CN115631419A - Method and device for extracting rice planting area and spatial distribution based on change detection - Google Patents
Method and device for extracting rice planting area and spatial distribution based on change detection Download PDFInfo
- Publication number
- CN115631419A CN115631419A CN202211568345.8A CN202211568345A CN115631419A CN 115631419 A CN115631419 A CN 115631419A CN 202211568345 A CN202211568345 A CN 202211568345A CN 115631419 A CN115631419 A CN 115631419A
- Authority
- CN
- China
- Prior art keywords
- band
- target
- ratio
- remote sensing
- period
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/58—Extraction of image or video features relating to hyperspectral data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Abstract
The invention provides a method and a device for extracting rice planting area and spatial distribution based on change detection, which relate to the technical field of remote sensing survey and monitoring of natural resources and comprise the following steps: acquiring target data of a region to be extracted in a preset period, wherein the preset period comprises the following steps: the transplanting period and heading period of the rice, and the target data comprise: multispectral remote sensing image data and high-precision farmland vector data; processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer; calculating the wave band parameters of each object in the image object layer; the planting area and the spatial distribution condition of the rice in the region to be extracted are determined based on the wave band parameters, and the technical problem that the extraction efficiency and the extraction precision of the existing rice planting area and spatial distribution extraction method are low is solved.
Description
Technical Field
The invention relates to the technical field of natural resource remote sensing investigation and monitoring, in particular to a method and a device for extracting rice planting area and spatial distribution based on change detection.
Background
Rice is one of three major crops in the world, and is concerned about the safety of human food and the social stability. The paddy field is used as an important wetland ecological type and has very important significance for environmental protection. As a main rice producing country, rice planting plays an important role in China. Remote sensing and artificial intelligence technology are combined, rice planting area and spatial distribution are rapidly mastered, annual change is analyzed, and scientific basis can be provided for formulating grain production policy, macroscopically regulating and controlling rice planting region and sustainable development of agricultural resources.
The common remote sensing data source for rice identification is optical and SAR (synthetic aperture radar) remote sensing data with medium and low resolution, such as foreign Landsat series, modis, sentinel series and the like, while the satellite data of domestic data such as resource (ZY) series, high score (GF) series, sky plot (TH) series and the like are less used. The common rice information extraction method is based on the key phenological period of rice, the spectral characteristics of rice and other fields are obviously different, a spectral band sensitive to vegetation and water bodies or normalized vegetation indexes NDVI, normalized water body indexes NDWI and the like are selected, and rice information extraction is carried out by adopting supervised classification, unsupervised classification or knowledge rule classification. The supervised classification method requires a certain number of samples to be collected, and the result is greatly influenced by the quality of the samples. Unsupervised classification completely depends on similarity clustering among spectral bands, and the result is often unsatisfactory. The knowledge rule classification method usually adopts a fixed threshold value, so that the algorithm has poor transportability and low automation degree. Some people also adopt long-time sequence data covering the whole rice growth period to extract rice information through neural network modeling or other models, so that the algorithm complexity is high, and the calculation workload is large. Most of the methods are based on pixel prediction, are limited by the spatial resolution of the used remote sensing image, and have limited attribute and area precision of rice extraction.
No effective solution has been proposed to the above problems.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for extracting a rice planting area and a spatial distribution based on change detection, so as to alleviate the technical problem of low extraction efficiency and accuracy of the existing method for extracting a rice planting area and a spatial distribution.
In a first aspect, an embodiment of the present invention provides a method for extracting a rice planting area and spatial distribution based on change detection, including: acquiring target data of a region to be extracted in a preset period, wherein the preset period comprises the following steps: the transplanting period of the rice and the heading period of the rice, and the target data comprise: multispectral remote sensing image data and high-precision farmland vector data; processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer, wherein the image object layer and the farmland block layer have a topological association relationship; calculating the wave band parameters of each object in the image object layer, wherein the wave band parameters comprise: -a ratio between the brightness of a target band and the overall brightness, said target band comprising: transplanting period near infrared wave band, heading period near infrared wave band and heading period blue wave band, wherein the total brightness is the sum of the brightness of each wave band in the multispectral remote sensing image data corresponding to the preset period; and determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the wave band parameters.
Further, based on the high-precision farmland vector data, processing the multispectral remote sensing image data to obtain a farmland block layer and an image object layer, and the method comprises the following steps: preprocessing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain target multispectral remote sensing image data, wherein the preprocessing comprises the following steps: radiometric calibration processing, atmospheric correction processing, orthometric correction processing and geometric registration processing; merging the target multispectral remote sensing image data to obtain merged data; and based on the high-precision farmland vector data and a scale set segmentation algorithm, segmenting the merged data to obtain the farmland block layer and the image object layer, wherein the image object layer comprises a plurality of objects, the objects consist of homogeneous pixels, the farmland block layer comprises a plurality of blocks, and one block comprises one or more objects.
Further, calculating the band parameters of each object in the image object layer includes: calculating target parameters of each object in the image object layer, wherein the target parameters include: the method comprises the following steps of obtaining a blue band ratio and a near-infrared band ratio, wherein the blue band ratio is the ratio between the blue band value of the multispectral remote sensing image data in the transplanting period and the blue band value of the multispectral remote sensing image data in the heading period, and the near-infrared band ratio is the ratio between the near-infrared band value of the multispectral remote sensing image data in the heading period and the near-infrared band value of the multispectral remote sensing image data in the transplanting period; and calculating the waveband parameters based on the target parameters.
Further, determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the waveband parameters, including: based on the wave band parameters, calculating the characteristic values of blue wave band ratio and near-infrared wave band ratio of all objects in the image object layer, wherein the characteristic values comprise: mean and variance; determining a target threshold value based on the characteristic values of the blue band ratio and the near-infrared band ratio, wherein the target threshold value comprises: a threshold value of the blue band ratio and a threshold value of the near-infrared band ratio; and determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the target threshold and the wave band parameters.
Further, based on the target threshold and the band parameters, determining the planting area and the spatial distribution condition of the rice in the region to be extracted, including: determining the object with the blue band ratio larger than the threshold of the blue band ratio and the near-infrared band ratio larger than the threshold of the near-infrared band ratio as a first target object; based on the band parameters, removing the second target object from the first target object to obtain a third target object, wherein the second target object comprises: the first target object is a first target object, wherein the ratio of the brightness of the near-infrared band to the total brightness in the transplanting period is larger than a first preset threshold value, or the ratio of the brightness of the near-infrared band to the total brightness in the heading period is smaller than the first preset threshold value, and the ratio of the blue band in the heading period is larger than a second preset threshold value; transmitting a fourth target object with the rice area larger than a preset threshold value in the third target object to a cultivated land block layer through an inheritance relationship to obtain a target cultivated land block layer; constructing first vector data based on the fourth target object, and constructing second vector data based on the target farmland block layer; and determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the first vector data and the second vector data.
In a second aspect, an embodiment of the present invention further provides a device for extracting a rice planting area and spatial distribution based on change detection, including: the device comprises an acquisition unit, a storage unit and a processing unit, wherein the acquisition unit is used for acquiring target data of a region to be extracted in a preset period, and the preset period comprises: the transplanting period of the rice and the heading period of the rice, and the target data comprise: multispectral remote sensing image data and high-precision farmland vector data; the processing unit is used for processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer, wherein the image object layer and the farmland block layer have a topological association relationship; a calculating unit, configured to calculate a band parameter of each object in the image object layer, where the band parameter includes: a ratio between a luminance of a target band and a total luminance, the target band including: transplanting period near infrared wave band, heading period near infrared wave band and heading period blue wave band, wherein the total brightness is the sum of the brightness of each wave band in the multispectral remote sensing image data corresponding to the preset period; and the determining unit is used for determining the planting area and the spatial distribution condition of the rice in the area to be extracted based on the waveband parameters.
Further, the processing unit is configured to: preprocessing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain target multispectral remote sensing image data, wherein the preprocessing comprises the following steps: radiometric calibration processing, atmospheric correction processing, orthometric correction processing and geometric registration processing; merging the target multispectral remote sensing image data to obtain merged data; and segmenting the merged data based on the high-precision farmland vector data and a scale set segmentation algorithm to obtain the farmland block layer and the image object layer, wherein the image object layer comprises a plurality of objects, the objects consist of homogeneous pixels, the farmland block layer comprises a plurality of blocks, and one block comprises one or more objects.
Further, the computing unit is configured to: calculating target parameters of each object in the image object layer, wherein the target parameters include: the method comprises the following steps of obtaining a blue band ratio and a near-infrared band ratio, wherein the blue band ratio is the ratio between the blue band value of the multispectral remote sensing image data in the transplanting period and the blue band value of the multispectral remote sensing image data in the heading period, and the near-infrared band ratio is the ratio between the near-infrared band value of the multispectral remote sensing image data in the heading period and the near-infrared band value of the multispectral remote sensing image data in the transplanting period; and calculating the waveband parameters based on the target parameters.
In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory and a processor, where the memory is used to store a program that supports the processor to execute the method in the first aspect, and the processor is configured to execute the program stored in the memory.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored.
In the embodiment of the present invention, target data of a region to be extracted in a preset period is acquired, where the preset period includes: the transplanting period of the rice and the heading period of the rice, and the target data comprise: multispectral remote sensing image data and high-precision farmland vector data; processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer, wherein the image object layer and the farmland block layer have a topological association relationship; calculating the wave band parameters of each object in the image object layer, wherein the wave band parameters comprise: a ratio between a luminance of a target band and a total luminance, the target band including: transplanting period near infrared wave band, heading period near infrared wave band and heading period blue wave band, wherein the total brightness is the sum of the brightness of each wave band in the multispectral remote sensing image data corresponding to the preset period; based on the wave band parameters, the planting area and the spatial distribution condition of the rice in the region to be extracted are determined, the purpose of efficiently and accurately extracting the planting area and the spatial distribution of the rice is achieved, the technical problem that the extraction efficiency and the extraction precision of the existing extraction method for the planting area and the spatial distribution of the rice are low is solved, and the technical effect of improving the extraction efficiency and the extraction precision of the extraction method for the planting area and the spatial distribution of the rice is achieved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for extracting rice planting area and spatial distribution based on change detection according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a device for extracting rice planting area and spatial distribution based on change detection according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
according to an embodiment of the present invention, there is provided an embodiment of a rice planting area and spatial distribution extraction method based on change detection, it should be noted that the steps shown in the flowchart of the drawings may be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown or described herein.
Fig. 1 is a flowchart of a rice planting area and spatial distribution extraction method based on change detection according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S102, acquiring target data of a region to be extracted in a preset period, wherein the preset period comprises: the transplanting period of the rice and the heading period of the rice, and the target data comprise: multispectral remote sensing image data and high-precision farmland vector data;
the remote sensing image data satisfying the detection requirements in space, spectrum, and time phase is selected based on the regional distribution of rice, the lunar calendar, and the like. Since rice mostly grows in areas with more clouds and rains, in order to ensure that optical image data of a transplanting period and a heading period are obtained, common optical remote sensing data with medium-low resolution can be used as multispectral remote sensing image data in the embodiment of the invention as long as the multispectral remote sensing image data has four multispectral wave bands of blue, green, red and near infrared, such as optical satellite high-definition (GF) series, resource (ZY) series, sky-painting (TH) series in China, and Landsat, sentinel and the like in foreign countries.
Step S104, processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer, wherein the image object layer and the farmland block layer have a topological association relationship;
step S106, calculating a band parameter of each object in the image object layer, wherein the band parameter includes: -a ratio between the brightness of a target band and the overall brightness, said target band comprising: transplanting period near infrared wave band, heading period near infrared wave band and heading period blue wave band, wherein the total brightness is the sum of the brightness of each wave band in the multispectral remote sensing image data corresponding to the preset period;
and S108, determining the planting area and the spatial distribution condition of the rice in the area to be extracted based on the wave band parameters.
In the embodiment of the present invention, target data of a region to be extracted in a preset period is obtained, where the preset period includes: the transplanting period of the rice and the heading period of the rice, and the target data comprise: multispectral remote sensing image data and high-precision farmland vector data; processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer, wherein the image object layer and the farmland block layer have a topological association relationship; calculating the wave band parameters of each object in the image object layer, wherein the wave band parameters comprise: a ratio between a luminance of a target band and a total luminance, the target band including: transplanting period near infrared wave band, heading period near infrared wave band and heading period blue wave band, wherein the total brightness is the sum of the brightness of each wave band in the multispectral remote sensing image data corresponding to the preset period; based on the wave band parameters, the planting area and the spatial distribution condition of the rice in the area to be extracted are determined, the purpose of efficiently and accurately extracting the planting area and the spatial distribution of the rice is achieved, the technical problem that the extraction efficiency and the extraction precision of the existing extraction method for the planting area and the spatial distribution of the rice are low is solved, and the technical effect of improving the extraction efficiency and the extraction precision of the extraction method for the planting area and the spatial distribution of the rice is achieved.
In the embodiment of the present invention, step S104 includes the following steps:
preprocessing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain target multispectral remote sensing image data, wherein the preprocessing comprises the following steps: radiometric calibration processing, atmospheric correction processing, orthometric correction processing and geometric registration processing;
merging the target multispectral remote sensing image data to obtain merged data;
and segmenting the merged data based on the high-precision farmland vector data and a scale set segmentation algorithm to obtain the farmland block layer and the image object layer, wherein the image object layer comprises a plurality of objects, the objects consist of homogeneous pixels, the farmland block layer comprises a plurality of blocks, and one block comprises one or more objects.
In the embodiment of the invention, the coordinate system in the high-precision farmland vector data is taken as a reference to respectively carry out radiometric calibration, atmospheric correction, orthorectification, geometric registration and other treatments on the multispectral image data in the transplanting period and the heading period, and then the images in the 4 wave bands in the two periods are sequentially synthesized into an 8 wave band image data file (namely, merged data) according to time sequence.
The expression for the merged data is
In the formula (I), the reaction is carried out,
the blue, green, red and near infrared wave bands are adopted in the transplanting period,
the ear sprouting period is blue, green, red and near infrared wave bands.
Radiometric calibration is to eliminate the radiometric error caused by the sensor itself and to convert the dimensionless DN value recorded by the sensor into the radiance or reflectivity of the top layer of the atmosphere with practical physical meaning.
The atmospheric correction is to convert the radiance value (or atmospheric top reflectivity) of the atmospheric top layer into the solar radiance value (or surface reflectivity) of the surface reflection, mainly to eliminate the influence of atmospheric absorption and scattering on the radiation transmission.
The orthorectification method is to correct the image point displacement caused by sensor errors, topographic relief and the like by means of satellite sensor model parameters, a geometric model, control points and DEM data, eliminate the geometric deformation of an image and generate an orthorectified image.
Geometric matching criteria is the process of precisely matching, superimposing together, identical surface feature elements in a data set.
And finally, taking the farmland vector boundary in the high-precision farmland vector data as a constraint condition, and adopting a scale set segmentation algorithm to segment the synthetic image into object layers with upper and lower topological association relations, namely an upper farmland block layer and a lower image object layer. The object is an image block composed of homogeneous pixels and is a basic unit for rice identification. The land parcel consists of one or more objects, and the rice extraction result of the object layer is transmitted to the cultivated land parcel layer through inheritance relationship.
In the embodiment of the present invention, step S106 includes the following steps:
calculating target parameters of each object in the image object layer, wherein the target parameters include: the method comprises the following steps of obtaining a blue band ratio and a near-infrared band ratio, wherein the blue band ratio is the ratio between the blue band value of the multispectral remote sensing image data in the transplanting period and the blue band value of the multispectral remote sensing image data in the heading period, and the near-infrared band ratio is the ratio between the near-infrared band value of the multispectral remote sensing image data in the heading period and the near-infrared band value of the multispectral remote sensing image data in the transplanting period;
and calculating the waveband parameter based on the target parameter.
In the embodiment of the present invention, the ratio change detection assumes that the regions that do not change between the two images generally have the same or similar gray-level values, and the corresponding gray-level values of the changed regions have larger differences. The wave band ratio is obtained by dividing the corresponding wave bands of the front and back two-stage images, and the changed area wave band ratio has larger difference with the background value. According to the characteristic that the rice is water body on the image of the transplanting period and dense vegetation on the image of the heading period, the blue wave band and the near infrared wave band between the two images change most.
Blue wave band (0.45-0.52)
) Attenuation coefficient of water bodyThe part with the smallest and weakest scattering has the largest penetrating power to water, underwater details can be obtained, and the part is positioned in the green absorption area of the green vegetation leaves, so the gray value of the blue wave band of the water body in the transplanting period is greater than the gray value of the blue wave band of the vegetation in the heading period, the blue wave band of the image in the transplanting period is divided by the blue wave band of the image in the heading period, and the ratio of the blue wave band of each image object is obtained
。
Near infrared band (0.76-0.90)
) The near-infrared band of the vegetation in the heading stage is far greater than that of the water body in the transplanting stage, and the near-infrared band of the image in the heading stage is divided by the near-infrared band of the image in the transplanting stage to obtain the near-infrared band ratio of each image object
。
Although the rice can be well distinguished from the background by using the two characteristics of the blue-band ratio and the near-infrared-band ratio, a small amount of natural vegetation, other crops and high-sediment water are mixed sometimes, the natural vegetation and other crops can be removed by using the over-high ratio of the near-infrared-band in the transplanting period and the over-low ratio of the near-infrared-band in the heading period, and the high-sediment water can be removed by using the over-high ratio of the blue-band in the heading period.
After the wave band ratio is calculated, calculating the near infrared wave band ratio of each image object in the transplanting period
And ratio of near-infrared band at heading stage
And ratio of blue band at heading stage
. The ratio refers to a ratio of the luminance of a specific band to the total luminance of all bands.
In the formula
The blue, green, red and near infrared wave bands are adopted in the transplanting period,
the ear sprouting period is blue, green, red and near infrared wave bands.
In the embodiment of the present invention, step S108 includes the following steps:
determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the wave band parameters, wherein the method comprises the following steps:
based on the wave band parameters, calculating characteristic values of blue wave band ratio and near-infrared wave band ratio of all objects in the image object layer, wherein the characteristic values comprise: mean and variance;
determining a target threshold value based on the characteristic values of the blue band ratio and the near-infrared band ratio, wherein the target threshold value comprises: a threshold value of the blue band ratio and a threshold value of the near-infrared band ratio;
and determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the target threshold and the wave band parameters.
Specifically, the method for determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the target threshold and the band parameters comprises the following steps:
determining an object with the blue band ratio being greater than the threshold of the blue band ratio and the near-infrared band ratio being greater than the threshold of the near-infrared band ratio as a first target object;
based on the band parameters, removing the second target object from the first target object to obtain a third target object, wherein the second target object comprises: the first target object is a first target object, wherein the ratio of the brightness of the near-infrared band to the total brightness in the transplanting period is larger than a first preset threshold value, or the ratio of the brightness of the near-infrared band to the total brightness in the heading period is smaller than the first preset threshold value, and the ratio of the blue band in the heading period is larger than a second preset threshold value;
transmitting a fourth target object with the rice area larger than a preset threshold value in the third target object to a cultivated land block layer through an inheritance relationship to obtain a target cultivated land block layer;
constructing first vector data based on the fourth target object, and constructing second vector data based on the target farmland block layer;
and determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the first vector data and the second vector data.
In the embodiment of the invention, the average values of the blue band ratio and the near-infrared band ratio of all the image objects are respectively counted
Sum variance
And self-adaptively determining the threshold value by adopting a mean-variance method.
In the formula (I), the compound is shown in the specification,
、
、
respectively a threshold value, a mean value and a standard deviation of the blue band ratio; a is an empirical coefficient.
In the formula (I), the compound is shown in the specification,
、
、
are respectively provided withThe threshold value, the average value and the standard deviation of the ratio of the near infrared band are obtained; b is an empirical coefficient.
And establishing a combined judgment rule model to extract the rice information of the object layer according to the principle that the water body characteristics of the rice in the transplanting period are changed into the dense vegetation characteristics in the heading period and the change is the largest.
If Blue Index> 
AND NIR Index> 
the then target layer rice;
if necessary, the band ratio is further optimized.
If 
>0.25 OR 
<0.25 Removing mixed vegetation from the then;
If 
>0.08 Removing the mixed water body from the then;
then, the rice area of the object layer which is more than 85 percent (the percentage can be determined according to the requirements of users) is transferred to the block layer through the inheritance relationship.
If Relative Area of object-layer rice >0.85 the parcel-layer rice.
Finally, the rice extraction results of the land layer and the object layer are respectively led out in a point and surface vector form together with attribute information such as a blue wave band ratio, a near infrared wave band ratio and the like, and the led-out land layer point vector can be automatically hung to an original cultivated land vector layer and is used for counting the rice planting area in the cultivated land, so that the influence of the spatial resolution of the used remote sensing image and elements such as ridges, ditches and the like on the area precision is avoided, and the consistency of the area precision is ensured; the object level vector can be used for counting and analyzing the newly-added rice planting area outside the original cultivated land, and finally, a statistical report and a rice space distribution map are obtained.
The embodiment of the invention overcomes the defects of low attribute and area precision of rice extraction in the prior art, only four-waveband multispectral images and corresponding farmland vector data in a rice transplanting period and a heading period are needed to be input, full-automatic and high-precision identification of rice is realized through detection based on object ratio change, the area calculation is based on the farmland vector with high precision, the influence of factors such as spatial resolution of used remote sensing images, ridges and channels is avoided, and the consistency of area precision is ensured.
The embodiment of the invention has a solid remote sensing physical foundation, is simple in algorithm, independent of samples, strong in transportability and interpretability, and can be used for monitoring the rice planting condition in any region of the world.
The second embodiment:
the embodiment of the invention also provides a device for extracting the rice planting area and the spatial distribution based on the change detection, which is used for executing the method for extracting the rice planting area and the spatial distribution based on the change detection provided by the embodiment of the invention.
As shown in fig. 2, fig. 2 is a schematic diagram of the above-mentioned rice planting area and spatial distribution extracting apparatus based on change detection, and the rice planting area and spatial distribution extracting apparatus based on change detection includes:
an obtaining unit 10, configured to obtain target data of an area to be extracted in a preset period, where the preset period includes: the transplanting period of the rice and the heading period of the rice, and the target data comprises: multispectral remote sensing image data and high-precision farmland vector data;
the processing unit 20 is configured to process the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer, where a topological association relationship exists between the image object layer and the farmland block layer;
a calculating unit 30, configured to calculate a band parameter of each object in the image object layer, where the band parameter includes: a ratio between a luminance of a target band and a total luminance, the target band including: transplanting period near infrared wave band, heading period near infrared wave band and heading period blue wave band, wherein the total brightness is the sum of the brightness of each wave band in the multispectral remote sensing image data corresponding to the preset period;
and the determining unit 40 is used for determining the planting area and the spatial distribution condition of the rice in the area to be extracted based on the wave band parameters.
In the embodiment of the present invention, target data of a region to be extracted in a preset period is acquired, where the preset period includes: the transplanting period of the rice and the heading period of the rice, and the target data comprise: multispectral remote sensing image data and high-precision farmland vector data; processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer, wherein the image object layer and the farmland block layer have a topological association relationship; calculating the wave band parameters of each object in the image object layer, wherein the wave band parameters comprise: -a ratio between the brightness of a target band and the overall brightness, said target band comprising: transplanting period near infrared wave band, heading period near infrared wave band and heading period blue wave band, wherein the total brightness is the sum of the brightness of each wave band in the multispectral remote sensing image data corresponding to the preset period; based on the wave band parameters, the planting area and the spatial distribution condition of the rice in the area to be extracted are determined, the purpose of efficiently and accurately extracting the planting area and the spatial distribution of the rice is achieved, the technical problem that the extraction efficiency and the extraction precision of the existing extraction method for the planting area and the spatial distribution of the rice are low is solved, and the technical effect of improving the extraction efficiency and the extraction precision of the extraction method for the planting area and the spatial distribution of the rice is achieved.
Example three:
an embodiment of the present invention further provides an electronic device, including a memory and a processor, where the memory is used to store a program that supports the processor to execute the method described in the first embodiment, and the processor is configured to execute the program stored in the memory.
Referring to fig. 3, an embodiment of the present invention further provides an electronic device 100, including: the device comprises a processor 50, a memory 51, a bus 52 and a communication interface 53, wherein the processor 50, the communication interface 53 and the memory 51 are connected through the bus 52; the processor 50 is arranged to execute executable modules, such as computer programs, stored in the memory 51.
The Memory 51 may include a Random Access Memory (RAM) and a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 53 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The bus 52 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 3, but this does not indicate only one bus or one type of bus.
The memory 51 is used for storing a program, the processor 50 executes the program after receiving an execution instruction, and the method executed by the apparatus defined by the flow process disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 50, or implemented by the processor 50.
The processor 50 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 50. The Processor 50 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, etc. as is well known in the art. The storage medium is located in the memory 51, and the processor 50 reads the information in the memory 51 and completes the steps of the method in combination with the hardware thereof.
Example four:
the embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the method in the first embodiment.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as being fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in a specific case to those of ordinary skill in the art.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units into only one type of logical function may be implemented in other ways, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the following descriptions are only illustrative and not restrictive, and that the scope of the present invention is not limited to the above embodiments: those skilled in the art can still make modifications or changes to the embodiments described in the foregoing embodiments, or make equivalent substitutions for some features, within the scope of the disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A rice planting area and space distribution extraction method based on change detection is characterized by comprising the following steps:
acquiring target data of a region to be extracted in a preset period, wherein the preset period comprises the following steps: the transplanting period of the rice and the heading period of the rice, and the target data comprises: multispectral remote sensing image data and high-precision farmland vector data;
processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer, wherein the image object layer and the farmland block layer have a topological association relationship;
calculating the wave band parameters of each object in the image object layer, wherein the wave band parameters comprise: a ratio between a luminance of a target band and a total luminance, the target band including: transplanting period near infrared wave band, heading period near infrared wave band and heading period blue wave band, wherein the total brightness is the sum of the brightness of each wave band in the multispectral remote sensing image data corresponding to the preset period;
and determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the wave band parameters.
2. The method of claim 1, wherein processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer comprises:
preprocessing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain target multispectral remote sensing image data, wherein the preprocessing comprises the following steps: radiometric calibration processing, atmospheric correction processing, orthometric correction processing and geometric registration processing;
merging the target multispectral remote sensing image data to obtain merged data;
and segmenting the merged data based on the high-precision farmland vector data and a scale set segmentation algorithm to obtain the farmland block layer and the image object layer, wherein the image object layer comprises a plurality of objects, the objects consist of homogeneous pixels, the farmland block layer comprises a plurality of blocks, and one block comprises one or more objects.
3. The method of claim 1, wherein calculating the band parameters for each object in the image object layer comprises:
calculating target parameters of each object in the image object layer, wherein the target parameters comprise: the method comprises the following steps of obtaining a blue band ratio and a near-infrared band ratio, wherein the blue band ratio is the ratio between the blue band value of the multispectral remote sensing image data in the transplanting period and the blue band value of the multispectral remote sensing image data in the heading period, and the near-infrared band ratio is the ratio between the near-infrared band value of the multispectral remote sensing image data in the heading period and the near-infrared band value of the multispectral remote sensing image data in the transplanting period;
and calculating the waveband parameters based on the target parameters.
4. The method according to claim 3, wherein the determining of the planting area and the spatial distribution of the rice in the region to be extracted based on the waveband parameters comprises:
based on the wave band parameters, calculating characteristic values of blue wave band ratio and near-infrared wave band ratio of all objects in the image object layer, wherein the characteristic values comprise: mean and variance;
determining a target threshold value based on the characteristic values of the blue band ratio and the near-infrared band ratio, wherein the target threshold value comprises: a threshold value of the blue band ratio and a threshold value of the near-infrared band ratio;
and determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the target threshold and the wave band parameters.
5. The method according to claim 4, wherein the determining of the planting area and the spatial distribution of the rice in the region to be extracted based on the target threshold and the band parameters comprises:
determining an object with the blue band ratio being greater than the threshold of the blue band ratio and the near-infrared band ratio being greater than the threshold of the near-infrared band ratio as a first target object;
based on the band parameters, removing a second target object from the first target object to obtain a third target object, wherein the second target object comprises: the first target object is a first target object, wherein the ratio of the brightness of the near-infrared band to the total brightness in the transplanting period is larger than a first preset threshold value, or the ratio of the brightness of the near-infrared band to the total brightness in the heading period is smaller than the first preset threshold value, and the ratio of the blue band in the heading period is larger than a second preset threshold value;
transmitting a fourth target object with the rice area larger than a preset threshold value in the third target object to a cultivated land block layer through an inheritance relationship to obtain a target cultivated land block layer;
constructing first vector data based on the fourth target object, and constructing second vector data based on the target farmland block layer;
and determining the planting area and the spatial distribution condition of the rice in the region to be extracted based on the first vector data and the second vector data.
6. The utility model provides a rice planting area and spatial distribution extraction element based on change detects which characterized in that includes:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring target data of a region to be extracted in a preset period, and the preset period comprises the following steps: the transplanting period of the rice and the heading period of the rice, and the target data comprises: multispectral remote sensing image data and high-precision farmland vector data;
the processing unit is used for processing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain a farmland block layer and an image object layer, wherein the image object layer and the farmland block layer have a topological association relationship;
a calculating unit, configured to calculate a band parameter of each object in the image object layer, where the band parameter includes: -a ratio between the brightness of a target band and the overall brightness, said target band comprising: transplanting period near infrared wave band, heading period near infrared wave band and heading period blue wave band, wherein the total brightness is the sum of the brightness of each wave band in the multispectral remote sensing image data corresponding to the preset period;
and the determining unit is used for determining the planting area and the spatial distribution condition of the rice in the area to be extracted based on the waveband parameters.
7. The apparatus according to claim 6, wherein the processing unit is configured to:
preprocessing the multispectral remote sensing image data based on the high-precision farmland vector data to obtain target multispectral remote sensing image data, wherein the preprocessing comprises the following steps: radiometric calibration processing, atmospheric correction processing, orthometric correction processing and geometric registration processing;
merging the target multispectral remote sensing image data to obtain merged data;
and segmenting the merged data based on the high-precision farmland vector data and a scale set segmentation algorithm to obtain the farmland block layer and the image object layer, wherein the image object layer comprises a plurality of objects, the objects consist of homogeneous pixels, the farmland block layer comprises a plurality of blocks, and one block comprises one or more objects.
8. The apparatus according to claim 6, wherein the computing unit is configured to:
calculating target parameters of each object in the image object layer, wherein the target parameters include: the method comprises the following steps of obtaining a blue band ratio and a near infrared band ratio, wherein the blue band ratio is the ratio between a blue band value of multispectral remote sensing image data in a transplanting period and a blue band value of multispectral remote sensing image data in a heading period, and the near infrared band ratio is the ratio between a near infrared band value of the multispectral remote sensing image data in the heading period and a near infrared band value of the multispectral remote sensing image data in the transplanting period;
and calculating the waveband parameter based on the target parameter.
9. An electronic device comprising a memory for storing a program that enables a processor to perform the method of any of claims 1 to 5 and a processor configured to execute the program stored in the memory.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of the claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211568345.8A CN115631419B (en) | 2022-12-08 | 2022-12-08 | Rice planting area and spatial distribution extraction method and device based on change detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211568345.8A CN115631419B (en) | 2022-12-08 | 2022-12-08 | Rice planting area and spatial distribution extraction method and device based on change detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115631419A true CN115631419A (en) | 2023-01-20 |
| CN115631419B CN115631419B (en) | 2023-05-09 |
Family
ID=84909927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211568345.8A Active CN115631419B (en) | 2022-12-08 | 2022-12-08 | Rice planting area and spatial distribution extraction method and device based on change detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115631419B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115995005A (en) * | 2023-03-22 | 2023-04-21 | 航天宏图信息技术股份有限公司 | Crop extraction method and device based on single-period high-resolution remote sensing image |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740759A (en) * | 2016-01-15 | 2016-07-06 | 武汉珈和科技有限公司 | Middle-season rice information decision tree classification method based on multi-temporal data feature extraction |
| CN110472184A (en) * | 2019-08-22 | 2019-11-19 | 电子科技大学 | A kind of cloudy misty rain area rice recognition methods based on Landsat remotely-sensed data |
| US20200141877A1 (en) * | 2018-11-06 | 2020-05-07 | Nanjing Agricultural University | Method for estimating aboveground biomass of rice based on multi-spectral images of unmanned aerial vehicle |
| CN112818749A (en) * | 2020-12-31 | 2021-05-18 | 中国电子科技集团公司第二十七研究所 | Multi-cropping mode remote sensing monitoring method for bulk grain and oil crops in double cropping area of one year |
| CN114821362A (en) * | 2022-07-01 | 2022-07-29 | 江苏省水利科学研究院 | Multi-source data-based rice planting area extraction method |
-
2022
- 2022-12-08 CN CN202211568345.8A patent/CN115631419B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740759A (en) * | 2016-01-15 | 2016-07-06 | 武汉珈和科技有限公司 | Middle-season rice information decision tree classification method based on multi-temporal data feature extraction |
| US20200141877A1 (en) * | 2018-11-06 | 2020-05-07 | Nanjing Agricultural University | Method for estimating aboveground biomass of rice based on multi-spectral images of unmanned aerial vehicle |
| CN110472184A (en) * | 2019-08-22 | 2019-11-19 | 电子科技大学 | A kind of cloudy misty rain area rice recognition methods based on Landsat remotely-sensed data |
| CN112818749A (en) * | 2020-12-31 | 2021-05-18 | 中国电子科技集团公司第二十七研究所 | Multi-cropping mode remote sensing monitoring method for bulk grain and oil crops in double cropping area of one year |
| CN114821362A (en) * | 2022-07-01 | 2022-07-29 | 江苏省水利科学研究院 | Multi-source data-based rice planting area extraction method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115995005A (en) * | 2023-03-22 | 2023-04-21 | 航天宏图信息技术股份有限公司 | Crop extraction method and device based on single-period high-resolution remote sensing image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115631419B (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Early season detection of rice plants using RGB, NIR-GB and multispectral images from unmanned aerial vehicle (UAV) | |
| US11521380B2 (en) | Shadow and cloud masking for remote sensing images in agriculture applications using a multilayer perceptron | |
| Zhang et al. | Growth monitoring of greenhouse lettuce based on a convolutional neural network | |
| CN111242224B (en) | Multi-source remote sensing data classification method based on unmanned aerial vehicle extraction classification sample points | |
| CN110751019B (en) | High-resolution image crop automatic extraction method and device based on deep learning | |
| Zhao et al. | Mapping rice paddies in complex landscapes with convolutional neural networks and phenological metrics | |
| CN112001374B (en) | Cloud detection method and device for hyperspectral image | |
| CN110796001A (en) | Satellite image film-covering farmland identification and extraction method and system | |
| CN114821362B (en) | Multi-source data-based rice planting area extraction method | |
| Wang et al. | Unsupervised discrimination between lodged and non-lodged winter wheat: A case study using a low-cost unmanned aerial vehicle | |
| CN108764284B (en) | Classification and denoising method and system for high-resolution image of dead pine | |
| CN110647932B (en) | Planting crop structure remote sensing image classification method and device | |
| CN114926748A (en) | Soybean remote sensing identification method combining Sentinel-1/2 microwave and optical multispectral images | |
| Liang et al. | Improved estimation of aboveground biomass in rubber plantations by fusing spectral and textural information from UAV-based RGB imagery | |
| CN116543316B (en) | Method for identifying turf in paddy field by utilizing multi-time-phase high-resolution satellite image | |
| CN115631419B (en) | Rice planting area and spatial distribution extraction method and device based on change detection | |
| CN110610438B (en) | Crop canopy petiole included angle calculation method and system | |
| CN115861629A (en) | High-resolution farmland image extraction method | |
| Guo et al. | Panicle Ratio Network: streamlining rice panicle measurement by deep learning with ultra-high-definition aerial images in the field | |
| Kim et al. | Growth monitoring of field-grown onion and garlic by CIE L* a* b* color space and region-based crop segmentation of UAV RGB images | |
| CN115995005B (en) | Crop extraction method and device based on single-period high-resolution remote sensing image | |
| CN110059890B (en) | County scale agricultural flood monitoring method and system | |
| CN109784320B (en) | Ginseng facility agricultural domain determination method | |
| Concepcion II et al. | A novel artificial bee colony-optimized visible oblique dipyramid greenness index for vision-based aquaponic lettuce biophysical signatures estimation | |
| CN115035423A (en) | Hybrid rice male and female parent identification and extraction method based on unmanned aerial vehicle remote sensing image |
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 |