[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2021248599A1 - 一种类型异常图斑自动识别方法及系统 - Google Patents

一种类型异常图斑自动识别方法及系统 Download PDF

Info

Publication number
WO2021248599A1
WO2021248599A1 PCT/CN2020/100451 CN2020100451W WO2021248599A1 WO 2021248599 A1 WO2021248599 A1 WO 2021248599A1 CN 2020100451 W CN2020100451 W CN 2020100451W WO 2021248599 A1 WO2021248599 A1 WO 2021248599A1
Authority
WO
WIPO (PCT)
Prior art keywords
index
image
pattern
abnormal
images
Prior art date
Application number
PCT/CN2020/100451
Other languages
English (en)
French (fr)
Inventor
李冲
李昊霖
Original Assignee
自然资源部四川测绘产品质量监督检验站(四川省测绘产品质量监督检验站)
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 自然资源部四川测绘产品质量监督检验站(四川省测绘产品质量监督检验站) filed Critical 自然资源部四川测绘产品质量监督检验站(四川省测绘产品质量监督检验站)
Publication of WO2021248599A1 publication Critical patent/WO2021248599A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • 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
    • 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
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G06T2207/10036—Multispectral image; Hyperspectral image

Definitions

  • the present invention relates to the technical field of image processing, and in particular to a method and system for automatically identifying types of abnormal patterns.
  • the purpose of the present invention is to provide a method and system for automatically identifying types of abnormal patterns.
  • the present invention provides the following solutions:
  • a method for automatically identifying types of abnormal patterns including:
  • each patch image According to the size of the comprehensive spectral index of each patch image, sort each patch image by element type;
  • If there are abnormal categorical patterns add a set number of pattern images before and/or after the pattern image sequence, and perform category anomaly recognition on the added pattern images. If there are categorical abnormalities in the added pattern image For spots, skip to the step of "adding a set number of spot images before and/or after the spot image sequence for identification" until there are no abnormal spots in the added spot images;
  • the method before the cropping of the multispectral remote sensing image based on the geometric range of the pattern, the method further includes:
  • the sorting of each map spot image according to the size of the comprehensive spectral index of each map spot image by element category specifically includes:
  • each patch image is sorted by feature class.
  • the method for detecting category abnormal patterns includes:
  • the abnormal pattern is all the patterns between the adjacent pattern image and the first end of the pattern sequence, and the first end is the distance of the pattern sequence. The closer end of the adjacent spot image.
  • the method before calculating the comprehensive spectral index of each spot image, the method further includes:
  • Stretching processing is performed on the differential building index and the normalized vegetation index and water body index.
  • the method further includes:
  • the abnormal pattern image of the category recognized by the computer is output to the human-computer interaction terminal for manual secondary recognition.
  • the cropping process of the multi-spectral remote sensing image is performed in a computer memory.
  • the present invention also provides an automatic identification system for abnormal patterns, including:
  • the to-be-identified multi-spectral remote sensing image acquisition module is used to acquire the to-be-identified multi-spectral remote sensing image
  • the patch image cropping module is used for cropping the multi-spectral remote sensing image based on the geometric range of the patch to obtain the image of the patch that is prone to error or confusion;
  • the comprehensive spectral index calculation module is used to calculate the comprehensive spectral index of each patch image, and the comprehensive spectral index is composed of a weighted combination of vegetation index, water index, and differential building index to distinguish the types of the patch elements;
  • the sorting module is used to sort the image of each patch according to the size of the comprehensive spectral index of the image of each patch;
  • the category abnormality determination module is used to determine whether there are category abnormal spots in the set number of spot images before and after the spot image sequence, and to determine whether there are category abnormal spots in the added spot images.
  • system further includes:
  • the initial parameter determination module is used to determine the error-prone or confusing element types and the weight coefficients of the vegetation index, the water body index, and the differential building index in the comprehensive spectral index used to distinguish the error-prone or confusing element types based on historical data.
  • the sorting module specifically includes:
  • a numerical value determining unit for determining the median or average value of the comprehensive spectral index of each of the pattern images
  • the sorting unit is used for sorting each spot image according to the size of the middle value or average value of the comprehensive spectral index of the spot image.
  • the present invention discloses the following technical effects: the method and system for automatically identifying abnormal patterns provided by the present invention first extract the error-prone or confusing patterns in the multi-spectral remote sensing image to be identified, and then correct Calculate the spectral index of each pattern that can distinguish error-prone or confusing patterns, and sort the available patterns according to the size of the spectral index, and finally classify abnormalities by setting the number of patterns at both ends of the sequence Detection to determine the category of abnormal patterns.
  • the invention realizes the automatic recognition of the abnormal pattern category and improves the detection efficiency.
  • FIG. 1 is a schematic flowchart of a method for automatically identifying abnormal patterns according to Embodiment 1 of the present invention
  • Fig. 2 is a schematic structural diagram of an automatic identification system for type abnormal patterns provided by Embodiment 2 of the present invention.
  • Fig. 1 is a schematic flow chart of the method for automatic identification of abnormal patterns according to Embodiment 1 of the present invention.
  • the method for automatic identification of abnormal patterns provided by this embodiment includes the following steps:
  • Step 101 Obtain a multi-spectral remote sensing image to be identified
  • Step 102 Based on the geometric range of the pattern, crop the multispectral remote sensing image to obtain an image of pattern prone to error or confusion;
  • Step 103 Calculate the comprehensive spectral index of each map spot image, where the comprehensive spectral index is composed of a weighted combination of vegetation index, water index, and differential building index to distinguish the types of map spot elements;
  • Step 104 According to the size of the comprehensive spectral index of each map spot image, sort the map spot images according to the feature class;
  • Step 105 Determine whether there are abnormal patterns in the set number of pattern images before and after the pattern image sequence
  • Step 106 If there are abnormal categorical patterns, add a set number of pattern images before and/or after the pattern image sequence, and perform category abnormality recognition on the added pattern images. If the added pattern images are If there are abnormal patterns in the category, skip to the step of "adding a set number of pattern images before and/or after the pattern image sequence for identification" until there are no abnormal patterns in the added pattern image;
  • Step 107 Output the abnormal pattern image.
  • the geometric range of each map spot is sequentially obtained from the ground cover vector data, and the image cropping function is defined.
  • the cropped range is the geometric range of the map spot
  • the cropped image is the multi-spectral remote sensing image to be identified
  • the number of bands of the multi-spectral remote sensing image to be identified should be no less than 4, including at least red, green, blue, near-infrared and other bands.
  • the image cropping function defines the image data processing method for the speckle spectral index. Among them, the preferred Yes, the processing is carried out in the computer memory, and the cutting results are not output to the computer hard disk. Calculate the comprehensive spectral index of each patch image.
  • the comprehensive spectral index is composed of a weighted combination of vegetation index, water index, and differential building index to distinguish the types of patch elements.
  • other spectral feature data that can distinguish the types of pattern elements can also be used.
  • the middle value of the comprehensive spectral index of the pattern image can be selected to represent that the patterns are sorted according to their size.
  • the average value of the integrated spectral index of the pattern image can also be selected to represent the pattern for pattern sorting.
  • the patches belonging to the same feature class are sorted separately, for example, all feature category attributes are paddy fields.
  • the patches of the class are sorted as a group, and the patches of all the feature category attributes are lakes are sorted as a group.
  • the method for determining the intermediate value of the comprehensive spectral index of the pattern image is as follows: when the number of pixels in the pattern is an odd number, the middle value in the pixel comprehensive spectral index sequence is the middle of the comprehensive spectral index of the pattern. When the number of pixels in the pattern is an even number, the two middle values in the pixel comprehensive spectral index sequence are taken out, and the average of the two values is calculated, which is the middle value of the pattern comprehensive spectral index of the pattern.
  • the category abnormal pattern after determining the abnormal pattern, can be directly output, or the category abnormal pattern can be output to the human-computer interaction terminal, and the secondary identification is manually performed.
  • step 102 may further include: determining the element types that are prone to error or confusion based on historical data and the vegetation index, water index, and the comprehensive spectral index used to distinguish the element types that are prone to error or confusion.
  • the weight coefficient of the difference building index may be determining the element types that are prone to error or confusion based on historical data and the vegetation index, water index, and the comprehensive spectral index used to distinguish the element types that are prone to error or confusion.
  • the spectral information of the non-visible light band and the visible light band can obtain the weight coefficients of the vegetation index, the water index and the difference building index in the comprehensive spectral index of the pattern that can distinguish the error-prone and confusing element types.
  • the method for detecting category abnormal patterns may specifically be:
  • the abnormal pattern is all the patterns between the adjacent pattern image and the first end of the pattern sequence, and the first end is the distance from the phase in the pattern sequence. The nearest end of the adjacent spot image.
  • the specific operation method is: to judge the comprehensive spectral index of two adjacent patterns among the 5 patterns (such as the middle value of the comprehensive spectral index) Whether the difference between is greater than the set threshold, the set threshold can generally be set to 0.04, if the difference between the integrated spectral index of the 4th and 5th spots (such as the middle value of the integrated spectral index) is greater than the set threshold, then It is considered that the first 4 spots are all abnormal spots.
  • each index needs to be preprocessed.
  • the preprocessing process may include normalization processing and stretching processing. The specific process is as follows:
  • B nir is the near-infrared band of remote sensing images
  • B red is the red band of remote sensing images.
  • B nir is the near-infrared band of remote sensing images
  • B green is the green band of remote sensing images.
  • k is the calculation coefficient, which can generally be set to 0.5
  • B blue is the blue band of the remote sensing image
  • B red is the red band of the remote sensing image
  • B green is the green band of the remote sensing image.
  • the normalized vegetation index, normalized water index, and differential building index are stretched to stretch the value range to [0,1], and the normalized vegetation index and normalized water index are processed according to the following formula Stretching treatment.
  • Pixel v is the pixel value on the original normalized water body or vegetation index
  • Pixel' v is the pixel value after stretching.
  • the differential building index is stretched according to the following formula.
  • Pixel v is the pixel value on the original differential building index
  • Pixel' v is the pixel value after stretching
  • Pixel v_min is the minimum pixel value of the original differential building index for the entire scene
  • Pixel v_max is the original differential building for the entire scene The maximum pixel value of the object index.
  • the vegetation index NDVI, the water index NDWI, and the building index NSBI are comprehensively weighted according to the following formula to calculate the comprehensive spectral index NCI of the pattern.
  • k 1 is the coefficient of NDVI
  • k 2 is the coefficient of NDWI
  • k 3 is the coefficient of NSBI.
  • the values of k 1 , k 2 , and k 3 can be determined based on the statistical analysis results of the spectral information of each type of element.
  • the NCI of this type of element is calculated When the value of k 1 is set to 1, the value of k 2 and k 3 is set to 0; when the value of NDWI is easier to distinguish a certain feature category from other feature categories, when calculating the NCI of this type of feature, k The value of 2 is set to 1, the value of k 1 and k 3 is set to 0; when the value of NSBI is easier to distinguish a certain feature category from other feature categories, when calculating the NCI of this type of feature, the value of k 3 is set The values of 1, k 1 and k 2 are set to zero.
  • FIG. 2 is a schematic structural diagram of the automatic identification system for abnormal patterns according to Embodiment 2 of the present invention.
  • the automatic identification system for abnormal patterns provided by this embodiment includes:
  • the to-be-identified multi-spectral remote sensing image acquisition module 201 is used to acquire the to-be-identified multi-spectral remote sensing image
  • the patch image cropping module 202 is configured to crop the multi-spectral remote sensing image based on the geometric range of the patch to obtain an image with a pattern that is prone to error or confusion;
  • the comprehensive spectral index calculation module 203 is used to calculate the comprehensive spectral index of each pattern image, the comprehensive spectral index is composed of a weighted combination of vegetation index, water index, and differential building index to distinguish the types of pattern elements;
  • the sorting module 204 is used for sorting each spot image according to the size of the comprehensive spectral index of each spot image according to the feature class;
  • the category abnormality determining module 205 is used to determine whether there are abnormal categorical patterns in the set number of pattern images before and after the pattern image sequence, and to determine whether there are abnormal categorical patterns in the added pattern image.
  • system further includes:
  • the initial parameter determination module is used to determine the error-prone or confusing element types based on historical data and the weight coefficients of the vegetation index, water index, and differential building index in the comprehensive spectral index used to distinguish error-prone or confusing element types.
  • the sorting module 204 specifically includes:
  • a numerical value determining unit for determining the median or average value of the comprehensive spectral index of each of the pattern images
  • the sorting unit is used for sorting each spot image according to the size of the middle value or average value of the comprehensive spectral index of the spot image.
  • the category abnormality determining module 205 specifically includes:
  • the judging unit is used for judging whether the difference of the comprehensive spectral index of adjacent spot images is greater than a set threshold
  • the category abnormal pattern determination unit is used to determine the category of all the patterns between the adjacent pattern image and the first end of the pattern sequence when the difference of the comprehensive spectral index of the adjacent pattern image is greater than the set threshold value
  • the first end is an end of the pattern sequence that is closer to the image of the adjacent pattern.
  • system further includes:
  • the normalization processing module is used to perform normalization processing on the vegetation index and the water body index;
  • the stretching processing module is used to perform stretching processing on the differential building index and the normalized vegetation index and water body index.
  • the method and system for automatic identification of type abnormal patterns realizes automatic extraction of large pattern and same-spectrum foreign matter errors, improves the efficiency and reliability of surface coverage data quality detection, and effectively improves the quality of results of geographic and national conditions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Quality & Reliability (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

一种类型异常图斑自动识别方法及系统。该方法包括：获取待识别多光谱遥感影像（101）；基于图斑的几何范围，对多光谱遥感影像进行裁切，以获得类别易出错或易混淆的图斑的影像（102）；计算各图斑影像的综合光谱指数（103）；根据各图斑影像综合光谱指数的大小，分要素类对各图斑影像进行排序（104）；确定图斑影像序列前后设定数量的图斑影像中是否存在类别异常图斑（105）；如果存在，则在图斑影像序列的前和/或后增加设定数量的图斑影像，并对增加的图斑影像进行类别异常识别，如果增加的图斑影像中存在类别异常图斑，则跳转至"在图斑影像序列的前和/或后增加设定数量的图斑影像进行识别"步骤，直至增加的图斑影像中不存在类别异常图斑为止（106）。该方法能够实现类别异常图斑的自动识别。

Description

一种类型异常图斑自动识别方法及系统
本申请要求于2020年06月12日提交中国专利局、申请号为202010534638.9、发明名称为“一种类型异常图斑自动识别方法及系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及图像处理技术领域，特别是涉及一种类型异常图斑自动识别方法及系统。
背景技术
随着社会的发展，在地理国情监测领域，对地表覆盖数据的准确度、精细度提出了更高的要求。然而，由于我国地表情况复杂、遥感影像质量不一、解译受人员主观影响大等因素，地表覆盖数据中经常出现图斑分类错误问题，严重影响了地理国情监测成果的质量，每年各生产单位、质检单位需要花费大量人力、物力、财力去排查地表覆盖数据中的大图斑及同谱异物错误。
发明内容
本发明的目的是提供一种类型异常图斑自动识别方法及系统。
为实现上述目的，本发明提供了如下方案：
一种类型异常图斑自动识别方法，包括：
获取待识别多光谱遥感影像；
基于图斑的几何范围，对所述多光谱遥感影像进行裁切，以获得类别易出错或易混淆的图斑的影像；
计算各图斑影像的综合光谱指数，所述综合光谱指数由植被指数、水体指数以及差分建筑物指数加权组合构成，用以区分图斑要素类别；
根据各图斑影像的综合光谱指数的大小，分要素类对各图斑影像进行排序；
确定图斑影像序列前后设定数量的图斑影像中是否存在类别异常图斑；
如果存在类别异常图斑，则在图斑影像序列的前和/或后增加设定数量的图斑影像，并对增加的图斑影像进行类别异常识别，如果增加的图斑影像中存在类别异常图斑，则跳转至“在图斑影像序列的前和/或后增加设定数量的图斑影像进行识别”步骤，直至增加的图斑影像中不存在类别异常图斑为止；
输出异常图斑影像。
可选的，在所述基于图斑的几何范围，对所述多光谱遥感影像进行裁切之前，还包括：
根据历史数据确定易出错或易混淆的要素类别以及用以区分易出错或易混淆的要素类别的综合光谱指数中植被指数、水体指数以及差分建筑物指数的权重系数。
可选的，所述根据各图斑影像的综合光谱指数的大小，分要素类对各图斑影像进行排序，具体包括：
确定每一所述图斑影像的综合光谱指数的中间值或平均值；
根据图斑影像的综合光谱指数的中间值或平均值的大小，分要素类对各图斑影像进行排序。
可选的，所述类别异常图斑检测方法包括：
判断相邻图斑影像的综合光谱指数的差值是否大于设定阈值；
如果是，则表示存在类别异常图斑，且类别异常图斑为所述相邻图斑影像到图斑序列第一端之间所有的图斑，所述第一端为图斑序列距离所述相邻图斑影像较近的一端。
可选的，在所述计算各图斑影像的综合光谱指数之前，还包括：
对所述植被指数和所述水体指数进行归一化处理；
对所述差分建筑物指数以及归一化的植被指数和水体指数进行拉伸处理。
可选的，所述方法还包括：
向人机交互端输出计算机识别出的类别异常图斑影像，以供人工进行二次识别。
可选的，所述多光谱遥感影像的裁切过程在计算机内存中进行。
本发明还提供了一种类型异常图斑自动识别系统，包括：
待识别多光谱遥感影像获取模块，用于获取待识别多光谱遥感影像；
图斑影像裁切模块，用于基于图斑的几何范围，对所述多光谱遥感影像进行裁切，以获得类别易出错或易混淆的图斑的影像；
综合光谱指数计算模块，用于计算各图斑影像的综合光谱指数，所述综合光谱指数由植被指数、水体指数以及差分建筑物指数加权组合构成，用以区分图斑要素类别；
排序模块，用于根据各图斑影像的综合光谱指数的大小，分要素类对各图斑影像进行排序；
类别异常确定模块，用于确定图斑影像序列前后设定数量的图斑影像中是否存在类别异常图斑，以及确定增加的图斑影像中是否存在类别异常图斑。
可选的，所述系统还包括：
初始参数确定模块，用于根据历史数据确定易出错或易混淆的要素类别以及用以区分易出错或易混淆的要素类别的综合光谱指数中植被指数、水体指数以及差分建筑物指数的权重系数。
可选的，所述排序模块，具体包括：
数值确定单元，用于确定每一所述图斑影像的综合光谱指数的中间值或平均值；
排序单元，用于根据图斑影像的综合光谱指数的中间值或平均值的大小，分要素类对各图斑影像进行排序。
根据本发明提供的具体实施例，本发明公开了以下技术效果：本发明提供的类型异常图斑自动识别方法及系统首先提取待识别多光谱遥感影像中易于出错或易于混淆的图斑，然后对各图斑的能够区分出易出错或易混淆图斑的光谱指数进行计算，并根据该光谱指数的大小对各可图斑进行排序，最后通过对序列两端设定数量的图斑进行类别异常检测以确定类别异常图斑。本发明实现了图斑类别异常的自动识别，提高了检测的效率。
说明书附图
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附 图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例1提供的类型异常图斑自动识别方法流程示意图；
图2为本发明实施例2提供的类型异常图斑自动识别系统结构示意图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
为使本发明的上述目的、特征和优点能够更加明显易懂，下面结合附图和具体实施方式对本发明作进一步详细的说明。
实施例1
图1为本发明实施例1提供的类型异常图斑自动识别方法流程示意图，参见图1，本实施例提供的类型异常图斑自动识别方法包括以下步骤：
步骤101：获取待识别多光谱遥感影像；
步骤102：基于图斑的几何范围，对多光谱遥感影像进行裁切，以获得类别易出错或易混淆的图斑的影像；
步骤103：计算各图斑影像的综合光谱指数，所述综合光谱指数由植被指数、水体指数以及差分建筑物指数加权组合构成，用以区分图斑要素类别；
步骤104：根据各图斑影像的综合光谱指数的大小，分要素类对各图斑影像进行排序；
步骤105：确定图斑影像序列前后设定数量的图斑影像中是否存在类别异常图斑；
步骤106：如果存在类别异常图斑，则在图斑影像序列的前和/或后增加设定数量的图斑影像，并对增加的图斑影像进行类别异常识别，如果 增加的图斑影像中存在类别异常图斑，则跳转至“在图斑影像序列的前和/或后增加设定数量的图斑影像进行识别”步骤，直至增加的图斑影像中不存在类别异常图斑为止；
步骤107：输出类别异常图斑影像。
在本实施例中，依次从地表覆盖矢量数据中获取各图斑的几何范围，定义影像裁切函数，裁切的范围为图斑的几何范围，被裁切的影像为待识别多光谱遥感影像，待识别多光谱遥感影像的波段数应不少于4个，至少包括红、绿、蓝、近红外等波段，影像裁切函数面向图斑光谱指数定义了影像数据的处理方式，其中，优选的，处理过程在计算机内存中进行，不输出裁切结果到计算机硬盘。计算各图斑影像的综合光谱指数，综合光谱指数由植被指数、水体指数以及差分建筑物指数加权组合构成，用以区分图斑要素类别。当然，在其他实施例中，也可以采用其他可以区分图斑要素类别的光谱特征数据。在计算得到各图斑影像的综合光谱指数后，可以选取图斑影像综合光谱指数的中间值代表该图斑按照大小进行图斑排序。当然，在其他实施例中，也可以选取图斑影像综合光谱指数的平均值代表该图斑进行图斑排序。在排序时，要分要素类进行排序，也就是说，不是所有要素类的图斑混合在一起进行排序，而是将属于同一要素类的图斑单独进行排序，比如，所有要素类别属性为水田类的图斑为一组进行排序，所有要素类别属性为湖泊的图斑为一组进行排序。在得到图斑序列后，首先判断图斑序列的前后设定数量(比如2个)的图斑影像中是否存在类别异常图斑，如果不存在，则认为整个图斑序列中的图斑都正常，不存在类别异常图斑，如果图斑序列的前后设定数量的图斑影像中存在类别异常图斑，比如，图斑序列的前端(后端)设定数量的图斑影像中存在类别异常图斑，则在图斑序列前端(后端)增加设定数量(比如2～3个)的图斑进行类别异常检测，直至增加的设定数量的图斑均为正常图斑时为止，此时，则认为最后一次增加的图斑为类别正常图斑，在这之前识别的图斑均为类别异常图斑。
其中，图斑影像综合光谱指数的中间值的确定方式如下：当图斑内的像素点数为奇数时，像素综合光谱指数序列中最中间的一个数值即是该图斑的图斑综合光谱指数中间值，当图斑内的像素点数为偶数时，取出像素 综合光谱指数序列中最中间的两个数值，计算两个数值的平均值，即是该图斑的图斑综合光谱指数中间值。
在本实施例中，在确定异常图斑后，可以将类别异常图斑直接输出，也可以将类别异常图斑输出到人机交互端，由人工进行二次识别。
在本实施例中，在步骤102之前，还可以包括：根据历史数据确定易出错或易混淆的要素类别以及用以区分易出错或易混淆的要素类别的综合光谱指数中植被指数、水体指数以及差分建筑物指数的权重系数。比如，统计历年国家基础性地理国情监测数据中发现的大图斑和同谱异物质量问题，重点针对易出错、易混淆的要素类别，如水田与旱地、果园与林地等，研究分析其影像的非可见光波段、可见光波段的光谱信息，获得能够区分易出错、易混淆要素类别的图斑综合光谱指数中植被指数、水体指数以及差分建筑物指数的权重系数。
作为一种实施方式，所述类别异常图斑检测方法具体可以为：
判断相邻图斑影像的综合光谱指数的差值是否大于设定阈值；
如果是，则表示存在类别异常图斑，且类别异常图斑为相邻图斑影像到图斑序列第一端之间所有的图斑，所述第一端为图斑序列中距离所述相邻图斑影像较近的一端。
比如，判断图斑序列前5个图斑中是否存在类别异常图斑，具体的操作方法为：判断5个图斑中相邻两个图斑的综合光谱指数(比如综合光谱指数的中间值)的差值是否大于设定阈值，设定阈值一般可以设为0.04，如果第4个和第5个图斑的综合光谱指数(比如综合光谱指数的中间值)的差值大于设定阈值，则认为前4个图斑均为类别异常图斑。
在本实施例中，在计算各图斑的综合光谱指数时，需要对各指数进行预处理，预处理过程可以包括归一化处理以及拉伸处理，具体过程如下：
首先，利用以下公式计算图斑的归一化植被指数NDVI，突出影像中的植被信息。
Figure PCTCN2020100451-appb-000001
其中，B nir为遥感影像的近红外波段，B red为遥感影像的红色波段。
然后，利用以下公式计算图斑的归一化水体指数NDWI，突出影像中的水体信息。
Figure PCTCN2020100451-appb-000002
其中，B nir为遥感影像的近红外波段，B green为遥感影像的绿色波段。
之后，利用以下公式计算图斑的差分建筑物指数DSBI。
DSBI＝k*(B blue-B red)+(1-k)*(B blue-B green)
其中，k为计算系数，一般可以设置为0.5，B blue为遥感影像的蓝色波段，B red为遥感影像的红色波段，B green为遥感影像的绿色波段。
最后，拉伸处理归一化植被指数、归一化水体指数、差分建筑物指数，将值域范围拉伸至[0,1]，归一化植被指数和归一化水体指数按以下公式进行拉伸处理。
Figure PCTCN2020100451-appb-000003
其中，Pixel v为原始归一化水体或植被指数上的像素值，Pixel' v为拉伸处理后的像素值。
差分建筑物指数按以下公式进行拉伸处理。
Figure PCTCN2020100451-appb-000004
其中，Pixel v为原始差分建筑物指数上的像素值，Pixel' v为拉伸处理后的像素值，Pixel v_min为整景原始差分建筑物指数的最小像素值，Pixel v_max为整景原始差分建筑物指数的最大像素值。
按以下公式综合加权处理拉伸后的植被指数NDVI、水体指数NDWI、建筑物指数NSBI，计算图斑的综合光谱指数NCI。
Figure PCTCN2020100451-appb-000005
其中，k 1为NDVI的系数，k 2为NDWI的系数，k 3为NSBI的系数。k 1、k 2、k 3的值可依据对各类别要素光谱信息统计分析结果确定，当NDVI的值更容易把某一要素类别与其他要素类别区分开来时，则计算该类要素的NCI时，k 1值设为1、k 2和k 3的值设为0；当NDWI的值更容易把某一要素类别与其他要素类别区分开来时，则计算该类要素的NCI时，k 2值设为1、k 1和k 3的值设为0；当NSBI的值更容易把某一要素类别与其他要素类别区分开来时，则计算该类要素的NCI时，k 3值设为1、k 1和k 2的值设为0。
实施例2
图2为本发明实施例2提供的类型异常图斑自动识别系统结构示意图，参见图2，本实施例提供的类型异常图斑自动识别系统包括：
待识别多光谱遥感影像获取模块201，用于获取待识别多光谱遥感影像；
图斑影像裁切模块202，用于基于图斑的几何范围，对所述多光谱遥感影像进行裁切，以获得类别易出错或易混淆的图斑的影像；
综合光谱指数计算模块203，用于计算各图斑影像的综合光谱指数，所述综合光谱指数由植被指数、水体指数以及差分建筑物指数加权组合构成，用以区分图斑要素类别；
排序模块204，用于根据各图斑影像的综合光谱指数的大小，分要素类对各图斑影像进行排序；
类别异常确定模块205，用于确定图斑影像序列前后设定数量的图斑影像中是否存在类别异常图斑，以及确定增加的图斑影像中是否存在类别异常图斑。
作为一种实施方式，所述系统还包括：
初始参数确定模块，用于根据历史数据确定易出错或易混淆的要素类 别以及用以区分易出错或易混淆的要素类别的综合光谱指数中植被指数、水体指数以及差分建筑物指数的权重系数。
作为一种实施方式，排序模块204具体包括：
数值确定单元，用于确定每一所述图斑影像的综合光谱指数的中间值或平均值；
排序单元，用于根据图斑影像的综合光谱指数的中间值或平均值的大小，分要素类对各图斑影像进行排序。
作为一种实施方式，所述类别异常确定模块205具体包括：
判断单元，用于判断相邻图斑影像的综合光谱指数的差值是否大于设定阈值；
类别异常图斑确定单元，用于在相邻图斑影像的综合光谱指数的差值大于设定阈值时，将相邻图斑影像到图斑序列第一端之间所有的图斑确定我类别异常图斑，所述第一端为图斑序列中距离所述相邻图斑影像较近的一端。
作为一种实施方式，所述系统还包括：
归一化处理模块，用于对所述植被指数和所述水体指数进行归一化处理；
拉伸处理模块，用于对所述差分建筑物指数以及归一化的植被指数和水体指数进行拉伸处理。
本发明提供的类型异常图斑自动识别方法及系统实现了大图斑及同谱异物错误的自动提取，提高了地表覆盖数据质量检测的效率和可靠性，有效提升了地理国情成果的质量。
本说明书中各个实施例采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似部分互相参见即可。对于实施例公开的系统而言，由于其与实施例公开的方法相对应，所以描述的比较简单，相关之处参见方法部分说明即可。
本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的一般技术人员，依据本发明的思想，在具体实施方式及应用范围 上均会有改变之处。综上所述，本说明书内容不应理解为对本发明的限制。

Claims (10)

  1. 一种类型异常图斑自动识别方法，其特征在于，包括：
    获取待识别多光谱遥感影像；
    基于图斑的几何范围，对所述多光谱遥感影像进行裁切，以获得类别易出错或易混淆的图斑的影像；
    计算各图斑影像的综合光谱指数，所述综合光谱指数由植被指数、水体指数以及差分建筑物指数加权组合构成，用以区分图斑要素类别；
    根据各图斑影像的综合光谱指数的大小，分要素类对各图斑影像进行排序；
    确定图斑影像序列前后设定数量的图斑影像中是否存在类别异常图斑；
    如果存在类别异常图斑，则在图斑影像序列的前和/或后增加设定数量的图斑影像，并对增加的图斑影像进行类别异常识别，如果增加的图斑影像中存在类别异常图斑，则跳转至“在图斑影像序列的前和/或后增加设定数量的图斑影像进行识别”步骤，直至增加的图斑影像中不存在类别异常图斑为止，
    输出类别异常图斑影像。
  2. 根据权利要求1所述的类型异常图斑自动识别方法，其特征在于，在所述基于图斑的几何范围，对所述多光谱遥感影像进行裁切之前，还包括：
    根据历史数据确定易出错或易混淆的要素类别以及用以区分易出错或易混淆的要素类别的综合光谱指数中植被指数、水体指数以及差分建筑物指数的权重系数。
  3. 根据权利要求1所述的类型异常图斑自动识别方法，其特征在于，所述根据各图斑影像的综合光谱指数的大小，分要素类对各图斑影像进行排序，具体包括：
    确定每一所述图斑影像的综合光谱指数的中间值或平均值；
    根据图斑影像的综合光谱指数的中间值或平均值的大小，分要素类对各图斑影像进行排序。
  4. 根据权利要求1所述的类型异常图斑自动识别方法，其特征在于，所述类别异常图斑检测方法包括：
    判断相邻图斑影像的综合光谱指数的差值是否大于设定阈值；
    如果是，则表示存在类别异常图斑，且类别异常图斑为所述相邻图斑影像到图斑序列第一端之间所有的图斑，所述第一端为图斑序列距离所述相邻图斑影像较近的一端。
  5. 根据权利要求1所述的类型异常图斑自动识别方法，其特征在于，在所述计算各图斑影像的综合光谱指数之前，还包括：
    对所述植被指数和所述水体指数进行归一化处理；
    对所述差分建筑物指数以及归一化的植被指数和水体指数进行拉伸处理。
  6. 根据权利要求1所述的类型异常图斑自动识别方法，其特征在于，所述方法还包括：
    向人机交互端输出计算机识别出的类别异常图斑影像，以供人工进行二次识别。
  7. 根据权利要求1所述的类型异常图斑自动识别方法，其特征在于，所述多光谱遥感影像的裁切过程在计算机内存中进行。
  8. 一种类型异常图斑自动识别系统，其特征在于，包括：
    待识别多光谱遥感影像获取模块，用于获取待识别多光谱遥感影像；
    图斑影像裁切模块，用于基于图斑的几何范围，对所述多光谱遥感影像进行裁切，以获得类别易出错或易混淆的图斑的影像；
    综合光谱指数计算模块，用于计算各图斑影像的综合光谱指数，所述综合光谱指数由植被指数、水体指数以及差分建筑物指数加权组合构成，用以区分图斑要素类别；
    排序模块，用于根据各图斑影像的综合光谱指数的大小，分要素类对各图斑影像进行排序；
    类别异常确定模块，用于确定图斑影像序列前后设定数量的图斑影像中是否存在类别异常图斑，以及确定增加的图斑影像中是否存在类别异常 图斑。
  9. 根据权利要求8所述的类型异常图斑自动识别系统，其特征在于，所述系统还包括：
    初始参数确定模块，用于根据历史数据确定易出错或易混淆的要素类别以及用以区分易出错或易混淆的要素类别的综合光谱指数中植被指数、水体指数以及差分建筑物指数的权重系数。
  10. 根据权利要求8所述的类型异常图斑自动识别系统，其特征在于，所述排序模块，具体包括：
    数值确定单元，用于确定每一所述图斑影像的综合光谱指数的中间值或平均值；
    排序单元，用于根据图斑影像的综合光谱指数的中间值或平均值的大小，分要素类对各图斑影像进行排序。
PCT/CN2020/100451 2020-06-12 2020-07-06 一种类型异常图斑自动识别方法及系统 WO2021248599A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010534638.9 2020-06-12
CN202010534638.9A CN111709927B (zh) 2020-06-12 2020-06-12 一种类型异常图斑自动识别方法及系统

Publications (1)

Publication Number Publication Date
WO2021248599A1 true WO2021248599A1 (zh) 2021-12-16

Family

ID=72540346

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/100451 WO2021248599A1 (zh) 2020-06-12 2020-07-06 一种类型异常图斑自动识别方法及系统

Country Status (3)

Country Link
CN (1) CN111709927B (zh)
AU (1) AU2021102441A4 (zh)
WO (1) WO2021248599A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113484245A (zh) * 2021-07-05 2021-10-08 重庆市规划和自然资源调查监测院 一种丘陵山区水田种植模式遥感快速监测方法、系统及计算机可读存储介质
CN114491187A (zh) * 2022-01-20 2022-05-13 重庆市规划和自然资源调查监测院 一种自然资源智能监测集成系统
CN118155005A (zh) * 2024-05-13 2024-06-07 成都坤舆空间科技有限公司 一种基于RAFT-Stereo算法的生态修复图斑匹配分类方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120271609A1 (en) * 2011-04-20 2012-10-25 Westerngeco L.L.C. Methods and computing systems for hydrocarbon exploration
KR101756380B1 (ko) * 2017-03-06 2017-07-10 한국지질자원연구원 공작석 초분광 영상을 이용한 반암동 광체 탐지 방법
CN109726679A (zh) * 2018-12-28 2019-05-07 常州市星图测绘科技有限公司 一种遥感分类误差空间分布制图方法
CN110135310A (zh) * 2019-04-30 2019-08-16 云南财经大学 一种基于单变量特征选择方法的农作物遥感识别方法
CN111144249A (zh) * 2019-12-16 2020-05-12 广州地理研究所 基于自动优化mesma的地表覆盖类型确定方法
CN111178169A (zh) * 2019-12-12 2020-05-19 广州地理研究所 一种基于遥感影像的城市地表覆盖物精细分类方法及装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103593853B (zh) * 2013-11-29 2016-05-11 武汉大学 基于联合稀疏表达的遥感影像多尺度面向对象分类方法
CN103593852A (zh) * 2013-11-29 2014-02-19 中国科学院光电研究院 基于同质图斑的高光谱影像异常探测方法
CN104408463B (zh) * 2014-10-15 2020-05-12 中国土地勘测规划院 一种高分辨率建设用地图斑识别方法
EP3173975A1 (en) * 2015-11-30 2017-05-31 Delphi Technologies, Inc. Method for identification of candidate points as possible characteristic points of a calibration pattern within an image of the calibration pattern
CN110363798B (zh) * 2019-07-24 2022-02-18 宁波市测绘和遥感技术研究院 一种遥感影像解译样本集的生成方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120271609A1 (en) * 2011-04-20 2012-10-25 Westerngeco L.L.C. Methods and computing systems for hydrocarbon exploration
KR101756380B1 (ko) * 2017-03-06 2017-07-10 한국지질자원연구원 공작석 초분광 영상을 이용한 반암동 광체 탐지 방법
CN109726679A (zh) * 2018-12-28 2019-05-07 常州市星图测绘科技有限公司 一种遥感分类误差空间分布制图方法
CN110135310A (zh) * 2019-04-30 2019-08-16 云南财经大学 一种基于单变量特征选择方法的农作物遥感识别方法
CN111178169A (zh) * 2019-12-12 2020-05-19 广州地理研究所 一种基于遥感影像的城市地表覆盖物精细分类方法及装置
CN111144249A (zh) * 2019-12-16 2020-05-12 广州地理研究所 基于自动优化mesma的地表覆盖类型确定方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LIU, WEI: "Auto-identify Classification Technology for LUCC Information Based on Remote Sensing Data", DOCTORAL DISSERTATION, 15 November 2012 (2012-11-15), CN, pages 1 - 158, XP009532889 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113484245A (zh) * 2021-07-05 2021-10-08 重庆市规划和自然资源调查监测院 一种丘陵山区水田种植模式遥感快速监测方法、系统及计算机可读存储介质
CN113484245B (zh) * 2021-07-05 2022-11-22 重庆市规划和自然资源调查监测院 一种丘陵山区水田种植模式遥感快速监测方法、系统及计算机可读存储介质
CN114491187A (zh) * 2022-01-20 2022-05-13 重庆市规划和自然资源调查监测院 一种自然资源智能监测集成系统
CN118155005A (zh) * 2024-05-13 2024-06-07 成都坤舆空间科技有限公司 一种基于RAFT-Stereo算法的生态修复图斑匹配分类方法

Also Published As

Publication number Publication date
CN111709927A (zh) 2020-09-25
CN111709927B (zh) 2022-05-27
AU2021102441A4 (en) 2021-06-24

Similar Documents

Publication Publication Date Title
WO2022042579A1 (zh) 一种用于lcd屏幕的缺陷检测方法、装置
WO2021248599A1 (zh) 一种类型异常图斑自动识别方法及系统
US7184890B2 (en) Cloud shadow detection: VNIR-SWIR
CN110376202B (zh) 基于成像高光谱技术的茶树炭疽病病斑识别方法
CN111091052A (zh) 一种基于最大似然法的玉米倒伏面积提取系统及方法
Gujjar et al. A method for identification of basmati rice grain of india and its quality using pattern classification
CN110309781A (zh) 基于多尺度光谱纹理自适应融合的房屋损毁遥感识别方法
CN108446584A (zh) 一种无人机侦察视频图像目标自动检测方法
CN108563979B (zh) 一种基于航拍农田图像判别水稻稻瘟病病情的方法
Ji et al. In-field automatic detection of maize tassels using computer vision
CN114937038B (zh) 面向可用性的遥感影像质量评价方法
CN115439759B (zh) 遥感影像中植被的提取方法、装置、电子设备及介质
CN117636185B (zh) 基于图像处理的松材线虫病检测系统
US20050111692A1 (en) Cloud cover assessment: VNIR-SWIR
CN111007013B (zh) 面向东北冷凉区的作物轮作休耕遥感监测方法与装置
CN111060455B (zh) 面向东北冷凉区的遥感图像作物标记方法和装置
CN116152220A (zh) 一种基于机器视觉的种子计数和尺寸测量方法
US7058511B2 (en) Sub-visible cloud cover assessment: VNIR-SWIR
CN111882573A (zh) 一种基于高分辨率影像数据的耕地地块提取方法及系统
CN114511781B (zh) 无人机搭载多光谱相机对伪装人员识别的方法、装置及介质
CN115587993A (zh) 一种基于ai与机器视觉算法的口罩焊点缺陷检测方法
CN114549494A (zh) 一种温室生产环境下草莓白粉病快速检测方法
JP5644655B2 (ja) 食用果実の検査方法、検査装置およびプログラム
CN114266975B (zh) 无人机遥感图像的荔枝果实检测与计数方法
CN111401275B (zh) 一种用于识别草地边缘的信息处理方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20940375

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20940375

Country of ref document: EP

Kind code of ref document: A1