CN106485239A - One kind is using one-class support vector machines detection river mesh calibration method - Google Patents

One kind is using one-class support vector machines detection river mesh calibration method Download PDF

Info

Publication number
CN106485239A
CN106485239A CN201610944422.3A CN201610944422A CN106485239A CN 106485239 A CN106485239 A CN 106485239A CN 201610944422 A CN201610944422 A CN 201610944422A CN 106485239 A CN106485239 A CN 106485239A
Authority
CN
China
Prior art keywords
river
feature
support vector
target
vector machine
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.)
Pending
Application number
CN201610944422.3A
Other languages
Chinese (zh)
Inventor
薄树奎
荆永菊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhengzhou University of Aeronautics
Original Assignee
Zhengzhou University of Aeronautics
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 Zhengzhou University of Aeronautics filed Critical Zhengzhou University of Aeronautics
Priority to CN201610944422.3A priority Critical patent/CN106485239A/en
Publication of CN106485239A publication Critical patent/CN106485239A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • G06V20/182Network patterns, e.g. roads or rivers
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines

Landscapes

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

Abstract

为了解决现有技术中无法通过训练样本进行学习及检测结果不够准确的问题,本发明提供一种利用单类支持向量机检测河流目标的方法,提取遥感图像中的光谱特征后经过粗筛选过程,基于光谱特征,提取河流候选区域,再利用光谱值生成的特征向量对单类支持向量机进行训练。针对粗筛选过程的结果再进行精细检测,以便对河流候选区域进行图像分割,生成形状特征,最后根据形状指数阈值,实现目标检测。本发明使用单类支持向量机方法仅需要一类训练样本,提高检测效率;同时通过粗筛选和精细检测两个环节提高了检测的准确度。

In order to solve the problems in the prior art that it is impossible to learn through training samples and the detection results are not accurate enough, the present invention provides a method for detecting river targets using a single-class support vector machine, extracting spectral features in remote sensing images and then going through a rough screening process. Based on the spectral features, the river candidate regions are extracted, and then the feature vectors generated by the spectral values are used to train the one-class support vector machine. Based on the results of the coarse screening process, fine detection is performed to segment the image of the river candidate area, generate shape features, and finally realize target detection according to the shape index threshold. The invention uses the single-class support vector machine method to only need one class of training samples, thereby improving the detection efficiency; meanwhile, the detection accuracy is improved through two steps of coarse screening and fine detection.

Description

一种利用单类支持向量机检测河流目标的方法A Method of Detecting River Objects Using One-Class Support Vector Machine

技术领域technical field

本发明涉及图像处理与计算机视觉领域,尤其涉及一种利用单类支持向量机方法检测遥感图像中河流目标的方法。The invention relates to the fields of image processing and computer vision, in particular to a method for detecting river targets in remote sensing images using a single-class support vector machine method.

背景技术Background technique

目标检测与跟踪是图像处理与计算机视觉领域的热门研究方向之一,在军事上的成像制导、跟踪军事目标,以及民事方面的安防监控、智能人机交互等方面均有着重要的研究价值。Target detection and tracking is one of the popular research directions in the field of image processing and computer vision. It has important research value in military imaging guidance and tracking military targets, as well as civil security monitoring and intelligent human-computer interaction.

现有的检测方法中,目标检测研究的难点在于对目标的有效表征,以及各种原因造成的目标尺度、旋转角度、光照等发生变化而引起的目标匹配问题。目标的表征在某种程度决定了匹配算法,包括:利用局部轮廓特征表示目标,首先提取图像目标的轮廓,并通过自动选取阈值滤去噪声边缘,得到显著性轮廓,从而能有效减少轮廓段数,降低后续特征提取及整个检测过程的时空复杂度。为了克服目标的尺度、旋转等变化,Lowe提出尺度不变特征变换(SIFT),通过计算多尺度高斯差分图像并寻找局部极大值点的方法,得到在一定范围内尺度、旋转不变特征。Among the existing detection methods, the difficulty of target detection research lies in the effective representation of the target, and the target matching problem caused by changes in the target scale, rotation angle, illumination, etc. caused by various reasons. The characterization of the target determines the matching algorithm to a certain extent, including: using local contour features to represent the target, first extracting the contour of the image target, and filtering out the noise edge by automatically selecting a threshold to obtain a salient contour, which can effectively reduce the number of contour segments. Reduce the time and space complexity of subsequent feature extraction and the entire detection process. In order to overcome changes in the scale and rotation of the target, Lowe proposed the Scale Invariant Feature Transform (SIFT). By calculating the multi-scale Gaussian difference image and finding the local maximum point, the scale and rotation invariant features within a certain range are obtained.

在目标检测中,除了目标自身的特征外,还可以利用上下文约束表征,实现图像目标的有效检测。在遥感图像目标检测中,由于图像尺寸较大而且复杂,为了避免产生较多的虚警,需要采取一定的措施尽量去除虚警目标。一般采用的方法是先由简单特征筛选出候选目标区域,然后再对候选区域进行精细检测。再有的,针对遥感图像飞机目标的检测问题,先使用级联式分类器检测出候选目标窗口,然后以Hough森林算法对候选窗口进行二次判断,滤除虚警,提高了检测效率,节省了运算时间。In object detection, in addition to the characteristics of the object itself, contextual constraints can also be used to achieve effective detection of image objects. In remote sensing image target detection, due to the large size and complexity of the image, in order to avoid more false alarms, it is necessary to take certain measures to remove false alarm targets as much as possible. The general method is to screen candidate target areas by simple features first, and then fine-tune the candidate areas. Furthermore, for the detection of aircraft targets in remote sensing images, a cascade classifier is used to detect candidate target windows, and then the Hough Forest algorithm is used to make a second judgment on the candidate windows to filter out false alarms, which improves the detection efficiency and saves operation time.

常用的分类方法如K-最近邻分类器、贝叶斯分类方法都具有过程较为复杂的缺点。Commonly used classification methods such as K-nearest neighbor classifier and Bayesian classification method all have the disadvantage of complicated process.

如K-最近邻是分类器算法中最通俗易懂的一种,计算测试样本到各训练样本的距离,取其中最小的K个,并根据这K个训练样本的标记进行投票得到测试样本的标记。算法的思路清晰简单,然而对于海量数据计算量过大,每个训练样本都有一个距离必须度量,耗费大量时间。For example, K-Nearest Neighbor is the most popular and easy-to-understand classifier algorithm. Calculate the distance between the test sample and each training sample, take the smallest K of them, and vote according to the marks of the K training samples to get the test sample. mark. The idea of the algorithm is clear and simple. However, the amount of calculation is too large for massive data, and each training sample has a distance that must be measured, which consumes a lot of time.

贝叶斯分类方法需要采用多个阶段完成计算:第一阶段——准备工作阶段,这个阶段的任务是为朴素贝叶斯分类做必要的准备,主要工作是根据具体情况确定特征属性,并对每个特征属性进行适当划分,然后由人工对一部分待分类项进行分类,形成训练样本集合。这一阶段的输入是所有待分类数据,输出是特征属性和训练样本。这一阶段是整个朴素贝叶斯分类中唯一需要人工完成的阶段,其质量对整个过程将有重要影响,分类器的质量很大程度上由特征属性、特征属性划分及训练样本质量决定。The Bayesian classification method needs to use multiple stages to complete the calculation: the first stage - the preparation stage, the task of this stage is to make the necessary preparations for the Naive Bayesian classification, the main work is to determine the feature attributes according to the specific situation, and to Each feature attribute is properly divided, and then a part of the items to be classified is manually classified to form a training sample set. The input of this stage is all the data to be classified, and the output is feature attributes and training samples. This stage is the only stage that needs to be completed manually in the entire Naive Bayesian classification, and its quality will have an important impact on the entire process. The quality of the classifier is largely determined by the feature attributes, feature attribute division, and training sample quality.

第二阶段——分类器训练阶段,这个阶段的任务就是生成分类器,主要工作是计算每个类别在训练样本中的出现频率及每个特征属性划分对每个类别的条件概率估计,并将结果记录。其输入是特征属性和训练样本,输出是分类器。这一阶段是机械性阶段,根据前面讨论的公式可以由程序自动计算完成。The second stage - classifier training stage, the task of this stage is to generate a classifier, the main work is to calculate the frequency of occurrence of each category in the training samples and the conditional probability estimation of each category for each feature attribute division, and The results are recorded. Its input is feature attributes and training samples, and the output is a classifier. This stage is a mechanical stage, which can be automatically calculated by the program according to the formula discussed above.

第三阶段——应用阶段。这个阶段的任务是使用分类器对待分类项进行分类,其输入是分类器和待分类项,输出是待分类项与类别的映射关系。这一阶段也是机械性阶段,由程序完成。The third stage - the application stage. The task of this stage is to use the classifier to classify the items to be classified, the input is the classifier and the items to be classified, and the output is the mapping relationship between the items to be classified and the categories. This stage is also a mechanical stage, completed by the program.

河流是遥感图像中的重要目标,河流目标检测在军事和民事方面都有广泛应用。现有技术中,在目标检测环节,图像目标检测中往往利用多种特征如颜色(光谱)特征、形状结构特征、纹理特征、上下文特征、SIFT特征等。在实际目标检测应用中,特征选择的原则是应能有效的对目标进行表征,对于不同的目标,特征选择结果也不同。Rivers are important targets in remote sensing images, and river target detection is widely used in military and civil affairs. In the prior art, in the target detection process, various features such as color (spectral) features, shape structure features, texture features, context features, SIFT features, etc. are often used in image target detection. In the actual target detection application, the principle of feature selection is to effectively characterize the target. For different targets, the feature selection results are also different.

光谱特征是图像像素的灰度值,表示地面目标的光谱反射特性,经常作为地物类别划分的依据,但不能反映待检测目标的几何结构特征。原始图像经过分割后产生的图像斑块具有形状结构特征,基于图像斑块内的像素坐标组成的矢量构造一个协方差矩阵,进一步可以提取该图像斑块的长宽比、形状指数、密度、主方向等特征。基于图像分割的特征提取,受分割方法和结果的影响很大,因此具有较高的不确定性。而纹理的表示方法很多,最常用的是基于灰度共生矩阵的纹理特征描述。灰度共生矩阵用两个位置的象素的联合概率密度来定义,它不仅反映亮度的分布特性,也反映具有同样亮度或接近亮度的象素之间的位置分布特性,是有关图象亮度变化的二阶统计特征,是定义一组纹理特征的基础。纹理特征对于一般的目标地面目标,区分性往往不强,常用的纹理特征有同质性、对比度、能量、熵等。The spectral feature is the gray value of the image pixel, which represents the spectral reflection characteristics of the ground object. It is often used as the basis for the classification of the ground object, but it cannot reflect the geometric structure characteristics of the target to be detected. The image patches generated after the original image is segmented have shape and structure characteristics, and a covariance matrix is constructed based on the vector composed of pixel coordinates in the image patches, and the aspect ratio, shape index, density, and main parameters of the image patches can be extracted further. characteristics such as direction. Feature extraction based on image segmentation is greatly affected by the segmentation method and results, so it has high uncertainty. There are many texture representation methods, the most commonly used is the texture feature description based on the gray level co-occurrence matrix. The gray level co-occurrence matrix is defined by the joint probability density of pixels at two positions. It not only reflects the distribution characteristics of brightness, but also reflects the distribution characteristics of the positions between pixels with the same brightness or close to brightness. It is related to the brightness change of the image. The second-order statistical features of are the basis for defining a set of texture features. Texture features are often not very distinguishable for general target ground targets. Commonly used texture features include homogeneity, contrast, energy, and entropy.

总之,现有的技术中:1.对于遥感图像河流目标检测方法采用的特征有颜色(光谱)特征、形状结构特征、纹理特征、上下文特征、SIFT特征等,算法复杂,检测的结果不够准确。In a word, in the existing technology: 1. The features used in the remote sensing image river target detection method include color (spectral) feature, shape structure feature, texture feature, context feature, SIFT feature, etc., the algorithm is complex, and the detection result is not accurate enough.

2.在目标检测任务中,要求从背景中检测出特定的目标类别,而背景中包含的类别数量不确定,一般无法对背景中的类别进行自动学习。2. In the target detection task, it is required to detect a specific target category from the background, but the number of categories contained in the background is uncertain, and it is generally impossible to automatically learn the categories in the background.

发明内容Contents of the invention

为了解决现有技术中无法通过训练样本进行学习及检测结果不够准确的问题,本发明提供一种利用单类支持向量机检测河流目标的方法,其具有:仅需要一类训练样本,采用单类分类向量机方法,克服了目标检测中非目标类别样本选择的困难,并使目标检测过程中的学习阶段简化,提高检测效率;同时通过粗筛选和精细检测两个环节提高了检测的准确度。In order to solve the problems in the prior art that the training samples cannot be used for learning and the detection results are not accurate enough, the present invention provides a method for detecting river targets using a single-class support vector machine. The classification vector machine method overcomes the difficulty of selecting non-target category samples in target detection, simplifies the learning stage in the process of target detection, and improves detection efficiency; at the same time, the accuracy of detection is improved through two links of coarse screening and fine detection.

本发明解决问题所采用的技术方案是:采用以下步骤:The technical solution adopted by the present invention to solve the problem is: adopt the following steps:

A.选择波段:在遥感图像中选取波段组合进行地物区分和河流提取,以便对水体、植被以及其他地面物体进行识别;A. Select the band: Select the band combination in the remote sensing image to distinguish the feature and extract the river, so as to identify the water body, vegetation and other ground objects;

B.特征分析与选择:选择A环节处理过的图像,进行光谱特征分析:光谱分析采用的光谱特征是:河流等水体目标在遥感图像中,以灰度值区分河流目标;B. Feature analysis and selection: Select the image processed in step A, and perform spectral feature analysis: the spectral feature used in spectral analysis is: rivers and other water targets in remote sensing images, distinguish river targets by gray value;

C.粗筛选过程:基于光谱特征,提取河流候选区域:选择若干目标样本,提取每个像素的光谱值作为分类特征,利用公式xi=(ri,gi,bi)生成特征向量,利用生成的特征向量对单类支持向量机进行训练,训练时采用RBF核函数进行训练,并通过10折交叉验证确定分类模型,对整个遥感影像进行单类分类,得到水体类别提取结果;其中,ri对应红色分量;gi对应绿色分量;bi对应蓝色分量;||xi-xj||表示空间中任意两点xi和xj之间的欧氏距离;γ为核参数。C. Rough screening process: based on spectral features, extract river candidate areas: select several target samples, extract the spectral value of each pixel as a classification feature, and use the formula x i = (r i , g i , b i ) to generate a feature vector, Use the generated feature vector to train the single-class support vector machine, and use the RBF kernel function during training Carry out training, and determine the classification model through 10-fold cross-validation, perform single-class classification on the entire remote sensing image, and obtain the water body category extraction result; among them, r i corresponds to the red component; g i corresponds to the green component; b i corresponds to the blue component; | | xi -x j || represents the Euclidean distance between any two points x i and x j in the space; γ is the kernel parameter.

D.精细检测过程:针对C环节中的结果,对河流候选区域进行图像分割,生成形状特征:在C环节粗筛选环节所得结果的基础上,采用图像分割技术,设置阈值参数,将大于阈值且相邻的像素进行合并,生成不同大小的目标类别连通区域,再由每个连通区域内的像素计算得到形状特征指数并设定面积阈值进行小区域去除,最后将去除小面域的图像合并到背景区域;其中,边界长e:边界象素的个数,一个象素的边界长为1;面积A:组成该对象的象素总数,其中一个象素边缘的长设为1。D. Fine detection process: Based on the results in the C link, image segmentation is performed on the river candidate area to generate shape features: On the basis of the results obtained in the C link rough screening, the image segmentation technology is used to set the threshold parameter, which will be greater than the threshold and Adjacent pixels are merged to generate target category connected regions of different sizes, and then the shape feature index is calculated from the pixels in each connected region And set the area threshold to remove the small area, and finally merge the image of the removed small area into the background area; where, the border length e: the number of border pixels, the border length of a pixel is 1; area A: the composition of the The total number of pixels of the object, where the length of a pixel edge is set to 1.

E.目标检测:设定形状指数阈值,并根据D环节得出的形状特征指数确定河流目标,实现目标检测。E. Target detection: set the shape index threshold, and determine the river target according to the shape feature index obtained in the D link, and realize the target detection.

所述的D环节的精细检测过程:采用阈值分割方法,以面积A的值为阈值,提取目标候选区域,同时生成形状特征S。The fine detection process of the D link: using the threshold segmentation method, using the area A as the threshold, extracting the target candidate area, and generating the shape feature S at the same time.

进一步的,所述的波段选择环节,选择遥感图像的4、3、2波段,分别赋予红、绿、蓝色,进行地物区分。Further, in the band selection link, the 4, 3, and 2 bands of the remote sensing image are selected, and red, green, and blue are respectively assigned to distinguish ground features.

进一步的,所述的特征分析与选择环节灰度值为10~20。Further, the gray value of the feature analysis and selection link is 10-20.

进一步的,所述的精细检测过程中图像分割时的阈值参数为:Th=10;面积阈值为:AT=50。Further, the threshold parameter for image segmentation in the fine detection process is: Th=10; the area threshold is: AT=50.

进一步的,所述的目标检测环节中的形状指数阈值为ST=2.5。Further, the shape index threshold in the target detection link is ST=2.5.

本发明的有益效果是:本发明使用单类支持向量机方法仅需要一类训练样本,克服了目标检测中非目标类别样本选择的困难,并使目标检测过程中的学习阶段简化,提高检测效率;同时通过粗筛选和精细检测两个环节提高了检测的准确度。The beneficial effects of the present invention are: the present invention only needs one class of training samples using the single-class support vector machine method, overcomes the difficulty of selecting non-target class samples in target detection, simplifies the learning stage in the target detection process, and improves detection efficiency ; At the same time, the accuracy of the detection is improved through the two links of coarse screening and fine detection.

附图说明Description of drawings

图1为遥感图像示意图。Figure 1 is a schematic diagram of a remote sensing image.

图2为利用单类支持向量机方法确定的河流候选区域示意图。Figure 2 is a schematic diagram of the river candidate regions determined by the single-class support vector machine method.

图3为利用最近邻分类方法确定的河流候选区域示意图。Figure 3 is a schematic diagram of river candidate regions determined by the nearest neighbor classification method.

图4为利用贝叶斯分类方法确定的河流候选区域示意图。Fig. 4 is a schematic diagram of river candidate areas determined by Bayesian classification method.

图5去除小于50像素的小区域示意图。Figure 5 is a schematic diagram of removing small areas smaller than 50 pixels.

图6形状特征指数大于2.5时的匹配结果示意图。Figure 6. Schematic diagram of matching results when the shape feature index is greater than 2.5.

具体实施方式detailed description

如图1~2所示,一种利用单类支持向量机检测河流目标的方法,采用以下步骤:As shown in Figures 1 and 2, a method for detecting river targets using a single-class support vector machine adopts the following steps:

A.遥感图像的波段选择,选取适合地物区分和河流提取的波段组合:选择遥感图像的4、3、2波段,分别赋予红、绿、蓝色,这些波段的组合成假彩色图像,其地物图像丰富,鲜明、层次好,能够较好的对水体、植被等进行识别。A. The band selection of the remote sensing image, select the band combination suitable for the distinction of ground features and river extraction: select the 4, 3, and 2 bands of the remote sensing image, and assign red, green, and blue colors respectively, and the combination of these bands forms a false color image. The images of ground features are rich, clear and well-layered, and can better identify water bodies and vegetation.

B.特征分析与选择:选择A环节处理过的图像,进行光谱特征分析:光谱分析采用的光谱特征是河流等水体目标的一个显著特征:在遥感图像中,河流目标具有较低的灰度值为10~20。B. Feature analysis and selection: Select the image processed in step A to perform spectral feature analysis: the spectral feature used in spectral analysis is a prominent feature of water objects such as rivers: in remote sensing images, river targets have lower gray values 10-20.

C.粗筛选过程:基于B环节中灰度特征的光谱分析,提取河流候选区域:首先,选择1000个像素作为目标类别样本,提取每个像素的光谱值作为分类特征xi=(ri,gi,bi),生成1000个特征向量xi,其中,ri为红色分量,gi为绿色分量,bi为蓝色分量。利用这些特征向量对单类支持向量机进行训练。给定l个训练样本,单类支持向量机最优化问题求解,即C. Rough screening process: Based on the spectral analysis of the gray features in the B link, extract the candidate area of the river: first, select 1000 pixels as the target category samples, and extract the spectral value of each pixel as the classification feature x i =(r i , g i , b i ), generate 1000 feature vectors x i , where ri is the red component, g i is the green component, and b i is the blue component. A one-class support vector machine is trained using these feature vectors. Given l training samples, the single-class support vector machine optimization problem is solved, namely

且满足(wTφ(xi)+b)≥1-ξi,ξi≥0 (2)。And satisfy (w T φ( xi )+b)≥1-ξ i , ξ i ≥0 (2).

其中,C>0是惩罚系数,φ(xi)是将向量xi映射到高维空间的函数;w是特征空间中分类面的法向量,wT是w的转置,b是w的截距,ξi是松弛因子。Among them, C>0 is the penalty coefficient, φ( xi ) is the function that maps the vector xi to a high-dimensional space; w is the normal vector of the classification surface in the feature space, w T is the transpose of w, and b is the The intercept, ξi is the relaxation factor.

通用的,K(xi,xj)≡φ(xi)Tφ(xi)为支持向量机中的核函数。Generally, K(x i , x j )≡φ(x i ) T φ(x i ) is the kernel function in the support vector machine.

在训练过程中,将特征向量和类别标号组合在一起,作为训练的输入参数,即(xi,yi),其中yi是类别标号,在本分类方法中,yi=1,即类别都是正类。在训练中选择RBF核函数其中,||xi-xj||表示空间中任意两点xi和xj之间的欧氏距离,并通过10折交叉验证获得分类参数。10折交叉验证方法是随机地将这1000个训练样本划分为10个相等的子集,轮流地选择其中9个子集作为训练,另外1个子集作为测试,这样,每个子集都会被用来作为测试数据,根据正确分类样本的比例计算交叉验证的精度。变换不同的参数组合,即惩罚系数C和核函数中的核参数γ值,选择获得最佳交叉验证精度的组合作为单类支持向量机分类模型参数,同时w、b也随之确定。利用确定的分类模型,对整个遥感影像进行单类分类,得到水体类别提取结果。In the training process, the feature vector and the category label are combined together as the training input parameters, that is, ( xi , y i ), where y i is the category label, and in this classification method, y i =1, that is, the category All are positive. Choose RBF kernel function in training Among them, || xi -x j || represents the Euclidean distance between any two points x i and x j in the space, and the classification parameters are obtained through 10-fold cross-validation. The 10-fold cross-validation method is to randomly divide the 1000 training samples into 10 equal subsets, and select 9 of them as training and 1 subset as testing in turn, so that each subset will be used as On the test data, the cross-validation accuracy is calculated based on the proportion of correctly classified samples. Change different parameter combinations, that is, the penalty coefficient C and the kernel parameter γ value in the kernel function, and select the combination that obtains the best cross-validation accuracy as the single-class support vector machine classification model parameters, and at the same time, w and b are determined accordingly. Using the determined classification model, single-class classification is carried out on the entire remote sensing image, and the water body class extraction result is obtained.

单类支持向量机只需要河流目标类别的样本进行学习,就能得到所需要的河流目标类别分类结果,减少了训练阶段的任务。而采用多类分类方法提取单一目标类别,需要将图像划分成多个地物类别,大大增加的工作量。The single-class support vector machine only needs the samples of the river target category to learn, and can obtain the required classification results of the river target category, which reduces the tasks in the training stage. However, using multi-class classification methods to extract a single target category requires dividing the image into multiple object categories, which greatly increases the workload.

在本实施例中,如图3、图4分别是采用最近邻分类和贝叶斯分类方法得到的河流目标提取结果。利用贝叶斯分类方法,需要将实验图像划分为不透水表面、林地、草地和水体四个类别,并分别为每个类别选取训练样本,增加了学习阶段的工作量和不确定性,使总体分类难度增加。与图2中采用一类训练样本的单类支持向量机方法相比,分类结果非常相近,而单类支持向量机方法的训练更加容易。In this embodiment, Fig. 3 and Fig. 4 respectively show the river target extraction results obtained by using the nearest neighbor classification and Bayesian classification methods. Using the Bayesian classification method, it is necessary to divide the experimental images into four categories: impermeable surface, woodland, grassland and water body, and select training samples for each category, which increases the workload and uncertainty of the learning stage, making the overall Classification difficulty increases. Compared with the one-class SVM method using one class of training samples in Figure 2, the classification results are very similar, and the training of the one-class SVM method is easier.

D.精细检测过程:对河流候选区域进行图像分割,生成形状特征:在C环节粗筛选环节所得结果的基础上,采用图像阈值分割方法,将目标候选区域提取出来,同时生成形状特征。由于河流候选区域图像中只有白色和黑色像素,设置阈值参数Th=10,将大于阈值且相邻的像素进行合并,生成不同大小的目标类别连通区域,再由每个连通区域内的像素计算得到形状特征,计算方法如公式(3)。D. Fine detection process: Segment the image of the candidate area of the river to generate shape features: Based on the results obtained in the rough screening of the C link, use the image threshold segmentation method to extract the target candidate area and generate shape features at the same time. Since there are only white and black pixels in the river candidate area image, set the threshold parameter Th=10, merge the adjacent pixels that are greater than the threshold, and generate target category connected areas of different sizes, and then calculate from the pixels in each connected area Shape features, the calculation method is as formula (3).

根据实际河流目标检查要求,去除小区域候选目标,以面积阈值AT=50进行小区域去除,即将面积特征A<50的候选目标去除,合并到背景区域,结果如图5所示。According to the actual river target inspection requirements, small area candidate targets are removed, and small area removal is carried out with the area threshold AT=50, that is, candidate targets with area feature A<50 are removed and merged into the background area. The result is shown in Figure 5.

根据实际应用要求,河流目标应具有一定的面积,相关形状特征描述如下。According to the actual application requirements, the river target should have a certain area, and the relevant shape characteristics are described as follows.

边界长e:边界象素的个数,一个象素的边界长为1。Border length e: the number of border pixels, the border length of a pixel is 1.

面积A:组成该对象的象素总数,其中一个象素边缘的长设为1。Area A: The total number of pixels that make up the object, and the length of a pixel edge is set to 1.

形状特征指数: Shape feature index:

边界长除以4倍的面积的平方根,S是描述对象边界与面积的关系,边界越长,值越大。The square root of the boundary length divided by 4 times the area, S describes the relationship between the object boundary and the area, the longer the boundary, the larger the value.

E.根据形状特征指数确定河流目标,实现目标检测:形状信息是遥感影像目视判别中的一个非常重要的因素,对于一幅遥感图像,通过分割提取形状信息,得到一个带有多个属性的图像对象集合,在这个集合中将每个图像对象的形状特征与河流目标的属性进行匹配,筛选出河流目标。河流目标形状特征主要是具有较大的形状特征指数,选择数值2.5作为阈值进行判断。E. Determine the river target according to the shape feature index to realize target detection: shape information is a very important factor in the visual discrimination of remote sensing images. For a remote sensing image, the shape information is extracted by segmentation to obtain a multi-attribute A collection of image objects. In this collection, the shape features of each image object are matched with the attributes of river targets to filter out river targets. The shape feature of the river target mainly has a large shape feature index, and the value 2.5 is selected as the threshold for judgment.

在D环节去除小区域目标的基础上,依据分割生成的候选目标形状特征指数,将形状特征指数阈值设置为ST=2.5,进行河流目标特征匹配。当候选目标区域的形状特征指数值S>2.5时,作为目标匹配结果保留,如果形状特征指数值S≤2.5,则作为背景去除,检测结果如图6所示。On the basis of removing the small area target in the D step, according to the shape feature index of the candidate target generated by the segmentation, the threshold of the shape feature index is set to ST=2.5, and the river target feature matching is carried out. When the shape feature index value S>2.5 of the candidate target area is retained as the target matching result, if the shape feature index value S≤2.5 is removed as the background, the detection result is shown in Figure 6.

在小区域目标去除和特征匹配过程中,所设定的行政特征阈值应该根据实际需要调整,不同的应用要求有不同的参数。In the process of small area target removal and feature matching, the set administrative feature threshold should be adjusted according to actual needs, and different applications require different parameters.

本发明采用单类支持向量机对河流目标进行检测,流程简单,计算量大大的减小,加快了工作效率,值得推广使用。The invention adopts a single-class support vector machine to detect the river target, has simple flow, greatly reduces calculation amount, accelerates work efficiency, and is worthy of popularization and use.

Claims (6)

1.一种利用单类支持向量机检测河流目标的方法,其特征是:包含以下步骤:1. A method utilizing a single-class support vector machine to detect river targets is characterized in that: comprising the following steps: A.选择波段:在遥感图像中选取波段组合进行地物区分和河流提取,以便对水体、植被以及其他地面物体进行识别;A. Select the band: Select the band combination in the remote sensing image to distinguish the feature and extract the river, so as to identify the water body, vegetation and other ground objects; B.特征分析与选择:选择A环节处理过的图像,进行光谱特征分析:光谱分析采用的光谱特征是:河流等水体目标在遥感图像中,以灰度值区分河流目标;B. Feature analysis and selection: Select the image processed in step A, and perform spectral feature analysis: the spectral feature used in spectral analysis is: rivers and other water targets in remote sensing images, distinguish river targets by gray value; C.粗筛选过程:基于光谱特征,提取河流候选区域:选择若干目标样本,提取每个像素的光谱值作为分类特征,利用公式xi=(ri,gi,bi)生成特征向量,利用生成的特征向量对单类支持向量机进行最优化问题求解,在训练时采用RBF核函数进行训练,并通过10折交叉验证确定分类模型,对整个遥感影像进行单类分类,得到水体类别提取结果;C. Rough screening process: based on spectral features, extract river candidate areas: select several target samples, extract the spectral value of each pixel as a classification feature, and use the formula x i = (r i , g i , b i ) to generate a feature vector, Use the generated feature vector to solve the optimization problem of the single-class support vector machine, and use the RBF kernel function during training Carry out training, and determine the classification model through 10-fold cross-validation, perform single-class classification on the entire remote sensing image, and obtain the water body category extraction result; 其中,ri为红色分量,gi为绿色分量,bi为蓝色分量;Among them, r i is the red component, g i is the green component, b i is the blue component; 其中,||xi-xj||表示空间中任意两点xi和xj之间的欧氏距离;γ为核参数;Among them, || xi -x j || represents the Euclidean distance between any two points x i and x j in the space; γ is the kernel parameter; D.精细检测过程:针对C环节中的结果,对河流候选区域进行图像分割,生成形状特征指数:在C环节粗筛选环节所得结果的基础上,采用图像阈值分割技术,设置阈值参数,将大于阈值且相邻的像素进行合并,生成不同大小的目标类别连通区域,再由每个连通区域内的像素计算得到形状特征指数并设定面积阈值进行小区域去除,最后将去除小面域的图像合并到背景区域;D. Fine detection process: According to the results in the C link, image segmentation is performed on the candidate area of the river, and the shape feature index is generated: On the basis of the results obtained in the rough screening of the C link, the image threshold segmentation technology is used to set the threshold parameter, which will be greater than Threshold and adjacent pixels are merged to generate connected regions of target categories of different sizes, and then the shape feature index is calculated from the pixels in each connected region And set the area threshold to remove the small area, and finally merge the image with the removed small area into the background area; 其中,边界长e:边界象素的个数,一个象素的边界长为1;Among them, the border length e: the number of border pixels, the border length of a pixel is 1; 面积A:组成该对象的象素总数,其中一个象素边缘的长设为1;Area A: the total number of pixels that make up the object, and the length of one pixel edge is set to 1; E.目标检测:设定形状指数阈值,并根据D环节得出的形状特征指数确定河流目标,实现目标检测。E. Target detection: set the shape index threshold, and determine the river target according to the shape feature index obtained in the D link, and realize the target detection. 2.根据权利要求1所述的利用单类支持向量机检测河流目标的方法,其特征是:所述的波段选择环节,选择遥感图像的4、3、2波段,分别赋予红、绿、蓝色进行地物区分。2. the method for utilizing a single-class support vector machine to detect river targets according to claim 1 is characterized in that: the band selection link selects the 4, 3, and 2 bands of the remote sensing image, and assigns red, green, and blue respectively color to distinguish features. 3.根据权利要求1所述的利用单类支持向量机检测河流目标的方法,其特征是:所述的特征分析与选择环节灰度值为10~20。3. The method for detecting river targets by using a single-class support vector machine according to claim 1, characterized in that: the gray value of the feature analysis and selection link is 10-20. 4.根据权利要求1所述的利用单类支持向量机检测河流目标的方法,其特征是:所述的精细检测过程中图像分割时的阈值参数为:Th=10;面积阈值为:AT=50。4. the method for utilizing single class support vector machine to detect river target according to claim 1, is characterized in that: the threshold parameter when image segmentation is in the described fine detection process is: Th=10; Area threshold is: AT= 50. 5.根据权利要求1所述的利用单类支持向量机检测河流目标的方法,其特征是:所述的目标检测环节中的形状指数阈值为ST=2.5。5. The method for detecting river targets by using a single-class support vector machine according to claim 1, characterized in that: the shape index threshold in the target detection link is ST=2.5. 6.根据权利要求1所述的利用单类支持向量机检测河流目标的方法,其特征是:所述的C环节中最优化问题求解的过程为:给定l个训练样本,则有: 6. the method utilizing single class support vector machine to detect river target according to claim 1 is characterized in that: the process of optimization problem solution in the described C link is: given 1 training samples, then have: 且满足(wTφ(xi)+b)≥1-ξi,ξi≥0And satisfy (w T φ(x i )+b)≥1-ξ i , ξ i ≥0 其中,C>0是惩罚系数,φ(xi)是将向量xi映射到高维空间的函数;w是特征空间中分类面的法向量,wT是w的转置,b是w的截距,ξi是松弛因子。Among them, C>0 is the penalty coefficient, φ( xi ) is the function that maps the vector xi to the high-dimensional space; w is the normal vector of the classification surface in the feature space, w T is the transpose of w, b is the intercept of w distance, and ξi is the relaxation factor.
CN201610944422.3A 2016-11-02 2016-11-02 One kind is using one-class support vector machines detection river mesh calibration method Pending CN106485239A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610944422.3A CN106485239A (en) 2016-11-02 2016-11-02 One kind is using one-class support vector machines detection river mesh calibration method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610944422.3A CN106485239A (en) 2016-11-02 2016-11-02 One kind is using one-class support vector machines detection river mesh calibration method

Publications (1)

Publication Number Publication Date
CN106485239A true CN106485239A (en) 2017-03-08

Family

ID=58271342

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610944422.3A Pending CN106485239A (en) 2016-11-02 2016-11-02 One kind is using one-class support vector machines detection river mesh calibration method

Country Status (1)

Country Link
CN (1) CN106485239A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108334909A (en) * 2018-03-09 2018-07-27 南京天数信息科技有限公司 Cervical carcinoma TCT digital slices data analysing methods based on ResNet
CN108710862A (en) * 2018-05-24 2018-10-26 河海大学 A kind of high-resolution remote sensing image Clean water withdraw method
CN108920998A (en) * 2018-04-14 2018-11-30 海南大学 Single category based on Pasteur's coefficient pours down remote sensing image target area extracting method
CN109472294A (en) * 2018-10-15 2019-03-15 广州地理研究所 A method, device, storage medium and equipment for identifying urban water bodies
CN109740485A (en) * 2018-12-27 2019-05-10 中国水利水电科学研究院 Reservoir or pond identification method based on spectral analysis and deep convolutional neural network
CN111695492A (en) * 2020-06-10 2020-09-22 国网山东省电力公司电力科学研究院 Method and system for detecting fishing hidden danger of power transmission line
CN114462542A (en) * 2022-02-14 2022-05-10 长光禹辰信息技术与装备(青岛)有限公司 An Optimization Method of Small Target Recognition Accuracy Based on Local Difference Analysis

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542259A (en) * 2011-12-29 2012-07-04 宁波工程学院 Identification method for near-shore on-land water body
CN102708354A (en) * 2011-12-31 2012-10-03 中国科学院遥感应用研究所 Method for identifying golf course
CN103646246A (en) * 2013-12-19 2014-03-19 交通运输部天津水运工程科学研究所 Decision tree model based multispectral remote sensing image river information extraction method
CN105335761A (en) * 2015-11-27 2016-02-17 郑州航空工业管理学院 Remote-sensing image single-category information extraction method based on nearest neighbor method
CN105550695A (en) * 2015-11-27 2016-05-04 郑州航空工业管理学院 Object-oriented single-class classification method for remote sensing image

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542259A (en) * 2011-12-29 2012-07-04 宁波工程学院 Identification method for near-shore on-land water body
CN102708354A (en) * 2011-12-31 2012-10-03 中国科学院遥感应用研究所 Method for identifying golf course
CN103646246A (en) * 2013-12-19 2014-03-19 交通运输部天津水运工程科学研究所 Decision tree model based multispectral remote sensing image river information extraction method
CN105335761A (en) * 2015-11-27 2016-02-17 郑州航空工业管理学院 Remote-sensing image single-category information extraction method based on nearest neighbor method
CN105550695A (en) * 2015-11-27 2016-05-04 郑州航空工业管理学院 Object-oriented single-class classification method for remote sensing image

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
WENKAI LI 等: "A Positive and Unlabeled Learning Algorithm for One-Class Classification of Remote-Sensing Data", 《IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING》 *
于晓升 等: "基于多特征融合的遥感图像河流目标检测算法", 《东北大学学报(自然科学版)》 *
张绍明 等: "基于高分辨率遥感影像的内河航标自动检测方法", 《同济大学学报(自然科学版)》 *
王凯峰 等: "基于单类SVM的遥感图像目标检测", 《计算机工程与应用》 *
薄树奎 等: "面向对象的遥感影像单类分类", 《现代电子技术》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108334909A (en) * 2018-03-09 2018-07-27 南京天数信息科技有限公司 Cervical carcinoma TCT digital slices data analysing methods based on ResNet
CN108334909B (en) * 2018-03-09 2020-06-16 上海天数智芯半导体有限公司 Cervical cancer TCT digital slice data analysis system based on ResNet
CN108920998A (en) * 2018-04-14 2018-11-30 海南大学 Single category based on Pasteur's coefficient pours down remote sensing image target area extracting method
CN108710862A (en) * 2018-05-24 2018-10-26 河海大学 A kind of high-resolution remote sensing image Clean water withdraw method
CN109472294A (en) * 2018-10-15 2019-03-15 广州地理研究所 A method, device, storage medium and equipment for identifying urban water bodies
CN109740485A (en) * 2018-12-27 2019-05-10 中国水利水电科学研究院 Reservoir or pond identification method based on spectral analysis and deep convolutional neural network
CN111695492A (en) * 2020-06-10 2020-09-22 国网山东省电力公司电力科学研究院 Method and system for detecting fishing hidden danger of power transmission line
CN114462542A (en) * 2022-02-14 2022-05-10 长光禹辰信息技术与装备(青岛)有限公司 An Optimization Method of Small Target Recognition Accuracy Based on Local Difference Analysis

Similar Documents

Publication Publication Date Title
Gao et al. Automatic change detection in synthetic aperture radar images based on PCANet
Li et al. Automatic pavement crack detection by multi-scale image fusion
Cheng et al. FusionNet: Edge aware deep convolutional networks for semantic segmentation of remote sensing harbor images
CN110443128B (en) Finger vein identification method based on SURF feature point accurate matching
CN106485239A (en) One kind is using one-class support vector machines detection river mesh calibration method
Sirmacek et al. Urban-area and building detection using SIFT keypoints and graph theory
Alsmadi et al. Fish recognition based on robust features extraction from size and shape measurements using neural network
CN104182985B (en) Remote sensing image change detection method
WO2018081929A1 (en) Hyperspectral remote sensing image feature extraction and classification method and system thereof
CN108921201B (en) Dam defect identification and classification method based on feature combination and CNN
Zhan et al. Unsupervised scale-driven change detection with deep spatial–spectral features for VHR images
Wang et al. Fan shape model for object detection
Alsmadi et al. Fish recognition based on robust features extraction from color texture measurements using back-propagation classifier
CN104794502A (en) Image processing and mode recognition technology-based rice blast spore microscopic image recognition method
CN108122008A (en) SAR image recognition methods based on rarefaction representation and multiple features decision level fusion
CN102760228B (en) Specimen-based automatic lepidoptera insect species identification method
CN104182763A (en) Plant type identification system based on flower characteristics
Deng et al. Cloud detection in satellite images based on natural scene statistics and gabor features
CN111898627B (en) A PCA-based SVM Cloud Particle Optimal Classification and Recognition Method
Alsmadi et al. Fish classification based on robust features extraction from color signature using back-propagation classifier
Chu et al. Strip steel surface defect recognition based on novel feature extraction and enhanced least squares twin support vector machine
Abdellah et al. Defect detection and identification in textile fabric by SVM method
CN106600613A (en) Embedded GPU-based improved LBP infrared target detection method
WO2020119624A1 (en) Class-sensitive edge detection method based on deep learning
Suwais et al. A review on classification methods for plants leaves recognition

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: 450000 Middle Road, 27 District University, Zhengzhou, Henan Province, No. 2

Applicant after: Zhengzhou Institute of Aeronautical Industry Management

Address before: 450046 15 Wen Yuan Xi Road, Zheng Dong New District, Zhengzhou, Henan.

Applicant before: Zhengzhou Institute of Aeronautical Industry Management

CB02 Change of applicant information
RJ01 Rejection of invention patent application after publication

Application publication date: 20170308

RJ01 Rejection of invention patent application after publication