CN112016391B - Fishpond identification method, system and medium based on high-resolution satellite remote sensing image - Google Patents
Fishpond identification method, system and medium based on high-resolution satellite remote sensing image Download PDFInfo
- Publication number
- CN112016391B CN112016391B CN202010684264.9A CN202010684264A CN112016391B CN 112016391 B CN112016391 B CN 112016391B CN 202010684264 A CN202010684264 A CN 202010684264A CN 112016391 B CN112016391 B CN 112016391B
- Authority
- CN
- China
- Prior art keywords
- vector
- fishpond
- vegetation
- processing
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 239000013598 vector Substances 0.000 claims abstract description 115
- 238000012545 processing Methods 0.000 claims abstract description 58
- 238000002310 reflectometry Methods 0.000 claims abstract description 33
- 230000011218 segmentation Effects 0.000 claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 25
- 230000002146 bilateral effect Effects 0.000 claims abstract description 21
- 238000001914 filtration Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 241000251468 Actinopterygii Species 0.000 claims description 43
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 238000004381 surface treatment Methods 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 2
- 238000003672 processing method Methods 0.000 abstract description 6
- 238000009360 aquaculture Methods 0.000 description 19
- 244000144974 aquaculture Species 0.000 description 19
- 230000000694 effects Effects 0.000 description 13
- 230000001186 cumulative effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000011835 investigation Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- 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
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The invention provides a fishpond identification method, a fishpond identification system and a fishpond identification medium based on a high-resolution satellite remote sensing image, wherein the fishpond identification method comprises the steps of preprocessing the high-resolution satellite remote sensing image to obtain reflectivity data comprising geometric positioning; processing by using bilateral filtering, OTSU algorithm segmentation and open operation image processing methods based on reflectivity data to obtain an initial fishpond vector result; based on the reflectivity data, extracting an initial fishpond vector result of a vegetation coverage vector result and a vegetation coverage vector result by using NDVI, and performing vector erasure operation; and carrying out smooth surface operation on the candidate fishpond vector, and carrying out manual intervention to obtain a fishpond final extraction result. The invention adopts the high-resolution satellite remote sensing image, forms a flow method of automatic fishpond extraction through a series of image processing methods, can reduce the workload of manually identifying and extracting the fishpond, reduces the experience error caused by manual intervention, realizes the automation of the identification method and improves the working efficiency.
Description
Technical Field
The invention belongs to the field of remote sensing image processing, and particularly relates to a fishpond identification method, a fishpond identification system and a fishpond identification medium based on high-resolution satellite remote sensing images.
Background
Due to the rapid increase of resident demands, driven by two factors of policy and science and technology, the aquaculture industry of China gets rapid development in quite a long time, and becomes the first large aquaculture country in the world, and the only country with the aquaculture yield exceeding the fishing yield in the world, wherein the aquaculture yield of a fishpond accounts for 49% of the total aquaculture yield of China. However, it is important that the difficulty of aquaculture management is continually increasing while the aquaculture industry is rapidly developing. The water-producing aquaculture industry shows a dynamic change process of the total amount of water resources required by aquaculture in different development stages; and the water resources of aquaculture are widely distributed by the wide operators in China, and the bottoms of the water resources of aquaculture in China are difficult to be scientifically and accurately touched and the dynamic changes of the water resources are difficult to be mastered by means of the traditional field investigation method.
With the continuous development and perfection of remote sensing technology, increasingly abundant remote sensing data provides a opportunity for resource investigation. In order to strengthen the monitoring of aquaculture resources, the current situation of the space position and the area of aquaculture in China is accurately grasped, the bottom of aquaculture industry is cleared, the aquaculture layout is reasonably planned, the aquaculture development level and the comprehensive effect are further improved, and satellite image technology becomes an effective means for resource investigation and monitoring. Meanwhile, satellite remote sensing data has the advantages of more time, short period, wide coverage range, abundant ground information reflection and the like, can dynamically and objectively record ground surface information in real time, provides favorable conditions for tracking and observing, and becomes an important data source for dynamic monitoring of aquaculture.
The fish pond information is extracted from the satellite remote sensing image, so that the fish pond distribution range and the fish pond cultivation area can be mastered, the fish industry cultivation scale and the fish industry cultivation yield can be estimated, the reasonable layout of the aquaculture industry is guided, and the regional economic development is promoted. The high-resolution satellite remote sensing data has the outstanding characteristic of high spatial resolution, has more abundant structural information and texture information, shows sufficient advantages in the refined extraction direction, has a better extraction effect on a small fishpond, and can effectively identify fishpond information.
But the current fishpond identification and extraction by using remote sensing images is mainly carried out by vectorization through manual sketching, is too dependent on manpower, has low automation degree and low efficiency, and severely restricts the large-scale, accurate and efficient monitoring of the dynamic change of the aquaculture industry.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a fishpond identification method based on high-resolution satellite remote sensing images, which can reduce the workload of manually identifying and extracting fishponds, reduce experience errors caused by manual intervention, realize automation of the identification method and improve the working efficiency.
The invention further provides a fishpond identification system based on the high-resolution satellite remote sensing image.
The invention also provides a medium for implementing the fishpond identification method based on the high-resolution satellite remote sensing image.
According to an embodiment of the first aspect of the invention, the fishpond identification method based on the high-resolution satellite remote sensing image comprises the following steps:
acquiring a high-resolution satellite remote sensing image, and preprocessing the image to obtain reflectivity data comprising geometric positioning; processing the reflectivity data based on bilateral filtering, an OTSU algorithm, open operation morphology and NDVI to obtain an initial pond vector result and a vegetation coverage vector result; performing vector wiping operation on the initial pond vector result and the vegetation coverage vector result, and removing the pseudo pond vector of the vegetation area to obtain a non-vegetation area candidate pond vector; and processing the candidate pond vectors to obtain a final pond extraction result.
According to the embodiment of the invention, the fishpond identification method based on the high-resolution satellite remote sensing image has at least the following beneficial effects:
compared with the methods of field investigation, statistics of the distribution position and the cultivation area of the fishpond, digitization by manually drawing the vector of the fishpond and the like, the fishpond identification method based on the high-resolution satellite remote sensing image provided by the embodiment of the invention has the advantages that the automation degree of identifying and extracting the fishpond is high, the manual intervention is less, the vector result of the fishpond can be quickly obtained in a short time, the fishpond identification and extraction efficiency is improved, the manual workload is reduced, and the interference error of the manual experience is reduced.
According to some embodiments of the invention, the preprocessing includes radiometric calibration, atmospheric correction, and orthographic correction.
According to some embodiments of the invention, the processing the reflectivity data includes:
A. extracting a 4 th wave band of the reflectivity data, processing the wave band through bilateral filtering of a nonlinear filter, and taking the spatial distance relation and the color similarity of pixels into calculation, reserving a target edge of the image and smoothing internal details; B. c, carrying out threshold segmentation on the image processed in the step A based on the maximum inter-class variance method of an OTSU algorithm, automatically calculating to obtain an optimal segmentation threshold of the fish pond and the non-fish pond area, and carrying out binarization processing according to the threshold; C. b, performing open operation morphological processing on the binary image obtained in the step B; D. carrying out vectorization processing on the image subjected to the open operation processing in the step C to obtain vector data; E. and setting area thresholds D and D according to the minimum and maximum counted fish pond area values, and deleting vectors smaller than the thresholds D and larger than the thresholds D to obtain an initial fish pond vector result.
According to some embodiments of the invention, the processing the reflectivity data further comprises:
F. performing band operation on the reflectivity data based on NDVI, determining a vegetation and non-vegetation area segmentation threshold according to an actual operation result, and performing binarization processing according to the vegetation and non-vegetation area segmentation threshold; G. and F, carrying out vectorization processing on the image subjected to binarization processing in the step F, calculating the area of the minimum vegetation area according to actual conditions, and deleting candidate vegetation vectors with the area smaller than the area of the minimum vegetation area to obtain a vegetation vector result.
According to some embodiments of the invention, the vector erasure operation includes:
setting the initial pond vector as an input element, and setting the vegetation vector as an erasing element; creating element classes by superimposing the input element with polygons of the erasure element; copying the part of the input element outside the outer boundary of the erasing element to the output element class to obtain a fishpond vector of the non-vegetation area.
According to some embodiments of the invention, the processing the candidate pond vector comprises: and carrying out smooth surface treatment on the candidate fish pond vectors, smoothing vector boundaries and removing burrs.
According to some embodiments of the invention, the processing the candidate pond vector comprises: and performing manual intervention on the candidate fishpond vectors to remove wrong fishpond vectors or repair and draw the missed fishpond.
According to a second aspect of the present invention, a fish pond identification system based on high-resolution satellite remote sensing image includes:
the preprocessing module is used for acquiring a high-resolution satellite remote sensing image, preprocessing the image and obtaining reflectivity data comprising geometric positioning; the first processing module is used for processing the reflectivity data based on bilateral filtering, an OTSU algorithm, open operation morphology and NDVI to obtain an initial fishpond vector result and a vegetation coverage vector result; the second processing module is used for carrying out vector erasure operation on the initial fishpond vector result and the vegetation coverage vector result, and removing the pseudo fishpond vector of the vegetation area to obtain a non-vegetation area candidate fishpond vector; and the third processing module is used for processing the candidate fishpond vector to obtain a fishpond final extraction result.
The fishpond identification system based on the high-resolution satellite remote sensing image provided by the embodiment of the invention has at least the following beneficial effects:
compared with methods of field investigation, statistics of the distribution position and the cultivation area of the fishpond, digitization by manually drawing the fishpond vector and the like, the fishpond identification system based on the high-resolution satellite remote sensing image provided by the embodiment of the invention has the advantages that the automation degree of fishpond identification and extraction is high, manual intervention is less, the fishpond vector result can be obtained quickly in a short time, the fishpond identification and extraction efficiency is improved, the manual workload is reduced, and the interference error of manual experience is reduced.
According to some embodiments of the invention, the first processing module is configured to process the reflectivity data based on the reflectivity data obtained by the preprocessing module by using a bilateral filtering, OTSU algorithm segmentation and open operation image processing method, so as to obtain an initial fishpond vector result.
A computer readable storage medium according to an embodiment of the third aspect of the present invention has stored thereon program instructions which, when executed by a processor, implement a method according to any of the embodiments of the first aspect of the present invention.
Since the computer-readable storage medium according to the embodiment of the invention stores thereon the computer-executable instructions for executing a fish pond identification method based on a high-resolution satellite remote sensing image according to any one of the first aspect of the invention, all the advantages of the first aspect of the invention are achieved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flow chart of a pond extraction process according to an embodiment of the present invention;
FIG. 2 is a satellite remote sensing image of an embodiment of the present invention;
FIG. 3 is a diagram of a bilateral filtering effect according to an embodiment of the present invention;
FIG. 4 is a graph of the OTSU threshold segmentation effect of an embodiment of the present invention;
FIG. 5 is an initial vector diagram of a fish pond according to an embodiment of the present invention;
FIG. 6 is a final extraction of a pond according to an embodiment of the present invention;
fig. 7 is an enlarged view of the effect of the extraction of the fish pond according to the embodiment of the invention;
fig. 8 is a system block diagram of an embodiment of the present invention.
Detailed Description
The conception, specific structure, and technical effects produced by the present invention will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, aspects, and effects of the present invention.
Referring to fig. 1, an embodiment of the invention provides a fishpond identification method based on high-resolution satellite remote sensing images, which comprises the following steps:
step 1, acquiring a high-resolution satellite remote sensing image (refer to fig. 2), and preprocessing the image to obtain reflectivity data with accurate geometric positioning;
in some embodiments, domestic GF2 remote sensing data is used as the input image, the data is a 0.8 m high resolution multispectral image, the scaling factor provided by the resource satellite center is used for radiometric scaling, the flashh atmospheric correction model is used for performing atmospheric correction processing on the image, then 10 m resolution DEM data is selected for performing orthographic correction on the image, and the raw data is processed into reflectivity data with accurate geometric positioning through the above preprocessing steps.
Step 2, processing by using a bilateral filtering, OTSU segmentation and division operation image processing method to obtain an initial fishpond vector result;
in some embodiments, the 4 th band image after preprocessing is selected as the data to be processed, the edge is enhanced, the internal texture is smoothed, the segmentation effect is improved, and the initial pond vector is extracted by using an image processing method, and the specific implementation mode is as follows:
step 2.1, selecting a nonlinear filter to perform bilateral filtering on the preprocessed 4 th band image, and taking the spatial distance relation and the color similarity of pixels into calculation, so that the edge of the fish pond is effectively reserved and the internal details are smoothed;
due to the diversity and complexity of the high-resolution images, the images are inevitably subjected to noise interference, region erroneous segmentation and the like, and in order to improve the accuracy of the extraction of the edges of the fishpond, the images are processed by bilateral filtering, edge protection and denoising are performed, edge information is enhanced, and the internal textures of the fishpond are smoothed.
Bilateral filtering is a nonlinear filter that is effective in preserving object edges and smoothing object internal details. It uses a weighted average method, using a weighted average of the surrounding pixel brightness values to represent the intensity of a certain pixel, the weighted average being based on a gaussian distribution. The bilateral filtering is used for calculating the weight of the center pixel, not only considering the Euclidean distance of the pixel, but also considering the radiation difference (such as the similarity degree between the pixel and the center pixel in a convolution kernel, the color intensity, the depth distance and the like) in the pixel range domain, and simultaneously taking the spatial distance relation and the color similarity of the pixel into calculation, so that when the image is filtered, the non-edge detail part of the target in the image can be smoothed, and meanwhile, the edge information of the target can be reserved.
The principle formula of bilateral filtering is as follows:
h(x)＝k -1 ∫∫f(ξ)c(ξ，x)s(f(ξ)，f(x))dξ
k(x)＝∫∫c(ξ，x)s(f(ξ)，f(x))dξ
wherein, c (ζ, x) and s (f (ζ), f (x)) have the following calculation formula:
for the discretized image, the principle formula of bilateral filtering is rewritten as:
in some embodiments, the diameter of the bilateral filtering window is set to 25 pixels, the variance of the pixel value range is 10, the variance of the space range is 10, the effect of the bilateral filtering processing of the image is shown in fig. 3, the information of the edge of the fish pond is enhanced, the internal details are smoothed, and the subsequent information extraction of the fish pond is facilitated.
Step 2.2, performing threshold segmentation by using an OTSU maximum inter-class variance method, automatically calculating to obtain an optimal segmentation threshold of the fish pond and non-fish pond areas, and performing binarization according to the threshold;
the OTSU method was first proposed by the japan oxford, also known as the oxford method or the maximum inter-class variance method. According to the method, the maximum inter-class variance between a target and a background is used as a threshold selection criterion according to a one-dimensional histogram of an image. The method is simple, has high treatment speed, and is especially suitable for fishpond extraction.
The basic idea of the OTSU method is as follows: firstly, calculating normalized histogram of image, assuming that gray level of image is L and number of pixels with gray value of i is n i Wherein i is E [0, L]Then the total pixels of the image areThe probability of the gray value i is P i ＝n i N. Then, the cumulative probability and the cumulative mean are calculated, and assuming that the found segmentation threshold is T, the segmentation threshold smaller than T is classified into one class, the segmentation threshold larger than T is classified into the other class, and the cumulative probability P (T) and the intra-class mean mu (T) can be obtained according to the previous probability and mean calculation formula, wherein the specific calculation formula is as follows:
wherein P is 0 (T) is the cumulative probability of the foreground, μ 0 (T) is the intra-class mean of the foreground, P 1 (T) is the cumulative probability of the background, μ 1 And (T) is the intra-class mean of the background.
Then, the intra-class mean and the cumulative probability calculated according to the above formula are calculated, and the inter-class variance sigma (T) is calculated according to the following specific calculation formula:
σ(T)＝P 0 (T)×P 1 (T)×(μ 0 (T)-μ 1 (T)) 2
and defines a threshold value for maximizing sigma (T) as an optimal threshold value.
In some embodiments, the OTSU method is used to calculate the optimal segmentation threshold T for the image after bilateral filtering, calculate the result threshold t=9, binarize the image with the threshold, assign the pixels greater than T to 0, and assign the pixels less than T to 1, and the segmentation effect is shown in fig. 4.
Step 2.3, performing open operation morphological treatment on the binary image obtained in the previous step, namely firstly corroding and then expanding, eliminating small objects, separating the objects at fine points, smoothing the boundary of a larger object, and simultaneously, not obviously changing the area of the object;
after the image is segmented by the OTSU method, the obtained target edge may have the conditions of burr protrusion, adjacent target adhesion and the like, so that the accurate boundary extraction of the subsequent fishpond is influenced, the accuracy is reduced, and therefore, after the image is binarized to obtain a preliminary result, the preliminary result is processed by adopting a mathematical morphology method, and the subsequent extraction effect is improved.
Mathematical morphology is also called image algebra, and the basic idea is to measure and extract the corresponding shape in the image by using structural elements with a certain shape, so as to achieve the purposes of image analysis and identification. The basic operation of mathematical morphology has four: expansion, corrosion, open operation and closed operation.
In some embodiments, the binarized image is subjected to open operation morphological processing, namely, the initial result is subjected to corrosion-before-expansion operation, the adhered adjacent fishponds are separated, the boundaries of the fishponds are smoothed, and part of non-fishpond pixel point interference is removed, so that the completeness and accuracy of fishpond extraction are improved.
Step 2.4, vectorizing the image subjected to the open operation processing in the step 2.3 to obtain vector data;
and 2.5, counting the minimum area and the maximum area of the fish pond, setting an area threshold d, and deleting vectors smaller than the threshold d to obtain an initial fish pond vector result.
In some embodiments, the minimum area of the fish pond is 400 square meters, the maximum area is 20000 square meters, vectors with areas smaller than 400 and larger than 20000 square meters are deleted, the initial fish pond vector results are shown in fig. 5, and it can be seen that small broken spots and large area non-fish pond vectors are deleted.
Step 3, based on the reflectivity data obtained in the step 1, using the NDVI to normalize the vegetation index, and extracting a vegetation coverage vector result;
in some embodiments, band operation is performed on the reflectivity data in the step 1 by using a normalized vegetation index NDVI, a vegetation and non-vegetation area segmentation threshold d is determined to be 0.3 according to an actual operation result, pixels larger than the threshold d 0.3 are assigned to 1, and the remaining pixels are assigned to 0, so that binarization is realized; and then vectorizing the binarized image, calculating the minimum vegetation area as 100 square meters according to the actual situation, and deleting candidate vegetation vectors with the area smaller than 100 square meters to obtain a vegetation vector result.
And 4, performing vector erasure operation by using the initial pond vector obtained in the step 2 and the vegetation vector extracted in the step 3. Vector erasure creates element classes by superimposing input elements with polygons of erasure elements, and copies only portions of the input elements outside the outer boundaries of the erasure elements to the output element classes. The initial fishpond vector is used as an input element, the vegetation vector is used as a wiping element, and the pseudo fishpond vector of the vegetation area is removed through wiping operation, so that the fishpond vector of the non-vegetation area is obtained;
and 5, carrying out smooth surface treatment on the candidate fishpond vectors in the step 4, smoothing vector boundaries, removing burrs, carrying out manual intervention, deleting wrong fishpond vectors or repairing and drawing missed fishponds to obtain a final fishpond extraction vector result, wherein fig. 6 is a final extraction result, and fig. 7 is an extraction fishpond amplification effect diagram. The fishpond identification method based on the high-resolution satellite remote sensing image provided by the invention is described in detail.
The invention also provides embodiments of the system corresponding to the previous embodiments. For system embodiments, reference is made to the description of method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the objectives of the disclosed solution. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Referring to fig. 8, fig. 8 is a schematic diagram illustrating a fish pond identification system based on a high-resolution satellite remote sensing image according to an exemplary embodiment of the present invention, including:
the preprocessing module is used for acquiring a high-resolution satellite remote sensing image, preprocessing the image and obtaining reflectivity data comprising geometric positioning;
the first processing module is used for processing the reflectivity data to obtain an initial fishpond vector result and a vegetation coverage vector result;
the second processing module is used for carrying out vector erasure operation on the initial fishpond vector result and the vegetation coverage vector result, and removing the pseudo fishpond vector of the vegetation area to obtain a non-vegetation area candidate fishpond vector;
and the third processing module is used for processing the candidate fishpond vector to obtain a fishpond final extraction result.
In some embodiments, the first processing module is configured to process the reflectivity data based on the reflectivity data obtained by the preprocessing module by using a bilateral filtering, OTSU algorithm segmentation and open operation image processing method, so as to obtain an initial fishpond vector result.
It should be appreciated that the method steps in embodiments of the present invention may be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in non-transitory computer-readable memory. The method may use standard programming techniques. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes (or variations and/or combinations thereof) described herein may be performed under control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications), by hardware, or combinations thereof, collectively executing on one or more processors. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of android computing platform operatively connected to the appropriate. Aspects of the invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and/or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, which when read by a computer, is operable to configure and operate the computer to perform the processes described herein. Further, the machine readable code, or portions thereof, may be transmitted over a wired or wireless network. When such media includes instructions or programs that, in conjunction with a microprocessor or other data processor, implement the steps described above, the invention described herein includes these and other different types of non-transitory computer-readable storage media. The invention may also include the computer itself when programmed according to the methods and techniques of the present invention.
The computer program can be applied to the input data to perform the functions described herein, thereby converting the input data to generate output data that is stored to the non-volatile memory. The output information may also be applied to one or more output devices such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects produced on a display.
The present invention is not limited to the above embodiments, but can be modified, equivalent, improved, etc. by the same means to achieve the technical effects of the present invention, which are included in the spirit and principle of the present invention. Various modifications and variations are possible in the technical solution and/or in the embodiments within the scope of the invention.
Claims (6)
1. A fishpond identification method based on high-resolution satellite remote sensing images is characterized by comprising the following steps of:
acquiring a high-resolution satellite remote sensing image, and preprocessing the image to obtain reflectivity data comprising geometric positioning;
processing the reflectivity data based on bilateral filtering, an OTSU algorithm, open operation morphology and NDVI to obtain an initial fishpond vector result and a vegetation coverage vector result;
performing vector erasure operation on the initial pond vector result and the vegetation coverage vector result, and removing the pseudo pond vector of the vegetation area to obtain a non-vegetation area candidate pond vector;
processing the candidate fishpond vector to obtain a final fishpond extraction result;
wherein said processing said reflectivity data comprises:
A. extracting a 4 th wave band of the reflectivity data, processing the wave band through bilateral filtering of a nonlinear filter, and incorporating the spatial distance relation and the color similarity of pixels into calculation, reserving a target edge of the image and smoothing internal details;
B. c, carrying out threshold segmentation on the image processed in the step A based on the maximum inter-class variance method of an OTSU algorithm, automatically calculating to obtain an optimal segmentation threshold value of the fish pond and non-fish pond areas, and carrying out binarization processing according to the optimal segmentation threshold value of the fish pond and non-fish pond areas;
C. b, performing open operation morphological processing on the binary image obtained in the step B;
D. c, carrying out vectorization processing on the image subjected to the open operation morphological processing in the step C to obtain vector data;
E. setting area thresholds D and D according to the minimum and maximum values of the counted fish pond areas, deleting vectors smaller than the thresholds D and larger than the thresholds D, and obtaining an initial fish pond vector result;
the processing of the reflectivity data further includes:
F. performing band operation on the reflectivity data based on NDVI, determining a vegetation and non-vegetation area segmentation threshold according to an actual operation result, and performing binarization processing according to the vegetation and non-vegetation area segmentation threshold;
G. f, carrying out vectorization treatment on the image subjected to binarization treatment in the step F, calculating the area of the minimum vegetation area according to actual conditions, and deleting candidate vegetation vectors with the area smaller than the area of the minimum vegetation area to obtain a vegetation vector result;
the vector erasure operation includes:
setting the initial pond vector as an input element, and setting the vegetation vector as an erasing element;
creating element classes by superimposing the input element with polygons of the erasure element;
copying the part of the input element outside the outer boundary of the erasing element to the output element class to obtain a fishpond vector of the non-vegetation area.
2. The method for fish pond identification based on high resolution satellite remote sensing images according to claim 1, wherein the preprocessing comprises radiometric calibration, atmospheric correction and orthographic correction.
3. The method for identifying fish ponds based on high resolution satellite remote sensing images of claim 1, wherein the processing of the candidate fish pond vectors includes:
and carrying out smooth surface treatment on the candidate fish pond vector, smoothing vector boundaries and removing burrs.
4. The method for identifying fish ponds based on high resolution satellite remote sensing images of claim 1, wherein the processing of the candidate fish pond vectors includes:
and performing manual intervention on the candidate fishpond vectors to remove wrong fishpond vectors or repair and draw the missed fishponds.
5. A pond identification system based on high-resolution satellite remote sensing image is characterized by comprising:
the preprocessing module is used for acquiring a high-resolution satellite remote sensing image, preprocessing the image and obtaining reflectivity data comprising geometric positioning;
the first processing module is used for processing the reflectivity data based on bilateral filtering, an OTSU algorithm, open operation morphology and NDVI to obtain an initial fishpond vector result and a vegetation coverage vector result;
the second processing module is used for carrying out vector erasure operation on the initial fishpond vector result and the vegetation coverage vector result, and removing the pseudo fishpond vector of the vegetation area to obtain a non-vegetation area candidate fishpond vector;
the third processing module is used for processing the candidate fishpond vector to obtain a fishpond final extraction result;
wherein said processing said reflectivity data comprises:
A. extracting a 4 th wave band of the reflectivity data, processing the wave band through bilateral filtering of a nonlinear filter, and incorporating the spatial distance relation and the color similarity of pixels into calculation, reserving a target edge of the image and smoothing internal details;
B. c, carrying out threshold segmentation on the image processed in the step A based on the maximum inter-class variance method of an OTSU algorithm, automatically calculating to obtain an optimal segmentation threshold value of the fish pond and non-fish pond areas, and carrying out binarization processing according to the optimal segmentation threshold value of the fish pond and non-fish pond areas;
C. b, performing open operation morphological processing on the binary image obtained in the step B;
D. c, carrying out vectorization processing on the image subjected to the open operation morphological processing in the step C to obtain vector data;
E. setting area thresholds D and D according to the minimum and maximum values of the counted fish pond areas, deleting vectors smaller than the thresholds D and larger than the thresholds D, and obtaining an initial fish pond vector result;
the processing of the reflectivity data further includes:
F. performing band operation on the reflectivity data based on NDVI, determining a vegetation and non-vegetation area segmentation threshold according to an actual operation result, and performing binarization processing according to the vegetation and non-vegetation area segmentation threshold;
G. f, carrying out vectorization treatment on the image subjected to binarization treatment in the step F, calculating the area of the minimum vegetation area according to actual conditions, and deleting candidate vegetation vectors with the area smaller than the area of the minimum vegetation area to obtain a vegetation vector result;
the vector erasure operation includes:
setting the initial pond vector as an input element, and setting the vegetation vector as an erasing element;
creating element classes by superimposing the input element with polygons of the erasure element;
copying the part of the input element outside the outer boundary of the erasing element to the output element class to obtain a fishpond vector of the non-vegetation area.
6. A computer readable storage medium, having stored thereon program instructions which, when executed by a processor, implement the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010684264.9A CN112016391B (en) | 2020-07-16 | 2020-07-16 | Fishpond identification method, system and medium based on high-resolution satellite remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010684264.9A CN112016391B (en) | 2020-07-16 | 2020-07-16 | Fishpond identification method, system and medium based on high-resolution satellite remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112016391A CN112016391A (en) | 2020-12-01 |
| CN112016391B true CN112016391B (en) | 2023-12-08 |
Family
ID=73498783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010684264.9A Active CN112016391B (en) | 2020-07-16 | 2020-07-16 | Fishpond identification method, system and medium based on high-resolution satellite remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112016391B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160262A (en) * | 2021-03-23 | 2021-07-23 | 珠海欧比特宇航科技股份有限公司 | Oyster row extraction method, system and medium based on high-resolution satellite remote sensing image |
| CN114612379A (en) * | 2022-01-23 | 2022-06-10 | 杭州领见数字农业科技有限公司 | SAR image-based shoal raft frame extraction method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537795A (en) * | 2018-04-23 | 2018-09-14 | 中国科学院地球化学研究所 | A kind of mountain stream information extracting method |
| CN110110028A (en) * | 2019-05-09 | 2019-08-09 | 浪潮软件集团有限公司 | A kind of method and system showing map by self defined area towards OGC standard |
| CN110929592A (en) * | 2019-11-06 | 2020-03-27 | 北京恒达时讯科技股份有限公司 | Extraction method and system for outer boundary of mariculture area |
| CN111199195A (en) * | 2019-12-26 | 2020-05-26 | 中科禾信遥感科技（苏州）有限公司 | Pond state full-automatic monitoring method and device based on remote sensing image |
| CN111339948A (en) * | 2020-02-25 | 2020-06-26 | 武汉大学 | Automatic identification method for newly-added buildings of high-resolution remote sensing images |
| AU2020100917A4 (en) * | 2020-06-02 | 2020-07-09 | Guizhou Institute Of Pratacultural | A Method For Extracting Vegetation Information From Aerial Photographs Of Synergistic Remote Sensing Images |
-
2020
- 2020-07-16 CN CN202010684264.9A patent/CN112016391B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537795A (en) * | 2018-04-23 | 2018-09-14 | 中国科学院地球化学研究所 | A kind of mountain stream information extracting method |
| CN110110028A (en) * | 2019-05-09 | 2019-08-09 | 浪潮软件集团有限公司 | A kind of method and system showing map by self defined area towards OGC standard |
| CN110929592A (en) * | 2019-11-06 | 2020-03-27 | 北京恒达时讯科技股份有限公司 | Extraction method and system for outer boundary of mariculture area |
| CN111199195A (en) * | 2019-12-26 | 2020-05-26 | 中科禾信遥感科技（苏州）有限公司 | Pond state full-automatic monitoring method and device based on remote sensing image |
| CN111339948A (en) * | 2020-02-25 | 2020-06-26 | 武汉大学 | Automatic identification method for newly-added buildings of high-resolution remote sensing images |
| AU2020100917A4 (en) * | 2020-06-02 | 2020-07-09 | Guizhou Institute Of Pratacultural | A Method For Extracting Vegetation Information From Aerial Photographs Of Synergistic Remote Sensing Images |
Non-Patent Citations (2)
| Title |
|---|
| A Method of Building Extraction Using Object Based Analysis of High Resolution Remote Sensing Images,;Wang Yan，et al;《2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS)》;pp. 1-5 * |
| 基于RS与GIS技术的数字流域水体信息的提取;杨旭;***;程潭武;刘锐;;《水资源与水工程学报》;29(第04期);第81-86页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112016391A (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110390267B (en) | Mountain landscape building extraction method and device based on high-resolution remote sensing image | |
| CN107256558B (en) | Unsupervised automatic cervical cell image segmentation method and system | |
| CN109255776B (en) | Automatic identification method for cotter pin defect of power transmission line | |
| Qiao et al. | An automatic active contour method for sea cucumber segmentation in natural underwater environments | |
| CN112016391B (en) | Fishpond identification method, system and medium based on high-resolution satellite remote sensing image | |
| Senthilkumar et al. | A novel region growing segmentation algorithm for the detection of breast cancer | |
| CN109064470B (en) | Image segmentation method and device based on self-adaptive fuzzy clustering | |
| CN103400151A (en) | Optical remote-sensing image, GIS automatic registration and water body extraction integrated method | |
| CN103839069A (en) | Lawn miss cutting recognition method based on image analysis | |
| CN107590512B (en) | The adaptive approach and system of parameter in a kind of template matching | |
| CN109325492B (en) | Character cutting method, device, computer equipment and storage medium | |
| CN110555382A (en) | Finger vein identification method based on deep learning and Wasserstein distance measurement | |
| CN113807301B (en) | Automatic extraction method and automatic extraction system for newly-added construction land | |
| CN110276759B (en) | Mobile phone screen bad line defect diagnosis method based on machine vision | |
| CN115147710A (en) | Sonar image target processing method based on heterogeneous filtering detection and level set segmentation | |
| CN116109637B (en) | System and method for detecting appearance defects of turbocharger impeller based on vision | |
| CN111047559A (en) | Method for rapidly detecting abnormal area of digital pathological section | |
| CN113592782A (en) | Method and system for extracting X-ray image defects of composite carbon fiber core rod | |
| CN105184802A (en) | Image processing method and device | |
| CN112396618B (en) | Grain boundary extraction and grain size measurement method based on image processing | |
| Chen et al. | Image segmentation based on mathematical morphological operator | |
| CN108967246B (en) | Shrimp larvae positioning method | |
| CN116934761A (en) | Self-adaptive detection method for defects of latex gloves | |
| CN115049684A (en) | Water gauge identification method and system based on water area segmentation | |
| Khan et al. | Segmentation of single and overlapping leaves by extracting appropriate contours |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230217 Address after: Obit Technology Park, No.1 Baisha Road, East Bank of Tangjia, Zhuhai, Guangdong 519000 Applicant after: Zhuhai Orbit Satellite Big Data Co.,Ltd. Address before: 519080 Eubit Science Park, No. 1 Baisha Road, East Bank of Tangjia, Zhuhai City, Guangdong Province Applicant before: ZHUHAI ORBITA AEROSPACE TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |