CN112232303A - Grassland road information extraction method based on high-resolution remote sensing image - Google Patents
Grassland road information extraction method based on high-resolution remote sensing image Download PDFInfo
- Publication number
- CN112232303A CN112232303A CN202011281927.9A CN202011281927A CN112232303A CN 112232303 A CN112232303 A CN 112232303A CN 202011281927 A CN202011281927 A CN 202011281927A CN 112232303 A CN112232303 A CN 112232303A
- Authority
- CN
- China
- Prior art keywords
- image
- road
- grassland
- segmentation
- remote sensing
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims abstract description 65
- 238000003709 image segmentation Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000013145 classification model Methods 0.000 claims abstract description 13
- 230000007613 environmental effect Effects 0.000 claims abstract description 13
- 230000006866 deterioration Effects 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 23
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 230000010365 information processing Effects 0.000 claims description 8
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 238000013075 data extraction Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 2
- 238000009304 pastoral farming Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/416—Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
Abstract
The invention belongs to the field of grassland road monitoring, and particularly discloses a grassland road information extraction method based on high-resolution remote sensing images, which comprises the following steps: dividing a grassland area to be extracted into a plurality of grassland road plots, and screening out an area with high weight point and high risk from the environmental area of the grassland road plots according to environmental factors which easily influence the grassland roads to cause road deterioration; acquiring remote sensing data of the key high-risk area, and preprocessing the remote sensing data through image preprocessing and road image segmentation identification; the image classification model and the semantic segmentation model are built, the image classification model is used for classifying and extracting image data, and road information is segmented in the image through the semantic segmentation model. The invention preprocesses the remote sensing image by image preprocessing, road image segmentation identification and other technologies, and performs classification extraction by an image classification model and the like, thereby obviously improving the quality of road segmentation and the extraction precision of the road.
Description
Technical Field
The invention relates to the field of grassland road monitoring, in particular to a grassland road information extraction method based on high-resolution remote sensing images.
Background
The grassland is one of the earth ecosystems, is divided into tropical grassland, temperate grassland and other types, and is the most widely distributed vegetation type on the earth. The reason for the formation of the grassland is that the soil layer is thin or the precipitation is small, and the influence of herbaceous plants is small, so that the plants cannot grow widely. China is one of the most abundant countries of grassland resources in the world, and the total area of the grassland is nearly 4 hundred million hectares, which accounts for 40 percent of the total area of the land in the country and is 3 times of the area of the existing cultivated land. A dynamic balance between grassland and the type of vegetation involved usually occurs. Sometimes, periods of drought, fire or intensive grazing favor the development of grassland, and other times, wet seasons and without major disturbances favor the growth of woody vegetation, and these changes in frequency and severity can cause an overall shift in the type of vegetation, and the phenomena of desertification, deterioration of chinese grassland are severe due to prolonged periods of over-reclamation and over-grazing.
Road extraction is an important application of the remote sensing image processing technology, and has wide practical application value in urban and rural planning, land utilization, emergency treatment, vehicle navigation and other aspects. In recent years, with the sequential emission of high-spatial-resolution remote sensing satellites such as IKONOS, SPOT-5 and the like, the processing and application of high-resolution remote sensing satellite data gradually become a research hotspot in the field of remote sensing application. As very important basic geographic information, the automatic real-time monitoring of the road information in the remote sensing image can effectively improve the level of information management such as planning, road network maintenance, navigation and traffic analysis. However, since the high-spatial-resolution remote sensing image has many road types and a complex spatial structure, and is affected by image noises such as road obstacles (such as vehicles) and shadows, and problems such as similarity of spectral features between roads and buildings or residents, road extraction on the high-spatial-resolution remote sensing image has been regarded as a difficult task.
And the accuracy of road planning can be further ensured by extracting the grassland road due to serious grassland desertification, geological disasters and the like. The existing road extraction method (such as the invention patent with the publication number of CN 201610647160.4) has poor road segmentation quality and road extraction precision, and is not suitable for extracting grassland road information in grassland plots due to the fact that the grassland plots are quite large.
Disclosure of Invention
The invention aims to provide a grassland road information extraction method based on high-resolution remote sensing images, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a grassland road information extraction method based on high-resolution remote sensing images comprises the following steps:
s1: dividing a grassland area to be extracted into a plurality of grassland road plots, and screening out an area with high weight point and high risk from the environmental area of the grassland road plots according to environmental factors which easily influence the grassland roads to cause road deterioration;
s2: acquiring remote sensing data of the key high-risk area, and preprocessing the remote sensing data through image preprocessing and road image segmentation identification;
s3: the image classification model and the semantic segmentation model are built, the image classification model is used for classifying and extracting image data, and road information is segmented in the image through the semantic segmentation model.
Preferably, the obtaining of the environmental factor in S1 is implemented by an information obtaining and comprehensive analysis system, and the information obtaining and comprehensive analysis system includes a parcel basic information query module, an information processing module and a data information evaluation module, wherein the parcel basic information query module retrieves and obtains corresponding documents, newspapers and news from an open platform through keywords, and the information processing module is used for performing natural paragraph processing and structured data extraction on the obtained document information.
Preferably, the specific acquiring step of the information acquiring and comprehensive analyzing system comprises: s11: selecting characteristic keywords according to environmental factors which easily influence the grassland road to cause road deterioration, wherein the characteristic keywords comprise related keywords including meteorological temperature, road peripheral desertification and geological conditions; s12: retrieving and acquiring corresponding documents from the open platform through the characteristic keywords, wherein the documents comprise document related information including document names, contents, source periodicals and publication time, and managing and classifying the retrieved document basic information through a database; s13: retrieving the acquired digital document content information through an information processing module, and preprocessing natural paragraphs in document contents, wherein the preprocessing process comprises the following steps: and judging description contents of the natural paragraph according to the structural feature words, dividing the natural paragraph into a plurality of content segments including basic information of the land parcel and evaluation information, and extracting structural data of the content segments.
Preferably, the image preprocessing and road image segmentation processing in S2 specifically includes: s21: the purpose of enhancing the difference between the road image and the background image is achieved by enhancing and filtering the obtained remote sensing image data; s22: carrying out segmentation extraction on the remote sensing image data through a preset image segmentation algorithm to obtain a primary segmentation image; s23: and performing secondary segmentation on the primary segmentation image, and finishing the preprocessing and segmentation processes after the secondary segmentation.
Preferably, the preset image segmentation algorithm comprises at least two of a threshold-based image segmentation algorithm, an edge-based image detection algorithm and a region-based image segmentation algorithm, when the edge information is extracted by the edge-based image detection algorithm, only a local maximum gradient is reserved by reducing the edge, two thresholds are used by a Canny algorithm to distinguish edge pixels, a low threshold is used to filter out a small gradient value caused by noise or color change, and a high threshold is used to distinguish strong edge points from weak edge points.
Preferably, S23 specifically includes:
s23 a: the method comprises the steps that a threshold segmentation algorithm based on a maximum inter-class variance method is used for carrying out segmentation processing on a preliminary segmentation image, a binary foreground feature map is obtained, a foreground image and a background image of a road are obtained according to the binary image, background information is set to be 0, foreground information containing grassland vegetation, desert and the road is set to be 1, and therefore the binary foreground feature map containing the grassland vegetation and the road is obtained;
s23 b: and performing significance analysis based on visual features on the binarization prospect feature map, obtaining a grassland vegetation and desert significance map through low-pass filtering and gamma transformation, and performing threshold segmentation and corrosion on the grassland vegetation and desert significance map again to obtain a binarization significance map.
Preferably, in S3, an image classification model is built, low-level image feature information is stored in parameters of a network during training of a classification task on a basic network, and the image feature information is transferred to a semantic segmentation model of the next level in a process of constructing a feature extraction model; the semantic segmentation model is used for segmenting road information in the remote sensing image, and after the semantic segmentation model is trained, network parameters for extracting the road information are stored in the segmentation model.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, the high risk of the heavy point is determined through technologies such as retrieval analysis and the like, the area of the extracted region is reduced, the remote sensing image is preprocessed through technologies such as image preprocessing, road image segmentation recognition and the like, and classification extraction is carried out through an image classification model and a semantic segmentation model, so that the quality of road segmentation and the extraction precision of the road are remarkably improved.
Drawings
FIG. 1 is a block flow diagram of the present invention.
Detailed Description
The technical solutions in the embodiments will be described clearly and completely with reference to the accompanying drawings of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1, the present invention provides a technical solution: a grassland road information extraction method based on high-resolution remote sensing images comprises the following steps:
s1: dividing a grassland area to be extracted into a plurality of grassland road plots, and screening out an area with high weight point and high risk from the environmental area of the grassland road plots according to environmental factors which easily influence the grassland roads to cause road deterioration;
s2: acquiring remote sensing data of the key high-risk area, and preprocessing the remote sensing data through image preprocessing and road image segmentation identification;
s3: the image classification model and the semantic segmentation model are built, the image classification model is used for classifying and extracting image data, and road information is segmented in the image through the semantic segmentation model.
In this embodiment, the obtaining of the environmental factor in S1 is implemented by an information obtaining and comprehensive analysis system, which includes a parcel basic information query module, an information processing module and a data information evaluation module, wherein the parcel basic information query module retrieves and obtains corresponding documents, newspapers and news from an open platform through a keyword, and the information processing module is configured to perform natural paragraph processing and structured data extraction on the obtained document information.
In this embodiment, the specific steps of acquiring the information and acquiring the comprehensive analysis system include: s11: selecting characteristic keywords according to environmental factors which easily influence the grassland road to cause road deterioration, wherein the characteristic keywords comprise related keywords including meteorological temperature, road peripheral desertification and geological conditions; s12: retrieving and acquiring corresponding documents from the open platform through the characteristic keywords, wherein the documents comprise document related information including document names, contents, source periodicals and publication time, and managing and classifying the retrieved document basic information through a database; s13: retrieving the acquired digital document content information through an information processing module, and preprocessing natural paragraphs in document contents, wherein the preprocessing process comprises the following steps: and judging description contents of the natural paragraph according to the structural feature words, dividing the natural paragraph into a plurality of content segments including basic information of the land parcel and evaluation information, and extracting structural data of the content segments.
In this embodiment, the image preprocessing and road image segmentation processing in S2 specifically includes: s21: the purpose of enhancing the difference between the road image and the background image is achieved by enhancing and filtering the obtained remote sensing image data; s22: carrying out segmentation extraction on the remote sensing image data through a preset image segmentation algorithm to obtain a primary segmentation image; s23: and performing secondary segmentation on the primary segmentation image, and finishing the preprocessing and segmentation processes after the secondary segmentation.
In this embodiment, before the image preprocessing, the step S2 further includes capturing resolution of the remote sensing image, and the data annotation is performed on the captured remote sensing image, where the data annotation specifically is: and observing and measuring the geographical range covered by the remote sensing image, and intercepting the original data of the image classification and semantic segmentation task by combining the actual condition of the road to be extracted, wherein the original data is the RGB remote sensing image with the size of 256 × 256, namely 0.23 pixel per meter resolution scale.
In this embodiment, the preset image segmentation algorithm includes at least two of a threshold-based image segmentation algorithm, an edge-based image detection algorithm, and a region-based image segmentation algorithm, and when the edge-based image detection algorithm extracts edge information, only a local maximum gradient is retained by reducing an edge, two thresholds are used by a Canny algorithm to distinguish edge pixels, a low threshold is used to filter out a small gradient value caused by noise or color change, and a high threshold is used to distinguish a strong edge point from a weak edge point.
In this embodiment, S23 specifically includes:
s23 a: the method comprises the steps that a threshold segmentation algorithm based on a maximum inter-class variance method is used for carrying out segmentation processing on a preliminary segmentation image, a binary foreground feature map is obtained, a foreground image and a background image of a road are obtained according to the binary image, background information is set to be 0, foreground information containing grassland vegetation, desert and the road is set to be 1, and therefore the binary foreground feature map containing the grassland vegetation and the road is obtained;
s23 b: and performing significance analysis based on visual features on the binarization prospect feature map, obtaining a grassland vegetation and desert significance map through low-pass filtering and gamma transformation, and performing threshold segmentation and corrosion on the grassland vegetation and desert significance map again to obtain a binarization significance map.
In this embodiment, in S3, an image classification model is first built, low-level image feature information is stored in parameters of a network during training of a classification task on a basic network, and the image feature information is transferred to a semantic segmentation model of a next level in a process of constructing a feature extraction model; the semantic segmentation model is used for segmenting road information in the remote sensing image, and after the semantic segmentation model is trained, network parameters for extracting the road information are stored in the segmentation model.
In this embodiment, the construction process of the semantic segmentation model includes:
and determining a target domain data set and a source domain data set by selecting the basic data set. The adopted data set is a benchmark data set segmented by ISPRS (WGII/4)2D semantics, wherein a Vaihingen data set and a Potsdam data set are selected as a target domain data set and a source domain data set respectively, the two data sets both contain high-resolution images, but the two data sets have different resolutions, and the difference of the resolutions is also a problem to be solved by the experiment;
training the segmentation model by adopting a source domain data set to obtain a source domain segmentation model, and extracting image features of the source domain segmentation model through a bilateral segmentation network;
performing countermeasure training on an image extracted from a source domain data set and a target domain data set to generate a real image sample, outputting the trained image sample to form a new target domain data set, and finely adjusting the source domain segmentation model by using the new target domain data set by adopting a weight value of the source domain data set after being trained by a segmentation model as a starting point of segmentation model training on the new target domain data set, wherein cross entropy is used as a loss function for fine adjustment, and finally, a semantic segmentation model suitable for the target domain data set is constructed.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A grassland road information extraction method based on high-resolution remote sensing images is characterized by comprising the following steps:
s1: dividing a grassland area to be extracted into a plurality of grassland road plots, and screening out an area with high weight point and high risk from the environmental area of the grassland road plots according to environmental factors which easily influence the grassland roads to cause road deterioration;
s2: acquiring remote sensing data of the key high-risk area, and preprocessing the remote sensing data through image preprocessing and road image segmentation identification;
s3: the image classification model and the semantic segmentation model are built, the image classification model is used for classifying and extracting image data, and road information is segmented in the image through the semantic segmentation model.
2. The method for extracting grassland road information based on high-resolution remote sensing images as claimed in claim 1, wherein the obtaining of the environmental factors in step S1 is achieved through an information obtaining and comprehensive analysis system, the information obtaining and comprehensive analysis system comprises a plot basic information query module, an information processing module and a data information evaluation module, wherein the plot basic information query module retrieves corresponding documents, newspapers and periodicals and news from an open platform through keywords, and the information processing module is used for performing natural paragraph processing and structured data extraction on the obtained document information.
3. The method for extracting grassland road information based on high-resolution remote sensing images as claimed in claim 1, wherein the image preprocessing and road image segmentation processing in step S2 specifically comprises:
s21: the purpose of enhancing the difference between the road image and the background image is achieved by enhancing and filtering the obtained remote sensing image data;
s22: carrying out segmentation extraction on the remote sensing image data through a preset image segmentation algorithm to obtain a primary segmentation image;
s23: and performing secondary segmentation on the primary segmentation image, and finishing the preprocessing and segmentation processes after the secondary segmentation.
4. The method for extracting grassland road information based on high-resolution remote sensing images as claimed in claim 3, wherein the step S22 specifically comprises:
s22 a: extracting a mark point image of a road from the remote sensing image data;
s22 b: and extracting a preliminary segmentation image of the road from the remote sensing image according to the mark point image based on a watershed algorithm of the mark points.
5. The method for extracting the grassland road information based on the high-resolution remote sensing image as claimed in claim 3, wherein the preset image segmentation algorithm comprises at least two of a threshold-based image segmentation algorithm, an edge-based image detection algorithm and a region-based image segmentation algorithm.
6. The method for extracting grassland road information based on high-resolution remote sensing images as claimed in claim 3, wherein the step S23 specifically comprises:
s23 a: the method comprises the steps that a threshold segmentation algorithm based on a maximum inter-class variance method is used for carrying out segmentation processing on a preliminary segmentation image, a binary foreground feature map is obtained, a foreground image and a background image of a road are obtained according to the binary image, background information is set to be 0, foreground information containing grassland vegetation, desert and the road is set to be 1, and therefore the binary foreground feature map containing the grassland vegetation and the road is obtained;
s23 b: and performing significance analysis based on visual features on the binarization prospect feature map, obtaining a grassland vegetation and desert significance map through low-pass filtering and gamma transformation, and performing threshold segmentation and corrosion on the grassland vegetation and desert significance map again to obtain a binarization significance map.
7. The method for extracting grassland road information based on high-resolution remote sensing images as claimed in claim 1, wherein in step S3, an image classification model is built, low-level image feature information is left in parameters of a network during training of classification tasks of a basic network, and the image feature information is transmitted to a semantic segmentation model of the next level in a process of constructing the feature extraction model.
8. The method for extracting grassland road information based on high-resolution remote sensing images as claimed in claim 1, wherein a semantic segmentation model is further built in the step S3 for segmenting road information in the remote sensing images, and after the semantic segmentation model is trained, network parameters for extracting the road information are stored in the segmentation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011281927.9A CN112232303B (en) | 2020-11-16 | 2020-11-16 | Grassland road information extraction method based on high-resolution remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011281927.9A CN112232303B (en) | 2020-11-16 | 2020-11-16 | Grassland road information extraction method based on high-resolution remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112232303A true CN112232303A (en) | 2021-01-15 |
| CN112232303B CN112232303B (en) | 2023-12-19 |
Family
ID=74124339
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011281927.9A Active CN112232303B (en) | 2020-11-16 | 2020-11-16 | Grassland road information extraction method based on high-resolution remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112232303B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113222963A (en) * | 2021-05-27 | 2021-08-06 | 大连海事大学 | Non-orthographic infrared monitoring sea surface oil spill area estimation method and system |
| CN114782711A (en) * | 2022-06-20 | 2022-07-22 | 四川航天职业技术学院(四川航天高级技工学校) | Intelligent risk detection method and system based on image recognition |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295562A (en) * | 2016-08-09 | 2017-01-04 | 中国科学院遥感与数字地球研究所 | A kind of high-resolution remote sensing image road information extracting method |
| CN106485254A (en) * | 2016-09-28 | 2017-03-08 | 国家电网公司 | A kind of electric transmission line channel topographical features change extraction method |
| CN107330413A (en) * | 2017-07-06 | 2017-11-07 | 中国科学院遥感与数字地球研究所 | A kind of mother drug plants recognition methods based on remote sensing technology |
| CN109711670A (en) * | 2018-11-23 | 2019-05-03 | 北京大学深圳研究生院 | A kind of management of Mangrove Wetlands birds and evaluation system |
| CN109800736A (en) * | 2019-02-01 | 2019-05-24 | 东北大学 | A kind of method for extracting roads based on remote sensing image and deep learning |
| WO2020107687A1 (en) * | 2018-11-27 | 2020-06-04 | 邦鼓思电子科技（上海）有限公司 | Vision-based working area boundary detection system and method, and machine equipment |
| CN111539432A (en) * | 2020-03-11 | 2020-08-14 | 中南大学 | Method for extracting urban road by using multi-source data to assist remote sensing image |
-
2020
- 2020-11-16 CN CN202011281927.9A patent/CN112232303B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295562A (en) * | 2016-08-09 | 2017-01-04 | 中国科学院遥感与数字地球研究所 | A kind of high-resolution remote sensing image road information extracting method |
| CN106485254A (en) * | 2016-09-28 | 2017-03-08 | 国家电网公司 | A kind of electric transmission line channel topographical features change extraction method |
| CN107330413A (en) * | 2017-07-06 | 2017-11-07 | 中国科学院遥感与数字地球研究所 | A kind of mother drug plants recognition methods based on remote sensing technology |
| CN109711670A (en) * | 2018-11-23 | 2019-05-03 | 北京大学深圳研究生院 | A kind of management of Mangrove Wetlands birds and evaluation system |
| WO2020107687A1 (en) * | 2018-11-27 | 2020-06-04 | 邦鼓思电子科技（上海）有限公司 | Vision-based working area boundary detection system and method, and machine equipment |
| CN109800736A (en) * | 2019-02-01 | 2019-05-24 | 东北大学 | A kind of method for extracting roads based on remote sensing image and deep learning |
| CN111539432A (en) * | 2020-03-11 | 2020-08-14 | 中南大学 | Method for extracting urban road by using multi-source data to assist remote sensing image |
Non-Patent Citations (1)
| Title |
|---|
| 杨先武;韦春桃;李彩露;吴平;: "基于形态重建的高分辨率遥感影像城市道路提取", 地理科学, no. 08 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113222963A (en) * | 2021-05-27 | 2021-08-06 | 大连海事大学 | Non-orthographic infrared monitoring sea surface oil spill area estimation method and system |
| CN113222963B (en) * | 2021-05-27 | 2024-03-26 | 大连海事大学 | Non-orthographic infrared monitoring sea surface oil spill area estimation method and system |
| CN114782711A (en) * | 2022-06-20 | 2022-07-22 | 四川航天职业技术学院(四川航天高级技工学校) | Intelligent risk detection method and system based on image recognition |
| CN114782711B (en) * | 2022-06-20 | 2022-09-16 | 四川航天职业技术学院(四川航天高级技工学校) | Intelligent risk detection method and system based on image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112232303B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Monthly estimation of the surface water extent in France at a 10-m resolution using Sentinel-2 data | |
| Yu et al. | A new approach for land cover classification and change analysis: Integrating backdating and an object-based method | |
| CN101840581B (en) | Method for extracting profile of building from satellite remote sensing image | |
| CN111597949B (en) | NPP-VIIRS night light data-based urban built-up area extraction method | |
| Veljanovski et al. | Object-based image analysis of VHR satellite imagery for population estimation in informal settlement Kibera-Nairobi, Kenya | |
| CN103984946A (en) | High resolution remote sensing map road extraction method based on K-means | |
| CN109919944A (en) | A kind of joint super-pixel figure of complex scene building variation detection cuts optimization method | |
| CN109063754A (en) | A kind of remote sensing image multiple features combining classification method based on OpenStreetMap | |
| CN112232303B (en) | Grassland road information extraction method based on high-resolution remote sensing image | |
| CN110570470A (en) | ghost community identification and housing vacancy rate estimation method based on multi-source remote sensing data | |
| CN112270291B (en) | Automatic detection method for illegal construction land development based on multi-source optical remote sensing image | |
| Jing et al. | A novel approach for quantifying high-frequency urban land cover changes at the block level with scarce clear-sky Landsat observations | |
| Yin et al. | Sub-pixel vs. super-pixel-based greenspace mapping along the urban–rural gradient using high spatial resolution Gaofen-2 satellite imagery: a case study of Haidian District, Beijing, China | |
| Nelson et al. | Spatial statistical techniques for aggregating point objects extracted from high spatial resolution remotely sensed imagery | |
| CN110765900A (en) | DSSD-based automatic illegal building detection method and system | |
| CN116503750A (en) | Large-range remote sensing image rural block type residential area extraction method and system integrating target detection and visual attention mechanisms | |
| CN113450461A (en) | Soil-discharging-warehouse geotechnical distribution cloud extraction method | |
| Wang et al. | Combining SAR images with land cover products for rapid urban flood mapping | |
| Zhang et al. | Research on pavement marking recognition and extraction method | |
| Alhaddad et al. | Urban detection, delimitation and morphology: comparative analysis of selective" megacities" | |
| Juel et al. | Integrating field survey and orthophoto information to monitor coastal habitats—A pilot study to develop methods and resolve key issues | |
| Chen et al. | Urban scenes change detection based on multi-scale irregular bag of visual features for high spatial resolution imagery | |
| Liu et al. | Identification of Damaged Building Regions from High-Resolution Images Using Superpixel-Based Gradient and Autocorrelation Analysis | |
| CN115797775B (en) | Intelligent illegal building identification method and system based on near-to-ground video image | |
| Vani et al. | Detection and Extraction of Roads using Cartosat-2 High Resolution Satellite Imagery |
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 |