixel;
otherwise, determining the pixel to be detected to be a relatively stable pixel.
In a specific embodiment, the Level-2/Tier-1 Landsat surface reflectance product published by the United states geological survey to ground resource observation science center (EROS-USGS) is utilized. The product is processed by geometric fine correction (error is less than or equal to 12 m), radiometric calibration and atmospheric correction (LEDAPS algorithm based on a 6S transmission model), and can be generally used for multi-time sequence analysis.
In the scheme, after main and auxiliary data sources are acquired and data preprocessing is carried out, a multi-time sequence pixel database is built through pixel change detection in main research, and the main implementation steps are as follows: 1. visually identifying the stable/varying pel samples; 2. establishing a stable pixel identification model based on a remote sensing index; 3. dividing the relative stable period of the change pixels based on a time sequence fitting algorithm
Firstly, random points are generated in a research area, and stable/variable pixel samples are obtained through visual interpretation by referring to field investigation data and high/medium resolution remote sensing images. This step only needs to judge whether the pixels are changed or not, and does not need to identify the geographic attribute of the pixels, and the urban area is convenient for field verification. Therefore, enough samples can be quickly and accurately acquired, the maximum number of the image pixels is not more than ten thousand, and the ratio of the image pixels in a research area is not more than 5%.
Due to the heterogeneity of the land coverage distribution in urban areas, most of the pixels in the medium resolution image are basically mixed by watertight surfaces, vegetation and soil. Therefore, focus is placed on the changes associated with these critical features, and the use of the water impermeable surface index (NDISI) and the change in the green component of the leaf cap to detect the pixel changes associated with artificial ground and vegetation in remote sensing. Unlike normalized building and bare soil indices (NDBSI) or other indices related to soil or bare land, NDISI significantly excludes factors of soil variation, and focus on the spectral changes in the pixels caused by artificial surfaces can be calculated by the following formula:
Where ρ NIR、ρSWIR1 and ρ TIR are the 5 th, 6 th and 11 th bands of the Landsat 8 OLI image, respectively, and MNDWI (improved normalized water index) can be calculated by the following formula:
where ρ green and ρ SWIR1 are the 3 rd and 6 th bands of the Landsat 8 OLI image, respectively.
The green component obtained by the tassel cap transformation is used to identify the pixel change associated with vegetation. The thysanoptera transform is a linear transformation based on multispectral images, enhancing the physical characteristics of the image by reducing the correlation between bands. The first few components obtained after transformation are closely related to the surface landscape, wherein the greenness component is highly sensitive to the state and change of vegetation, and is widely used for vegetation monitoring. For Landsat 8OLI images, the green component of the leaf cap transformation is calculated by the following formula:
Greenness＝-0.2941ρblue-0.243ρgreen-0.5424ρred+0.7276ρNIR+0.0713ρSWIR1-0.1608ρSWI22;
Where ρ blue、ρgreen、ρred、ρNIR、ρSWIR and ρ SWIR2 are the 2 nd to 7 th bands of the Landsat 8OLI image, respectively.
And then carrying out normalization processing on the two indexes, and dividing the pixels into ten levels respectively. If the level of NDISI and the greenness component of a pel remains unchanged throughout the study period, then there is no period of change and is identified as a stable pel; the period during which the level changes is defined as the change period. One picture element is identified as a changed picture element if it has two or more change periods. And then distinguishing the pixel category with one change period by using the land coverage data. By using the land cover data of the first and last two stages, 3*3 moving windows are used to improve the sensitivity of land cover change detection.
On the basis of identifying stable pixels and dividing the relative stable period of the changed pixels, reconstructing Landsat series ground surface reflectivity images, establishing a multi-time sequence pixel database, and recording the change condition of pixel spectra year by year.
And using a Cubis tool with an open source, taking the reflectivity of each wave band of the resolution image in the training sample as a variable, taking the watertight density as an independent variable, and establishing a classification and regression tree model for estimating the multi-time-sequence watertight density of the whole research area. The watertight density of the stable pixel is kept unchanged in the research period, so that classification and regression tree model calculation can be established based on the spectral reflectivity of the image in the whole research period. Whereas for a changing picture element, for which the changing period and the relative stabilizing period have been defined, its watertight density remains unchanged relative to the stabilizing period, similar to a stabilizing picture element. The spectral reflectance of the image over a corresponding period is used to estimate the water-impermeable density. And for the watertight density of the change pixels in the change period, establishing a classification and regression tree model based on the image reflectivity of the corresponding year for respective modeling estimation. Thus obtaining the multi-time sequence artificial earth surface variation distribution of sub-pixel scale of the whole research area.
The problems of the prior art to be solved by the proposal are as follows: the existing sub-pixel side aiming at the impervious surface estimation has a compound error, and abnormal changes which are inconsistent with the actual situation often occur when local multi-time sequence analysis is carried out. In addition, the fixed low time resolution also affects the effectiveness of multi-time series monitoring, and in most of the existing studies, temporary and drastic changes in the urban process, such as construction sites, temporary plant waste, urban village demolition, etc., cannot be reflected, and for long-term changes, the exact point in time at which the changes are made is difficult to determine. The limitation of sub-pel method estimation of impermeable surfaces in multi-temporal monitoring is a key obstacle that restricts its wider application. In this regard, the scheme is implemented by the following key points:
1. Analyzing the multi-time sequence remote sensing image through a change detection algorithm, dividing the image pixels into change pixels and stable pixels, analyzing the spectrum change characteristics of the change pixels, and dividing the relative stable period;
2. the method for modeling and estimating the single-phase images by the traditional remote sensing method is changed, all stable pixels and the changed pixels in the relative stable period are aggregated, and the multi-time sequence pixel database is reconstructed according to the change condition of the pixels.
Accordingly, the above scheme of the invention has the following advantages:
1. the scheme of the invention can realize the estimation of the impermeable surface of the sub-pixel level, deeply analyze the ground object composition in the pixel on the basis of the existing spatial resolution, and can more accurately reflect the spatial distribution and change of the impermeable surface;
2. The scheme of the invention can comprehensively utilize the advantages of classification and regression trees and linear spectrum mixed analysis, eliminates or reduces the defects and limitations of the two algorithms by error analysis and correction, and improves the accuracy and stability of the watertight surface estimation;
3. The scheme of the invention can be suitable for remote sensing images with different types and different spectral characteristics, and has stronger universality and adaptability.
The scheme has the characteristics that all key factors generated by multi-time-sequence impervious surface monitoring errors are focused, the technical process of multi-time-sequence impervious surface monitoring is comprehensively optimized from the aspects of accidental errors and systematic errors to compound errors, and the reliability of monitoring results is improved. Specifically, the innovation points of the project are as follows:
1. based on error source analysis, a coupling optimization method is provided, the CART model system error is reduced, and the estimation precision of the existing single-stage impervious surface is further improved;
2. The data source reconstruction is carried out on the traditional remote sensing image data set, the watertight surface monitoring is carried out on the basis of the data by using the multi-time sequence pixel database, so that noise and abnormal pixels of a single-period image are effectively reduced, accidental errors of a single-period estimation result are reduced, composite errors caused by superposition of the multi-period result can be avoided, time resolution and monitoring precision are obviously improved, and the watertight surface monitoring device accords with the real situation of watertight surface change.
The scheme of the invention is based on an objective pixel change detection method, improves a sub-pixel monitoring method of a multi-time sequence impermeable surface, and has the following advantages compared with the prior art:
1. the invention can obviously reduce multi-time sequence compound errors by using a pixel change detection method without a large amount of auxiliary data and complicated manual operation, and can be used for monitoring the urban artificial earth surface under the condition of limited data sources;
2. the data source reconstruction is carried out on the traditional remote sensing image data set, the watertight surface monitoring is carried out on the basis of the data by using the multi-time sequence pixel database, so that noise and abnormal pixels of a single-period image are effectively reduced, accidental errors of a single-period estimation result are reduced, composite errors caused by superposition of the multi-period result can be avoided, the time resolution and the monitoring precision are obviously improved, the real situation of the watertight surface change is consistent, and reliable basic data is provided for related researches of urban environments.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of an estimation algorithm optimizing apparatus based on pixel change detection according to an embodiment of the present invention. The estimation algorithm optimizing device based on pixel change detection described in fig. 2 is applied to a data processing chip, a processing terminal or a processing server (wherein the processing server may be a local server or a cloud server). As shown in fig. 2, the estimation algorithm optimizing apparatus based on the pixel change detection may include:
An acquisition module 201, configured to acquire training sample images of a target surface area in a plurality of time periods;
The identifying module 202 is configured to identify a stable pixel and a change pixel to be detected from training sample images in a plurality of time periods based on a pixel change identifying algorithm model;
The detection module 203 is configured to detect a relatively stable pixel and a change pixel from the change pixel to be detected based on a pixel change period detection algorithm model;
A first aggregation module 204, configured to aggregate the band reflectivity information of all the stable pixels and the relatively stable pixels and the corresponding stable time periods to obtain a stable training database; the stability training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the stability period;
A second aggregation module 205, configured to aggregate band reflectivity information of all the change pixels in the same change period to obtain a change training database; the change training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the corresponding change period.
As an optional embodiment, the identifying module identifies a specific mode of stabilizing the pixel and changing the pixel to be tested from the training sample images of a plurality of time periods based on the pixel change identifying algorithm model, and includes:
inputting training sample images of a plurality of time periods into a trained stable pixel identification machine learning model to obtain identified stable pixels; the stable pixel identification machine learning model is obtained through training a training data set comprising a plurality of training images and corresponding visual change marks;
And determining the pixels except the stable pixels in the training sample image as the pixels to be detected to be changed.
As an alternative embodiment, the specific manner of detecting the relatively stable pixel and the changed pixel from the changed pixels to be detected by the detection module 203 based on the pixel change period detection algorithm model includes:
For any change pixel to be detected, calculating the remote sensing index parameter of the change pixel to be detected;
judging whether the remote sensing index parameter of the pixel to be measured is changed within a preset time period;
If not, determining the pixel to be detected to be changed as a relatively stable pixel;
if yes, determining the number of the change periods of the pixels to be detected in the period of the time period;
and determining the pixel to be detected to be a relatively stable pixel or a change pixel according to the number of the change periods and a preset land coverage type change detection method.
As an alternative embodiment, the specific manner of calculating the remote sensing index parameter of the pixel to be measured by the detection module 203 includes:
Calculating NDISI indexes of the pixels to be detected;
Calculating the green degree component of the thysancap transformation of the pixel to be measured;
And carrying out normalization processing on NDISI indexes and the greenness component of the pixel to be detected to obtain remote sensing index parameters of the pixel to be detected.
As an optional embodiment, the specific manner of determining, by the detection module 203, whether the remote sensing index parameter of the pixel to be detected changes within the preset period of time includes:
dividing the remote sensing index parameter into a plurality of levels;
Judging whether the level of the remote sensing index parameter of the pixel to be detected is changed in a preset time period.
As an optional embodiment, the specific manner of determining the number of change periods of the change pixel to be detected in the period of the time period by the detection module 203 includes:
And determining the number of time periods when the level of the remote sensing index parameter of the pixel to be detected changes in the time period, and obtaining the number of change periods of the pixel to be detected.
As an optional embodiment, the detecting module 203 determines, according to the number of change periods and a preset land coverage type change detecting method, a specific manner in which the change pixel to be detected is a relatively stable pixel or a change pixel, including:
Judging whether the number of the change periods is 1, if not, determining the change pixel to be detected as a change pixel;
If so, determining the pixel to be detected as a relatively stable pixel or a change pixel based on a preset land coverage type change detection method.
As an optional embodiment, the detecting module 203 determines, based on a preset land coverage type change detecting method, a specific manner in which the change to-be-detected pixel is a relatively stable pixel or a change pixel, including:
Acquiring land coverage data of the first and the last periods in a period of time corresponding to a target surface area;
detecting the types of the land cover data in the first period and the last period by using 3*3 moving windows, and judging whether the types of the pixels to be detected in the change in the land cover data are changed in the change period or not;
If yes, determining the pixel to be detected as a change pixel;
otherwise, determining the pixel to be detected to be a relatively stable pixel.
Example III
Referring to fig. 3, fig. 3 is a schematic diagram of another device for optimizing an estimation algorithm based on pixel change detection according to an embodiment of the present invention. The estimation algorithm optimizing device based on pixel change detection described in fig. 3 is applied to a data processing chip, a processing terminal or a processing server (wherein the processing server can be a local server or a cloud server). As shown in fig. 3, the estimation algorithm optimizing apparatus based on the pixel change detection may include:
a memory 301 storing executable program code;
a processor 302 coupled with the memory 301;
Wherein the processor 302 invokes executable program code stored in the memory 301 for performing the steps of the estimation algorithm optimization method based on pel change detection described in embodiment one.
Example IV
The embodiment of the invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the estimation algorithm optimization method based on pixel change detection described in the embodiment one.
Example five
The embodiment of the invention discloses a computer program product, which comprises a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to make a computer execute the steps of the estimation algorithm optimization method based on pixel change detection described in the embodiment.
The foregoing describes certain embodiments of the present disclosure, other embodiments being within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. Furthermore, the processes depicted in the accompanying drawings do not necessarily have to be in the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-transitory computer readable storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to portions of the description of method embodiments being relevant.
The apparatus, the device, the nonvolatile computer readable storage medium and the method provided in the embodiments of the present disclosure correspond to each other, and therefore, the apparatus, the device, and the nonvolatile computer storage medium also have similar advantageous technical effects as those of the corresponding method, and since the advantageous technical effects of the method have been described in detail above, the advantageous technical effects of the corresponding apparatus, device, and nonvolatile computer storage medium are not described herein again.
In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable GATEARRAY, FPGA)) is an integrated circuit whose logic functions are determined by user programming of the device. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented with "logic compiler (logic compiler)" software, which is similar to the software compiler used in program development and writing, and the original code before being compiled is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but HDL is not just one, but a plurality of kinds, such as ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware DescriptionLanguage)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(RubyHardware Description Language), and VHDL (Very-High-SPEEDINTEGRATED CIRCUIT HARDWARE DESCRIPTION LANGUAGE) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application SPECIFIC INTEGRATED Circuits (ASICs), programmable logic controllers, and embedded microcontrollers, examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present specification.
It will be appreciated by those skilled in the art that the present description may be provided as a method, system, or computer program product. Accordingly, the present specification embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description embodiments may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that 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 phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
Finally, it should be noted that: the embodiment of the invention discloses an estimation algorithm optimizing method and device based on pixel change detection, which are disclosed by the embodiment of the invention only for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (8)
1. An estimation algorithm optimization method based on pixel change detection, which is characterized by comprising the following steps:
acquiring training sample images of a target surface area in a plurality of time periods;
Based on a pixel change recognition algorithm model, recognizing stable pixels and change to-be-detected pixels from the training sample images of the time periods;
Detecting a relatively stable pixel and a change pixel from the change pixel to be detected based on a pixel change period detection algorithm model; the pixel change recognition algorithm model is used for recognizing stable pixels and change to-be-detected pixels from training sample images in a plurality of time periods, and comprises the following steps:
inputting the training sample images of the time periods into a trained stable pixel identification machine learning model to obtain identified stable pixels; the stable pixel identification machine learning model is obtained through training a training data set comprising a plurality of training images and corresponding visual change marks;
determining the pixels except the stable pixels in the training sample image as pixels to be detected to be changed; the detection of the relatively stable pixel and the change pixel from the change pixel to be detected based on the pixel change period detection algorithm model comprises the following steps:
for any of the change detection pixels, calculating remote sensing index parameters of the change detection pixels;
Judging whether the remote sensing index parameter of the pixel to be measured is changed within a preset time period or not;
If not, determining the pixel to be detected to be changed as a relatively stable pixel;
If yes, determining the number of the change periods of the pixels to be detected in the period of the time period;
according to the number of the change periods and a preset land coverage type change detection method, determining that the change pixel to be detected is a relatively stable pixel or a change pixel;
aggregating the band reflectivity information of all the stable pixels and the relatively stable pixels and the corresponding stable time periods to obtain a stable training database; the stability training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the stability period;
The wave band reflectivity information of all the change pixels in the same change time period is aggregated to obtain a change training database; the change training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the corresponding change time period.
2. The method for optimizing an estimation algorithm based on pixel change detection according to claim 1, wherein the calculating the remote sensing index parameter of the pixel to be measured for change comprises:
Calculating NDISI indexes of the pixels to be detected;
Calculating the green degree component of the thysancap transformation of the pixel to be measured;
And carrying out normalization processing on the NDISI indexes and the greenness components of the pixels to be detected to obtain remote sensing index parameters of the pixels to be detected.
3. The method for optimizing an estimation algorithm based on pixel change detection according to claim 2, wherein the determining whether the remote sensing index parameter of the pixel to be measured for change changes within a preset period of time includes:
dividing the remote sensing index parameter into a plurality of levels;
Judging whether the level of the remote sensing index parameter of the pixel to be detected is changed in a preset time period or not.
4. The method for optimizing an estimation algorithm based on pixel change detection according to claim 3, wherein said determining the number of change periods of the change pixel to be detected in the period of the time period includes:
and determining the number of time periods when the level of the remote sensing index parameter of the pixel to be detected changes in the time period, and obtaining the number of change periods of the pixel to be detected.
5. The method for optimizing an estimation algorithm based on pixel change detection according to claim 4, wherein the determining that the change pixel to be detected is a relatively stable pixel or a change pixel according to the number of change periods and a preset land coverage type change detection method includes:
judging whether the number of the change periods is 1, if not, determining the change pixel to be detected as a change pixel;
If so, determining the pixel to be detected as a relatively stable pixel or a change pixel based on a preset land coverage type change detection method.
6. The method for optimizing an estimation algorithm based on pixel change detection according to claim 5, wherein the determining that the change pixel to be detected is a relatively stable pixel or a change pixel based on a preset land coverage type change detection method includes:
Acquiring land coverage data of the first and last two periods in the period of time corresponding to the target surface area;
Detecting the types of the land cover data in the first period and the last period by using 3*3 moving windows, and judging whether the types of the pixels to be detected in the change in the land cover data are changed in the change period or not;
If yes, determining the pixel to be detected as a change pixel;
otherwise, determining the pixel to be detected to be a relatively stable pixel.
7. An estimation algorithm optimizing apparatus based on pixel change detection, the apparatus comprising:
the acquisition module is used for acquiring training sample images of a plurality of time periods of the target surface area;
The identification module is used for identifying stable pixels and pixels to be tested in a change mode from training sample images of the time periods based on a pixel change identification algorithm model; the identification module identifies specific modes of stabilizing pixels and changing pixels to be detected from training sample images in a plurality of time periods based on a pixel change identification algorithm model, and the specific modes comprise:
inputting the training sample images of the time periods into a trained stable pixel identification machine learning model to obtain identified stable pixels; the stable pixel identification machine learning model is obtained through training a training data set comprising a plurality of training images and corresponding visual change marks;
determining the pixels except the stable pixels in the training sample image as pixels to be detected to be changed;
The detection module is used for detecting a relatively stable pixel and a change pixel from the change pixel to be detected based on a pixel change period detection algorithm model; the detection module detects a relatively stable pixel and a specific mode of a change pixel from the change pixel to be detected based on a pixel change period detection algorithm model, and comprises the following steps:
for any of the change detection pixels, calculating remote sensing index parameters of the change detection pixels;
Judging whether the remote sensing index parameter of the pixel to be measured is changed within a preset time period or not;
If not, determining the pixel to be detected to be changed as a relatively stable pixel;
If yes, determining the number of the change periods of the pixels to be detected in the period of the time period;
according to the number of the change periods and a preset land coverage type change detection method, determining that the change pixel to be detected is a relatively stable pixel or a change pixel;
The first aggregation module is used for aggregating the band reflectivity information of all the stable pixels and the relatively stable pixels and the corresponding stable time periods to obtain a stable training database; the stability training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the stability period;
The second aggregation module is used for aggregating the band reflectivity information of all the change pixels in the same change time period to obtain a change training database; the change training database is used for training an estimation algorithm model for estimating the watertight density parameter of the target surface area of the corresponding change time period.
8. An estimation algorithm optimizing apparatus based on pixel change detection, the apparatus comprising:
A memory storing executable program code;
A processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the method of optimizing the estimation algorithm based on pel change detection as claimed in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310981272.3A CN117218552B (en) | 2023-08-04 | 2023-08-04 | Estimation algorithm optimization method and device based on pixel change detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310981272.3A CN117218552B (en) | 2023-08-04 | 2023-08-04 | Estimation algorithm optimization method and device based on pixel change detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117218552A CN117218552A (en) | 2023-12-12 |
| CN117218552B true CN117218552B (en) | 2024-06-04 |
Family
ID=89034210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310981272.3A Active CN117218552B (en) | 2023-08-04 | 2023-08-04 | Estimation algorithm optimization method and device based on pixel change detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117218552B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118172630A (en) * | 2024-02-02 | 2024-06-11 | 华南师范大学 | Method and device for judging stable pixels |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104678392A (en) * | 2015-01-19 | 2015-06-03 | 河海大学 | Foundation SAR (Synthetic Aperture Radar) atmosphere delaying correction method based on stable pixel weighting |
| CN112017135A (en) * | 2020-07-13 | 2020-12-01 | 香港理工大学深圳研究院 | Method, system and equipment for spatial-temporal fusion of remote sensing image data |
| CN113222005A (en) * | 2021-05-08 | 2021-08-06 | 兰州交通大学 | Automatic updating method for land coverage |
| CN113327214A (en) * | 2021-05-19 | 2021-08-31 | 中国科学院地理科学与资源研究所 | Continuous time series water body remote sensing mapping method |
| CN115861823A (en) * | 2023-02-21 | 2023-03-28 | 航天宏图信息技术股份有限公司 | Remote sensing change detection method and device based on self-supervision deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476837B (en) * | 2019-01-23 | 2023-02-24 | 上海科技大学 | Adaptive stereo matching optimization method and device, equipment and storage medium thereof |
-
2023
- 2023-08-04 CN CN202310981272.3A patent/CN117218552B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104678392A (en) * | 2015-01-19 | 2015-06-03 | 河海大学 | Foundation SAR (Synthetic Aperture Radar) atmosphere delaying correction method based on stable pixel weighting |
| CN112017135A (en) * | 2020-07-13 | 2020-12-01 | 香港理工大学深圳研究院 | Method, system and equipment for spatial-temporal fusion of remote sensing image data |
| CN113222005A (en) * | 2021-05-08 | 2021-08-06 | 兰州交通大学 | Automatic updating method for land coverage |
| CN113327214A (en) * | 2021-05-19 | 2021-08-31 | 中国科学院地理科学与资源研究所 | Continuous time series water body remote sensing mapping method |
| CN115861823A (en) * | 2023-02-21 | 2023-03-28 | 航天宏图信息技术股份有限公司 | Remote sensing change detection method and device based on self-supervision deep learning |
Non-Patent Citations (3)
| Title |
|---|
| Multitemporal impervious surface estimation via an optimized stable/change pixel detection approach;Jin Wang et al;《GIScience & Remote Sensing》;20220902;第1406-1425页 * |
| 基于Cubist模型树的城市不透水面百分比遥感估算模型;戴舒;付迎春;赵耀龙;;地球信息科学学报;20161031(10);第1399-1409页 * |
| 戴舒;付迎春;赵耀龙.基于Cubist模型树的城市不透水面百分比遥感估算模型.地球信息科学学报.2016,(10),第1399-1409页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117218552A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2840436C (en) | System for mapping and identification of plants using digital image processing and route generation | |
| Ke et al. | A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing | |
| CN109543630B (en) | Remote sensing image woodland extraction method and system based on deep learning, storage medium and electronic equipment | |
| Chen et al. | Isolating individual trees in a savanna woodland using small footprint lidar data | |
| Liu et al. | An object-based conceptual framework and computational method for representing and analyzing coastal morphological changes | |
| Cavallaro et al. | Automatic attribute profiles | |
| CN110648347A (en) | Coastline extraction method and device based on remote sensing image | |
| CN117218552B (en) | Estimation algorithm optimization method and device based on pixel change detection | |
| CN106295613A (en) | A kind of unmanned plane target localization method and system | |
| CN113160183B (en) | Hyperspectral data processing method, device and medium | |
| CN116361737B (en) | Lake abnormity dynamic monitoring method and device, electronic equipment and storage medium | |
| Novelli et al. | Improving the ANN classification accuracy of landsat data through spectral indices and linear transformations (PCA and TCT) aimed at LU/LC monitoring of a river basin | |
| CN114494881A (en) | Method, device and terminal for detecting remote sensing image change based on subdivision grid | |
| Gonçalves et al. | Functions for aboveground biomass estimation derived from satellite images data in Mediterranean agroforestry systems | |
| CN117218551B (en) | Estimation algorithm optimization method and device based on error analysis | |
| CN106023268A (en) | Color image graying method based on two-step parameter subspace optimization | |
| CN112697218A (en) | Reservoir capacity curve reconstruction method | |
| Flynn et al. | Quantifying vegetation indices using terrestrial laser scanning: methodological complexities and ecological insights from a Mediterranean forest | |
| Erener et al. | A methodology for land use change detection of high resolution pan images based on texture analysis | |
| Han et al. | A deep learning technique-based automatic monitoring method for experimental urban road inundation | |
| Luo et al. | High-precise water extraction based on spectral-spatial coupled remote sensing information | |
| CN116740521A (en) | Landslide detection method and system based on multi-scale feature fusion | |
| Sakieh et al. | An integrated spectral-textural approach for environmental change monitoring and assessment: analyzing the dynamics of green covers in a highly developing region | |
| Liu et al. | Tree Crown width estimation, using discrete airborne LiDAR data | |
| CN116187525A (en) | Remote sensing prediction method and device for crop yield in northwest region combined with weather |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |