WO2019090509A1 - Procédé et systѐme de classification d'images hyperspectrales - Google Patents

Procédé et systѐme de classification d'images hyperspectrales Download PDF

Info

Publication number
WO2019090509A1
WO2019090509A1 PCT/CN2017/109914 CN2017109914W WO2019090509A1 WO 2019090509 A1 WO2019090509 A1 WO 2019090509A1 CN 2017109914 W CN2017109914 W CN 2017109914W WO 2019090509 A1 WO2019090509 A1 WO 2019090509A1
Authority
WO
WIPO (PCT)
Prior art keywords
classified
test set
feature point
local feature
feature points
Prior art date
Application number
PCT/CN2017/109914
Other languages
English (en)
Chinese (zh)
Inventor
李岩山
王贤辰
谢维信
Original Assignee
深圳大学
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 深圳大学 filed Critical 深圳大学
Priority to PCT/CN2017/109914 priority Critical patent/WO2019090509A1/fr
Publication of WO2019090509A1 publication Critical patent/WO2019090509A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition

Definitions

  • the invention belongs to the technical field of image processing, and in particular relates to a method and a system for classifying hyperspectral images.
  • hyperspectral images Compared with grayscale and RGB color maps, hyperspectral images contain spatial and spectral information, large amounts of data, and have important applications in detecting camouflage and concealed military targets, as well as in civilian search and rescue targets.
  • the current hyperspectral image exhibits high spatial resolution.
  • the object target has rich texture and structural information on the hyperspectral image, and the spectral information it contains is also very complicated and rich.
  • hyperspectral imagery uses many narrow electromagnetic wave bands to obtain useful information from objects of interest. While retaining high spatial resolution, its spectral resolution is greatly improved, reaching nanometers. An order of magnitude that can be used to detect and identify undetectable feature categories in traditional panchromatic and multispectral remote sensing.
  • hyperspectral remote sensing images Compared with traditional multi-spectral remote sensing images, hyperspectral remote sensing images have the characteristics of large amount of information and high spectral resolution, which greatly enhances the ability to describe and distinguish the types of features. It makes the original in multi-spectral remote sensing. Ground objects that cannot be effectively detected are detected.
  • conventional image classification methods have great limitations in processing hyperspectral images. How to quickly and accurately mine the required information from a large number of hyperspectral data to achieve high The classification of precision is still an urgent problem to be solved.
  • Traditional hyperspectral image classification mainly uses pixel-level classification methods.
  • Traditional remote sensing monitoring methods are mainly composed of medium and low resolution.
  • the size of an object on an image is the same size as a pixel.
  • the pixel-level classification method is suitable for such hyperspectral image classification.
  • the resolution of space and spectrum in hyperspectral images has been greatly improved.
  • Traditional pixel fraction at this time Class methods have not been well adapted to hyperspectral classification.
  • the word bag model is widely used due to its simplified representation of hyperspectral images and efficient coding of image features and visual words.
  • the classification method of the word bag model is shown in Figure 1. It is mainly divided into the following steps: 1 Extracting feature points from the image and describing them (such as SIFT features, Scale-invariant feature transform, scale-invariant feature transform characteristics) 2; K-means and other methods are used to train the generated feature points into a visual dictionary; 3 through the image feature coding method, the image features to be classified are mapped to visual words in the visual dictionary; 4 through the pooling algorithm to form image descriptors 5 categorize the image descriptors by a classification algorithm such as a support vector machine.
  • Hyperspectral feature coding is the process of quantifying the feature points of the image to be classified into visual words. The coding error is the main factor affecting the correct rate of image classification.
  • the traditional hyperspectral remote sensing image has low resolution, and the optical image has low resolution and low spectral resolution.
  • Most optical image resolutions are based on pixel-level spectral curves to analyze data. Most of the cases require pixel de-mixing, while low spectral resolution yields less information, which is prone to "foreign matter” and "same spectrum”.
  • the phenomenon of foreign matter, and the uncertainty of the mapping relationship between hyperspectral image feature points and hyperspectral words, the recognition of similar images is poor.
  • the large-scale high-resolution hyperspectral is a high-dimensional fine big data feature space.
  • the technical problem to be solved by the present invention is to provide a classification method and system for hyperspectral images, aiming at solving the uncertainty existing in the prior art in establishing a mapping relationship between hyperspectral image feature points and hyperspectral words, and the similar image recognition power difference The problem.
  • the present invention is achieved in such a manner that a method for classifying hyperspectral images includes:
  • the hyperspectral image is divided into a training set and a test set, and local feature points of the training set and local feature points of the test set to be classified are respectively extracted from the training set and the test set, according to local feature points of the training set and
  • the local feature points to be classified of the test set constitute a training set feature point set and a test set to be classified feature point set;
  • the neighboring feature points, the neighboring words and the spectral dimension distance triple constraint are introduced.
  • the local feature points of the test set to be classified and the coding coefficients of the dictionary words are obtained.
  • the coding coefficients are pooled by a maximum pooling algorithm, and the encoded coefficients obtained by the pooling are used as feature descriptors of the hyperspectral image, and the test set of the hyperspectral image is classified according to the feature descriptor.
  • test set to Y represents a group of local feature point set to be classified, when B is a dictionary, a Y y i to the i-th local feature point to be classified, y i expressed in [mu] i of Corresponding to the band information, the coding coefficient is represented by Z, then:
  • d i is the Euclidean distance between the local feature point y i to be classified and the dictionary word
  • d ij is the Euclidean distance between the local feature point to be classified and the neighbor feature point
  • h i is the spectral dimension between y i and the dictionary word
  • the Euclidean distance, ⁇ 1 , ⁇ 2 and ⁇ 3 are penalty factors.
  • the problem of solving the constrained minimum multiplication by solving includes:
  • the invention also provides a classification system for hyperspectral images, comprising:
  • a feature point extracting unit configured to divide the hyperspectral image into a training set and a test set, respectively extracting a local feature point of the training set and a local feature point of the test set to be classified from the training set and the test set, according to the
  • the local feature points of the training set and the local feature points of the test set to be classified constitute a training set A set of feature points to be classified and a set of test points to be classified;
  • a feature point calculation unit configured to calculate a local feature point of the training set by a K-means algorithm to form a dictionary, and adopt a KNN algorithm to form a nearest neighbor of the local feature points of the test set to be classified in the dictionary a word, using a KNN algorithm, searching for a nearest neighbor feature point for the feature point to be classified of the test set, and finding a neighbor word with the shortest spectral distance in the nearest neighbor word;
  • the image classification unit is used to introduce the neighboring feature points, the neighboring words and the spectral dimension distance triple constraint.
  • the local feature points and dictionary words to be classified in the test set to be classified are obtained.
  • a coding coefficient the coding coefficient is pooled by a maximum pooling algorithm, and the encoded coefficient obtained by the pooling is used as a feature descriptor of the hyperspectral image, and the test set of the hyperspectral image is determined according to the feature descriptor sort.
  • test set to Y represents a group of local feature point set to be classified, when B is a dictionary, a Y y i to the i-th local feature point to be classified, y i expressed in [mu] i of Corresponding to the band information, the coding coefficient is represented by Z, then:
  • d i is the Euclidean distance between the local feature point y i to be classified and the dictionary word
  • d ij is the Euclidean distance between the local feature point to be classified and the neighbor feature point
  • h i is the spectral dimension between y i and the dictionary word
  • the Euclidean distance, ⁇ 1 , ⁇ 2 and ⁇ 3 are penalty factors.
  • step of the image classification unit solving the constraint minimum multiplication fitting problem comprises:
  • the invention has the beneficial effects of introducing the local constraint of the hyperspectral image band information and the local correlation information of the neighbor feature points as the image feature points on the basis of the local constraints of the hyperspectral word points on the hyperspectral features.
  • the classification criterion solves the uncertainty existing in the mapping relationship between hyperspectral image feature points and dictionary words, and improves the recognition ability of similar images.
  • FIG. 1 is a flow chart of a method for classifying a word bag model provided by the prior art
  • FIG. 2 is a flowchart of a method for classifying hyperspectral images according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of a classification system for hyperspectral images according to an embodiment of the present invention.
  • FIG. 2 is a diagram showing a method for classifying hyperspectral images according to an embodiment of the present invention, including:
  • the hyperspectral image is divided into a training set and a test set, and local feature points of the training set and local feature points of the test set to be classified are respectively extracted from the training set and the test set, according to local features of the training set.
  • a point and a local feature point of the test set to be classified constitute a training set feature point set and a test set to be classified feature point set;
  • the coding coefficient is pooled by a maximum pooling algorithm, and the encoded coefficient obtained by the pooling is used as a feature descriptor of the hyperspectral image, and the test set of the hyperspectral image is performed according to the feature descriptor. classification.
  • the classification method provided by the embodiment of the present invention proposes a triple three-dimensional locality constrained linear coding algorithm, which introduces hyperspectral image band information and local related information of neighboring feature points on the basis of local constraints of hyperspectral words on hyperspectral feature points.
  • the local constraint is used as the distinguishing item of image feature point classification, which solves the uncertainty of the mapping relationship between hyperspectral image feature points and hyperspectral words, and improves the recognition ability of similar images.
  • the specific triple constraint refers to the local constraint of hyperspectral words, neighbor feature points and hyperspectral image band information on hyperspectral feature points.
  • Three-dimensional refers to the introduction of spectral dimensions on the basis of hyperspectral two-dimensional space.
  • the three-dimensional three-dimensional local constraint linear coding algorithm model is as follows:
  • B [b 1 , b 2 , ..., b M ] ⁇
  • R D ⁇ M denotes a dictionary
  • y i denotes the i-th local feature point to be classified in Y
  • ⁇ i denotes corresponding band information indicating y i , where [ ⁇ 1 , ⁇ 2 , . . .
  • d i is the Euclidean distance between the feature point y i and the dictionary word
  • the feature point d ij is the Euclidean distance between the feature point to be classified and the neighbor feature point
  • h i is the spectral dimension between the feature point y i and the dictionary word European distance.
  • ⁇ 1 , ⁇ 1 and ⁇ 3 are penalty factors, and ⁇ 1 , ⁇ 1 and ⁇ 3 are set according to the data set size of the hyperspectral image and the image feature similarity.
  • Constraint 1 T z i 1 also satisfies the requirement of translation invariance of LLC (Locality-constrained Linear Coding) coding coefficients.
  • item 1 in the above formula For signal fidelity, ensure that the classification signal energy is not lost; item 2 Is the coefficient z i constrained by the Euclidean distance of the nearest neighbor of the feature point, ensuring that the feature point is mapped to the nearest neighbor word;
  • the coefficient z i is constrained by the neighboring feature points to eliminate the ambiguity and uncertainty in the classification of hyperspectral image caused by external factors such as light changes and shooting angles; It is to use the coefficient z i to be constrained by the band of the neighbor word of the feature point, and to ensure that the feature point is mapped to the word with the closest band.
  • FIG. 3 shows a classification system for hyperspectral images provided by an embodiment of the present invention, including:
  • the feature point extraction unit 301 is configured to divide the hyperspectral image into a training set and a test set, and extract local feature points of the training set and local feature points of the test set from the training set and the test set, respectively, according to the The local feature points of the training set and the local feature points of the test set to be composed constitute a training set feature point set and a test set to be classified feature point set;
  • the feature point calculation unit 302 is configured to calculate a local feature point of the training set by using a K-means algorithm to form a dictionary, and adopt a KNN algorithm in which a local feature point to be classified of the test set is formed in the dictionary. a neighboring word, using a KNN algorithm, searching for a nearest neighbor feature point for the feature point to be classified of the test set, and finding a neighbor word with the shortest spectral distance in the nearest neighbor word;
  • the image classification unit 303 is configured to introduce a neighboring feature point, a neighboring word, and a spectral dimension distance triple constraint.
  • the local feature point and the dictionary word to be classified in the test feature to be classified in the test set are obtained.
  • a coding coefficient the coding coefficient is pooled by a maximum pooling algorithm, and the encoded coefficient obtained by the pooling is used as a feature descriptor of the hyperspectral image, and the test set of the hyperspectral image is determined according to the feature descriptor sort.
  • test set to Y represents a group of local feature point set to be classified, when B is a dictionary, a Y y i to the i-th local feature point to be classified, y i expressed in [mu] i of Corresponding to the band information, the coding coefficient is represented by Z, then:
  • d i is the Euclidean distance between the local feature point y i to be classified and the dictionary word
  • d ij is the Euclidean distance between the local feature point to be classified and the neighbor feature point
  • h i is the spectral dimension between y i and the dictionary word
  • the Euclidean distance, ⁇ 1 , ⁇ 2 and ⁇ 3 are penalty factors.
  • step of the image classification unit 303 solving the constraint minimum multiplication fitting problem includes:

Landscapes

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

Abstract

La présente invention peut s'appliquer à la classification d'images. L'invention concerne un procédé de classification d'images hyperspectrales, consistant à : diviser des images hyperspectrales en un ensemble d'apprentissage et un ensemble d'essai et extraire des points caractéristiques locaux ; calculer les points caractéristiques locaux de l'ensemble d'apprentissage au moyen d'un algorithme des K moyennes pour former un dictionnaire ; former les mots voisins les plus proches dans le dictionnaire pour des points caractéristiques locaux à classer de l'ensemble d'essai à l'aide d'un algorithme KNN et rechercher les points caractéristiques voisins les plus proches pour des points caractéristiques à classer des images dans l'ensemble d'essai ; rechercher le mot voisin ayant la distance de dimension spectrale la plus courte parmi les mots voisins les plus proches ; introduire les trois contraintes des points caractéristiques voisins, les mots voisins et la distance de dimension spectrale ; résoudre le problème d'ajustement de contrainte moins absolu pour obtenir un coefficient de codage ; et regrouper le coefficient de codage au moyen d'un algorithme de regroupement maximum et classer l'ensemble d'essai en prenant le coefficient de codage obtenu en tant que descripteur de caractéristique des images hyperspectrales. Le problème d'incertitude, lorsqu'une relation de correspondance entre un point caractéristique d'image hyperspectrale et un mot de dictionnaire est établie, est résolu et le discernement d'images similaires est amélioré.
PCT/CN2017/109914 2017-11-08 2017-11-08 Procédé et systѐme de classification d'images hyperspectrales WO2019090509A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/109914 WO2019090509A1 (fr) 2017-11-08 2017-11-08 Procédé et systѐme de classification d'images hyperspectrales

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/109914 WO2019090509A1 (fr) 2017-11-08 2017-11-08 Procédé et systѐme de classification d'images hyperspectrales

Publications (1)

Publication Number Publication Date
WO2019090509A1 true WO2019090509A1 (fr) 2019-05-16

Family

ID=66439056

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/109914 WO2019090509A1 (fr) 2017-11-08 2017-11-08 Procédé et systѐme de classification d'images hyperspectrales

Country Status (1)

Country Link
WO (1) WO2019090509A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111967182A (zh) * 2020-07-24 2020-11-20 天津大学 一种用于光谱分析的基于混合标记的高光谱建模方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005050533A2 (fr) * 2003-11-13 2005-06-02 Honda Motor Co., Ltd. Regroupement d'images a l'aide de mesures, d'une structure lineaire locale et d'une symetrie affine
CN103208011A (zh) * 2013-05-05 2013-07-17 西安电子科技大学 基于均值漂移和组稀疏编码的高光谱图像空谱域分类方法
CN104408466A (zh) * 2014-11-17 2015-03-11 中国地质大学（武汉） 基于局部流形学习构图的高光谱遥感图像半监督分类方法
CN104820840A (zh) * 2015-05-08 2015-08-05 西安电子科技大学 基于字典和波段重组的最近邻高光谱图像分类方法
CN105809205A (zh) * 2016-03-31 2016-07-27 深圳大学 一种高光谱图像的分类方法及其系统
CN106203510A (zh) * 2016-07-11 2016-12-07 南京大学 一种基于形态学特征和字典学习的高光谱图像分类方法
CN107823793A (zh) * 2017-11-21 2018-03-23 孝感葵兴机械科技有限公司 一种便携式神经肌肉康复治疗设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005050533A2 (fr) * 2003-11-13 2005-06-02 Honda Motor Co., Ltd. Regroupement d'images a l'aide de mesures, d'une structure lineaire locale et d'une symetrie affine
CN103208011A (zh) * 2013-05-05 2013-07-17 西安电子科技大学 基于均值漂移和组稀疏编码的高光谱图像空谱域分类方法
CN104408466A (zh) * 2014-11-17 2015-03-11 中国地质大学（武汉） 基于局部流形学习构图的高光谱遥感图像半监督分类方法
CN104820840A (zh) * 2015-05-08 2015-08-05 西安电子科技大学 基于字典和波段重组的最近邻高光谱图像分类方法
CN105809205A (zh) * 2016-03-31 2016-07-27 深圳大学 一种高光谱图像的分类方法及其系统
CN106203510A (zh) * 2016-07-11 2016-12-07 南京大学 一种基于形态学特征和字典学习的高光谱图像分类方法
CN107823793A (zh) * 2017-11-21 2018-03-23 孝感葵兴机械科技有限公司 一种便携式神经肌肉康复治疗设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111967182A (zh) * 2020-07-24 2020-11-20 天津大学 一种用于光谱分析的基于混合标记的高光谱建模方法
CN111967182B (zh) * 2020-07-24 2024-04-02 天津大学 一种用于光谱分析的基于混合标记的高光谱建模方法

Similar Documents

Publication Publication Date Title
CN109598241B (zh) 基于Faster R-CNN的卫星图像海上舰船识别方法
Chen et al. Building change detection with RGB-D map generated from UAV images
CN107992891B (zh) 基于光谱矢量分析多光谱遥感图像变化检测方法
CN107480620B (zh) 基于异构特征融合的遥感图像自动目标识别方法
CN105528794A (zh) 基于混合高斯模型与超像素分割的运动目标检测方法
CN109635726B (zh) 一种基于对称式深度网络结合多尺度池化的滑坡识别方法
CN107832793B (zh) 一种高光谱图像的分类方法及系统
Huang et al. A multispectral and multiangle 3-D convolutional neural network for the classification of ZY-3 satellite images over urban areas
CN107578003B (zh) 一种基于地理标记图像的遥感图像迁移学习方法
Liu et al. Density saliency for clustered building detection and population capacity estimation
Baik et al. Domain adaptation of learned features for visual localization
CN114140700A (zh) 基于级联网络的分步异源图像模板匹配方法
Li et al. Detecting building changes using multi-modal Siamese multi-task networks from very high resolution satellite images
Zhong et al. Online learning 3D context for robust visual tracking
WO2019090509A1 (fr) Procédé et systѐme de classification d'images hyperspectrales
CN108171270B (zh) 一种基于哈希学习的高光谱图像分类方法
WO2023273337A1 (fr) Procédé basé sur des caractéristiques représentatives pour détecter des cibles denses dans une image de télédétection
Li et al. Automatic matching of multispectral images based on nonlinear diffusion of image structures
Li et al. Semantic segmentation for high-resolution aerial imagery using multi-skip network and Markov random fields
CN112131962B (zh) 基于电磁散射特征和深度网络特征的sar图像识别方法
Huo et al. Change field: A new change measure for VHR images
CN111160433B (zh) 一种高分辨率图像特征点的高速匹配方法及系统
CN106033545B (zh) 行列式点过程的波段选择方法
Wu et al. LW-ODF: A light-weight object detection framework for optical remote sensing imagery
Li et al. A new framework of hyperspectral image classification based on spatial spectral interest point

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: 17931463

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 30.06.2020)

122 Ep: pct application non-entry in european phase

Ref document number: 17931463

Country of ref document: EP

Kind code of ref document: A1