技术领域technical field
本发明涉及一种遥感影像主方向确定方法及装置，属于遥感影像处理应用领域。The invention relates to a method and a device for determining the main direction of a remote sensing image, belonging to the application field of remote sensing image processing.
背景技术Background technique
目前，国内外针对遥感影像地物特征的描述主要集中在光谱、纹理和几何形状信息等3个方面。伴随遥感影像分辨率的提高，地物的形状多样性和光谱复杂性趋于明显，“同谱异物”、“异物同谱”现象更加显著，较高的类内变化和较低的类间差异极大地减弱了不同地物要素在光谱域的模式可分性，单纯依靠光谱信息已不能较好地实现地物的识别提取；几何特征主要利用形状和大小等信息，算法相对简单，常作为辅助特征用于地物识别提取后处理；而纹理特征作为基本视觉特征之一，能够兼顾宏观特征和微观细节，具有较强的稳定性，在遥感影像的处理分析中呈现越来越明显的优势。At present, the description of the features of remote sensing images at home and abroad mainly focuses on three aspects: spectrum, texture and geometric shape information. With the improvement of the resolution of remote sensing images, the shape diversity and spectral complexity of ground objects tend to be more obvious, and the phenomenon of "same-spectrum foreign objects" and "different objects with the same spectrum" are more significant, with higher intra-class variation and lower inter-class variation. The mode separability of different ground features in the spectral domain is greatly weakened, and the identification and extraction of ground features cannot be achieved simply by relying on spectral information; geometric features mainly use information such as shape and size, and the algorithm is relatively simple, often used as an auxiliary Features are used for post-processing of ground object recognition and extraction; and texture features, as one of the basic visual features, can take into account both macroscopic features and microscopic details, and have strong stability, showing more and more obvious advantages in the processing and analysis of remote sensing images.
在《基于纹理特征的遥感影像居民地提取技术研究》(金飞，解放军信息工程大学博士学位论文)一文中，公开了一种基于纹理特征的遥感影像居民地提取方法，文中采用基于种子点的区域生长方法来进行居民地的提取，采用8邻域的搜索方式，量测种子点和候选点之间的纹理特征的相似性距离，通过一定准则判定候选点是否与种子点归为一类，重复以上过程直至符合条件的像素点搜索完毕。其中，作者具体使用了多种不同方法(包括傅里叶变换、小波变换和Gabor变换等)来完成相应的纹理特征提取，以说明各个方法之间的优劣性。其使用的提取纹理特征的算法均需要计算出遥感影像的主方向。In the paper "Research on Residential Area Extraction from Remote Sensing Imagery Based on Texture Features" (Jin Fei, Ph.D. dissertation at PLA University of Information Engineering), a method for extracting residential areas from remote sensing images based on texture features is disclosed. The region growing method is used to extract residential areas, and the 8-neighbor search method is used to measure the similarity distance of the texture features between the seed point and the candidate point. Repeat the above process until the pixel points that meet the conditions are searched. Among them, the author uses a variety of different methods (including Fourier transform, wavelet transform and Gabor transform, etc.) to complete the corresponding texture feature extraction to illustrate the advantages and disadvantages of each method. The algorithms used to extract texture features all need to calculate the main direction of remote sensing images.
但上述方案针对每一块居民地均需要计算具体的、精确到度的纹理方向，而其弊端在于：人工干预环节太多，需要人工选定一个种子点，计算量大，不够实用。本领域中，一个地级市所管辖的行政村(居民地)一般在数百个之多，在一些人口密集区域，最多能够达到上千个，而现有技术所公开的居民地提取方法要求在整幅遥感影像中人工框定出每一个行政村，那么就需要由专人进行成百上千次的相应操作来完成，同时需要针对每一个行政村专门进行主方向的计算，计算量太大，实用性不高；而实际应用中，每一块居民地的大小是随机不确定的，因此其外轮廓也是不确定的，以种子点为基础，需要框定多大的影像范围来计算主方向无法确定，框定的范围小了，那么居民地(比如行政村)就框不完，框定范围大了的话，又把其他的村子或者地物框了进来，计算的主方向不准确。However, the above scheme needs to calculate a specific and accurate texture direction for each residential land, and its drawback is that there are too many manual intervention links, and a seed point needs to be manually selected, which requires a large amount of calculation and is not practical. In this field, there are generally hundreds of administrative villages (residential areas) under the jurisdiction of a prefecture-level city, and in some densely populated areas, the number of administrative villages (residential areas) can reach thousands at most, and the method for extracting residential areas disclosed in the prior art requires If each administrative village is manually framed in the entire remote sensing image, then it needs to be completed by a dedicated person for hundreds of thousands of corresponding operations. The practicability is not high; in practical applications, the size of each residential area is randomly uncertain, so its outer contour is also uncertain. Based on the seed point, how much image range needs to be framed to calculate the main direction cannot be determined. If the framed scope is too small, the residential areas (such as administrative villages) cannot be framed completely. If the framed scope is too large, other villages or features will be framed, and the main direction of the calculation will be inaccurate.
发明内容SUMMARY OF THE INVENTION
本发明的目的是提供一种遥感影像主方向确定方法及装置以解决目前遥感影像主方向确定方法过于依赖人工导致计算量太大的问题。The purpose of the present invention is to provide a method and device for determining the main direction of a remote sensing image to solve the problem that the current method for determining the main direction of a remote sensing image relies too much on manual work, resulting in a large amount of calculation.
为实现上述目的，本发明提供方案一：一种遥感影像主方向确定方法，该遥感影像主方向确定方法包括以下步骤：In order to achieve the above purpose, the present invention provides scheme 1: a method for determining the main direction of a remote sensing image, and the method for determining the main direction of a remote sensing image includes the following steps:
A、将遥感影像I分为N块区域(N为不小于1的整数)，分别记为I1，…，IN；A. Divide the remote sensing image I into N blocks of regions (N is an integer not less than 1), denoted as I1 , ..., IN respectively;
B、对遥感影像I不同遥感影像区域求主方向，根据主方向一致性对各遥感影像区域分类，将相互之间一致性偏差小于第一设定阈值的各遥感影像区域归为一个遥感影像区块；B. Find the main direction for different remote sensing image areas of remote sensing image I, classify each remote sensing image area according to the consistency of the main direction, and classify each remote sensing image area whose consistency deviation is less than the first set threshold as one remote sensing image area piece;
C、对每一个遥感影像区块求取其对应的主方向，每一个遥感影像区块的主方向的集合即为所述遥感影像I的主方向。C. Obtain its corresponding main direction for each remote sensing image block, and the set of the main directions of each remote sensing image block is the main direction of the remote sensing image I.
本方案给出了一种通过分类思想计算遥感影像主方向的方法，该方法通过将一致性强的区域归类为区块，用区块的主方向构成遥感影像的主方向，减少了人工干预，同时大大降低计算遥感影像主方向的计算量，提高遥感影像主方向确定的效率和实用性。This scheme provides a method for calculating the main direction of remote sensing images through the idea of classification. This method reduces manual intervention by classifying regions with strong consistency as blocks, and using the main directions of blocks to form the main direction of remote sensing images. At the same time, the calculation amount of calculating the main direction of remote sensing images is greatly reduced, and the efficiency and practicability of determining the main direction of remote sensing images are improved.
方案二：在方案一的基础上，步骤B中一致性判断进行分类的方法具体包括以下步骤：Option 2: On the basis of Option 1, the method for classifying by consistency judgment in step B specifically includes the following steps:
α)计算各遥感影像区域I1，…，IN对应的傅里叶变换幅度谱的角向分布，确定角向分布曲线中峰值的位置，将该位置对应的角度作为该遥感影像区域的主方向，得到每块遥感影像区域I1，…，IN所对应的主方向θ1，…，θN；α) Calculate the angular distribution of the Fourier transform amplitude spectrum corresponding toeach remote sensing image area I1 , . direction to obtain the main directions θ1 , ..., θN corresponding to each remote sensing image area I1 , ..., IN ;
β)按照各块遥感影像区域对应的主方向之间的一致性偏差小于第一设定阈值的判据对所有遥感影像区域分类，满足上述判据条件的遥感影像区域归入为一个遥感影像区块。β) Classify all remote sensing image areas according to the criterion that the consistency deviation between the main directions corresponding to each remote sensing image area is less than the first set threshold, and the remote sensing image areas that meet the above criteria are classified as one remote sensing image area piece.
方案三：在方案二的基础上，步骤C遥感影像区块求取其对应的主方向的方法具体包括以下步骤：Scheme 3: On the basis of Scheme 2, the method for obtaining the corresponding main direction of the remote sensing image block in step C specifically includes the following steps:
1)对组成该遥感影像区块的遥感影像区域所对应的主方向求取平均值；1) average the main directions corresponding to the remote sensing image regions forming the remote sensing image block;
2)将该平均值作为该遥感影像区块的主方向。2) The average value is taken as the main direction of the remote sensing image block.
方案四：在方案一或二或三的基础上，若某一个遥感影像区块只包括一块遥感影像区域Im，则该遥感影像区块的主方向的计算方法包括以下步骤：Scheme 4: On the basis of Scheme 1 or 2 or 3, if a certain remote sensing image block includes only one remote sensing image areaIm , the method for calculating the main direction of the remote sensing image block includes the following steps:
i)将遥感影像区域Im随机分为N′块子区域(N′为不小于1的整数)，分别记为i) The remote sensing image areaIm is randomly divided into N' sub-areas (N' is an integer not less than 1), which are respectively recorded as
ii)对遥感影像区域Im不同遥感影像子区域求主方向，根据主方向的一致性对各遥感影像子区域分类，将相互之间一致性偏差小于第二设定阈值的各遥感影像区域归为一个遥感影像子区块；ii) Find the main direction for different remote sensing image sub-regions in the remote sensing image areaIm , classify each remote sensing image sub-region according to the consistency of the main direction, and classify each remote sensing image area whose mutual consistency deviation is less than the second set threshold. is a remote sensing image sub-block;
iii)对每一个遥感影像子区块求取其对应的主方向，每一个遥感影像子区块的主方向的集合即为所述遥感影像区域Im对应遥感影像区块的主方向。iii) to each remote sensing image subblock to obtain its corresponding main direction, the set of the main direction of each remote sensing image subblock is the main direction of the corresponding remote sensing image block of described remote sensing image area 1m .
本方案针对差异性较大的遥感影像区域进行再次分类计算的处理，对该遥感影像区域进行细分，以提高最终遥感影像主方向的确定精度。This scheme re-classifies and calculates the remote sensing image area with large differences, and subdivides the remote sensing image area to improve the accuracy of determining the main direction of the final remote sensing image.
方案五：在方案四的基础上，步骤ii)中一致性判断进行分类的方法具体包括以下步骤：Option 5: On the basis of Option 4, the method for classifying by consistency judgment in step ii) specifically includes the following steps:
a)计算各遥感影像子区域对应的傅里叶变换幅度谱的角向分布，确定角向分布曲线中峰值的位置，将该位置对应的角度作为该遥感影像子区域的主方向，得到每块遥感影像子区域所对应的主方向a) Calculate each remote sensing image sub-region The angular distribution of the corresponding Fourier transform amplitude spectrum, determine the position of the peak in the angular distribution curve, and use the angle corresponding to the position as the main direction of the remote sensing image sub-region, and obtain each remote sensing image sub-region the corresponding main direction
b)按照各块遥感影像子区域对应的主方向之间的一致性偏差小于第二设定阈值的判据对所有遥感影像子区域分类，满足上述判据条件的遥感影像子区域归入为一个遥感影像子区块。b) Classify all remote sensing image sub-regions according to the criterion that the consistency deviation between the main directions corresponding to each remote sensing image sub-region is less than the second set threshold, and the remote sensing image sub-regions that meet the above criteria are classified as one Remote sensing image sub-block.
方案六：在方案五的基础上，步骤iii)遥感影像子区块求取其对应的主方向的方法具体包括以下步骤：Option 6: On the basis of Option 5, step iii) the method for obtaining the corresponding main direction of the remote sensing image sub-block specifically includes the following steps:
(1)对组成该遥感影像子区块的遥感影像子区域所对应的主方向求取平均值；(1) Obtain the average value of the main directions corresponding to the remote sensing image sub-regions constituting the remote sensing image sub-block;
(2)将该平均值作为该遥感影像子区块的主方向。(2) The average value is taken as the main direction of the remote sensing image sub-block.
此外，本发明还提供了方案七：一种遥感影像主方向确定装置，包括存储器、处理器以及存储在存储器中并可在处理器上运行的计算机程序，所述处理器执行所述程序时可以实现方案一至方案六任一遥感影像主方向确定方法。In addition, the present invention also provides scheme 7: a device for determining the main direction of remote sensing images, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, when the processor executes the program, it can A method for determining the main direction of any remote sensing image from Scheme 1 to Scheme 6 is implemented.
本方案给出了一种通过分类思想计算遥感影像主方向的装置，该装置通过运行相关程序，将一致性强的区域归类为区块，用区块的主方向构成遥感影像的主方向，减少了人工干预，同时大大降低计算遥感影像主方向的计算量，提高遥感影像主方向确定的效率和实用性。This scheme provides a device for calculating the main direction of remote sensing images through the idea of classification. The device classifies regions with strong consistency into blocks by running related programs, and uses the main directions of the blocks to form the main directions of remote sensing images. The manual intervention is reduced, the calculation amount for calculating the main direction of the remote sensing image is greatly reduced, and the efficiency and practicability of determining the main direction of the remote sensing image are improved.
附图说明Description of drawings
图1为本发明的一种遥感影像主方向确定方法的流程图。FIG. 1 is a flowchart of a method for determining the main direction of a remote sensing image according to the present invention.
具体实施方式Detailed ways
如图1所示为本发明的一种遥感影像主方向确定方法的流程图，其中M为小于等于N的整数。下面结合附图对本发明的具体实施方式做进一步的说明。FIG. 1 is a flowchart of a method for determining the main direction of a remote sensing image according to the present invention, wherein M is an integer less than or equal to N. The specific embodiments of the present invention will be further described below with reference to the accompanying drawings.
实施例1Example 1
按照以下步骤进行遥感影像主方向的确定：Follow the steps below to determine the main direction of remote sensing images:
1、将遥感影像I随机分为10块区域，分别记为I1，…，I10；1. The remote sensing image I is randomly divided into 10 areas, which are respectively recorded as I1 , ..., I10 ;
2、计算各遥感影像区域I1，…，I10对应的傅里叶变换幅度谱的角向分布，确定角向分布曲线中峰值的具体位置，将该具体位置对应的角度作为该遥感影像区域的主方向，得到每块遥感影像区域I1，…，I10所对应的主方向θ1，…，θ10；2. Calculate the angular distribution of the Fourier transform amplitudespectrum corresponding to each remote sensing image area I1 , . The main direction of each remote sensing image area I1 , ..., I10 corresponding to the main direction θ1 , ..., θ10 ;
3、按照各块遥感影像区域对应的主方向之间的一致性偏差小于第二设定阈值的判据对所有遥感影像区域分类，满足上述判据条件的遥感影像区域划分为一个遥感影像区块，换言之，当几个遥感影像区域对应的主方向的方差小于某设定值时(例如10°)，则说明这几个遥感影像区域的一致性较好，可以使用相同的滤波器进行相似度比较，因此把类似这样的区域从十个遥感影像区域中一一找到，并分好类别；3. Classify all remote sensing image areas according to the criterion that the consistency deviation between the main directions corresponding to each remote sensing image area is less than the second set threshold, and the remote sensing image areas that meet the above criteria are divided into a remote sensing image block , in other words, when the variance of the main directions corresponding to several remote sensing image areas is less than a certain set value (for example, 10°), it means that these remote sensing image areas have good consistency, and the same filter can be used to measure the similarity Therefore, similar areas are found one by one from ten remote sensing image areas, and they are classified into good categories;
4、对组成某一遥感影像区块的遥感影像区域所对应的主方向求取平均值，将该平均值作为该遥感影像区块的主方向；4. Calculate the average value of the main directions corresponding to the remote sensing image areas that form a certain remote sensing image block, and use the average value as the main direction of the remote sensing image block;
5、将各遥感影像区块对应的主方向的集合作为遥感影像I的主方向。5. The set of main directions corresponding to each remote sensing image block is used as the main direction of the remote sensing image I.
若某一个遥感影像区块只包括一块遥感影像区域Im，则需要对该遥感影像区块进行细分处理，重新计算该遥感影像区块的主方向，具体步骤如下：If a certain remote sensing image block only includes a remote sensing image areaIm , then the remote sensing image block needs to be subdivided, and the main direction of the remote sensing image block is recalculated, and the specific steps are as follows:
i)将遥感影像区域Im随机分为4块子区域，分别记为i) The remote sensing image areaIm is randomly divided into 4 sub-areas, which are respectively recorded as
ii)计算各遥感影像子区域对应的傅里叶变换幅度谱的角向分布，确定角向分布曲线中峰值的具体位置，将该具体位置对应的角度作为该遥感影像子区域的主方向，得到每块遥感影像子区域所对应的主方向ii) Calculate each remote sensing image sub-region The angular distribution of the corresponding Fourier transform amplitude spectrum, determine the specific position of the peak in the angular distribution curve, and use the angle corresponding to the specific position as the main direction of the remote sensing image sub-region, and obtain each remote sensing image sub-region the corresponding main direction
iii)按照各块遥感影像子区域对应的主方向之间的一致性偏差小于第二设定阈值的判据对所有遥感影像子区域分类，满足上述判据条件的遥感影像子区域划分为一个遥感影像子区块，换言之，当几个遥感影像子区域对应的主方向的方差小于某设定值时(例如10°)，则说明这几个遥感影像子区域的一致性较好，可以使用相同的滤波器进行相似度比较，因此把类似这样的子区域从4个遥感影像区域中一一找到，并分好类别；iii) Classify all remote sensing image sub-regions according to the criterion that the consistency deviation between the main directions corresponding to each remote sensing image sub-region is less than the second set threshold, and the remote sensing image sub-regions satisfying the above criteria are divided into a remote sensing image sub-region. Image sub-blocks, in other words, when the variance of the main directions corresponding to several remote sensing image sub-areas is less than a certain set value (for example, 10°), it means that these remote sensing image sub-areas have good consistency and can use the same The similarity of the filter is compared, so the sub-regions like this are found one by one from the four remote sensing image regions, and they are classified into good categories;
iv)对组成某一遥感影像子区块的遥感影像区域所对应的主方向求取平均值，将该平均值作为该遥感影像子区块的主方向；iv) obtaining the average value of the main directions corresponding to the remote sensing image regions forming a certain remote sensing image sub-block, and using the average value as the main direction of the remote sensing image sub-block;
v)将各遥感影像子区块对应的主方向的集合作为所述遥感影像区域Im对应的遥感影像区块的主方向。v) The set of main directions corresponding to each remote sensing image sub-block is taken as the main direction of the remote sensing image block corresponding to the remote sensing image areaIm .
至此，就求出来遥感影像所对应的主方向了，而至于具体如何使用该主方向，可以参考背景技术所提及的《基于纹理特征的遥感影像居民地提取技术研究》(金飞，解放军信息工程大学博士学位论文)一文第3.1章节“基于傅里叶变换的居民地提取”和第3.2章节“基于Gabor变换的居民地提取”具体内容。So far, the main direction corresponding to the remote sensing image has been obtained. As for how to use the main direction, you can refer to the "Research on the Extraction Technology of Remote Sensing Image Residential Areas Based on Texture Features" mentioned in the background art (Jin Fei, PLA Information). The specific content of chapter 3.1 "The extraction of residential areas based on Fourier transform" and chapter 3.2 "The extraction of residential areas based on Gabor transform".
当然，本发明的遥感影像主方向确定方法不仅仅局限于傅里叶变换以及Gabor变换，任何算法中只要需要使用到遥感影像主方向，均可以使用本发明的这种确定方法，上述方案应当仍落入本发明的保护范围内。Of course, the method for determining the main direction of remote sensing images of the present invention is not limited to Fourier transform and Gabor transform. As long as the main direction of remote sensing images needs to be used in any algorithm, the method for determining the main direction of the present invention can be used. The above scheme should still be used. fall within the protection scope of the present invention.
实施例2Example 2
本实施例为一种遥感影像主方向确定装置，包括存储器、处理器以及存储在存储器中并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现实施例1中所述遥感影像主方向确定方法，而在进行具体的编程时，由于编程语言的语法等知识是本领域的公知常识，技术人员完全有能力依据本发明具体的遥感影像主方向确定方法，使用现有的编程语言(例如C语言、JAVA、汇编语言、C#、C++等)进行相应的编程，这个过程在此不予以赘述。This embodiment is a device for determining the main direction of a remote sensing image, including a memory, a processor, and a computer program stored in the memory and running on the processor, the processor implementing the program described in Embodiment 1 when the processor executes the program The method for determining the main direction of remote sensing images, and when performing specific programming, since knowledge of programming language syntax and other knowledge is common knowledge in the field, technicians are fully capable of determining the main direction of remote sensing images according to the specific method of the present invention. A programming language (such as C language, JAVA, assembly language, C#, C++, etc.) is used to perform corresponding programming, and this process will not be repeated here.
在上述实施例中，对遥感影像进行随机分割形成了遥感影像区域，实际应用中，还可以设定特定的分割方案来进行分割，比如均匀分割、比例分割或模板分割等，上述方案应当仍落入本发明的保护范围内。In the above embodiment, remote sensing images are randomly divided to form remote sensing image regions. In practical applications, a specific segmentation scheme can also be set for segmentation, such as uniform segmentation, proportional segmentation, or template segmentation. into the protection scope of the present invention.
在上述实施例中，使用了各角度之间的方差作为一致性判断分类的标准，在实际应用中，可以通过对不同角度求均值，计算每个角度与该均值的偏差来进行一致性判断，还可以使用标准方差或最小二乘法或其他常用的一致性分类方法进行判断，上述方案应当仍落入本发明的保护范围内。In the above embodiment, the variance between angles is used as the criterion for consistency judgment and classification. In practical applications, consistency judgment can be made by averaging different angles and calculating the deviation between each angle and the average value. The standard deviation or the least squares method or other common consistency classification methods can also be used for judgment, and the above solutions should still fall within the protection scope of the present invention.
在上述实施例中，在计算遥感影像区块或子区块主方向时，采用了对构成该区块的区域对应主方向或构成该子区块的子区域对应主方向求均值的方式，在实际应用中还可以使用例如算数平均、误差最小等其他计算方式来求取，另外也可以使用现有的利用傅里叶变换幅度谱的角向分布的方式来求取，上述方案应当仍落入本发明的保护范围内。In the above-mentioned embodiment, when calculating the main direction of a remote sensing image block or sub-block, the method of averaging the main direction corresponding to the region constituting the block or the corresponding main direction of the sub-region constituting the sub-block is adopted. In practical applications, other calculation methods such as arithmetic mean and minimum error can also be used to obtain, in addition, the existing method using the angular distribution of the Fourier transform amplitude spectrum can also be used to obtain, the above scheme should still fall into within the protection scope of the present invention.
以上给出了具体的实施方式，但本发明不局限于所描述的实施方式。本发明的基本思路在于上述基本方案，在不脱离本发明的原理和精神的情况下对实施方式进行的变化、修改、替换和变型仍落入本发明的保护范围内。Specific embodiments are given above, but the present invention is not limited to the described embodiments. The basic idea of the present invention lies in the above-mentioned basic scheme, and changes, modifications, substitutions and alterations to the embodiments without departing from the principle and spirit of the present invention still fall within the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810903797.4ACN110309694B (en) | 2018-08-09 | 2018-08-09 | Method and device for determining main direction of remote sensing image |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810903797.4ACN110309694B (en) | 2018-08-09 | 2018-08-09 | Method and device for determining main direction of remote sensing image |
| Publication Number | Publication Date |
|---|---|
| CN110309694Atrue CN110309694A (en) | 2019-10-08 |
| CN110309694B CN110309694B (en) | 2021-03-26 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810903797.4AExpired - Fee RelatedCN110309694B (en) | 2018-08-09 | 2018-08-09 | Method and device for determining main direction of remote sensing image |
| Country | Link |
|---|---|
| CN (1) | CN110309694B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080146302A1 (en)* | 2006-12-14 | 2008-06-19 | Arlen Lynn Olsen | Massive Multiplayer Event Using Physical Skills |
| CN102542295A (en)* | 2012-01-08 | 2012-07-04 | 西北工业大学 | Method for detecting landslip from remotely sensed image by adopting image classification technology |
| CN102968634A (en)* | 2012-11-23 | 2013-03-13 | 南京大学 | Method for extracting parking lot structure under main direction restriction |
| CN103347187A (en)* | 2013-07-23 | 2013-10-09 | 北京师范大学 | Remote-sensing image compression method for discrete wavelet transform based on self-adaptation direction prediction |
| CN104657741A (en)* | 2015-01-09 | 2015-05-27 | 北京环境特性研究所 | Target classification method based on video images |
| CN105261014A (en)* | 2015-09-30 | 2016-01-20 | 西南交通大学 | Multi-sensor remote sensing image matching method |
| CN105825169A (en)* | 2016-03-10 | 2016-08-03 | 辽宁工程技术大学 | Road-image-based pavement crack identification method |
| CN105844337A (en)* | 2016-04-14 | 2016-08-10 | 吴本刚 | Intelligent garbage classification device |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080146302A1 (en)* | 2006-12-14 | 2008-06-19 | Arlen Lynn Olsen | Massive Multiplayer Event Using Physical Skills |
| CN102542295A (en)* | 2012-01-08 | 2012-07-04 | 西北工业大学 | Method for detecting landslip from remotely sensed image by adopting image classification technology |
| CN102968634A (en)* | 2012-11-23 | 2013-03-13 | 南京大学 | Method for extracting parking lot structure under main direction restriction |
| CN103347187A (en)* | 2013-07-23 | 2013-10-09 | 北京师范大学 | Remote-sensing image compression method for discrete wavelet transform based on self-adaptation direction prediction |
| CN104657741A (en)* | 2015-01-09 | 2015-05-27 | 北京环境特性研究所 | Target classification method based on video images |
| CN105261014A (en)* | 2015-09-30 | 2016-01-20 | 西南交通大学 | Multi-sensor remote sensing image matching method |
| CN105825169A (en)* | 2016-03-10 | 2016-08-03 | 辽宁工程技术大学 | Road-image-based pavement crack identification method |
| CN105844337A (en)* | 2016-04-14 | 2016-08-10 | 吴本刚 | Intelligent garbage classification device |
| Publication number | Publication date |
|---|---|
| CN110309694B (en) | 2021-03-26 |
| Publication | Publication Date | Title |
|---|---|---|
| CN107301661B (en) | High-resolution remote sensing image registration method based on edge point features | |
| Shi et al. | Automatic road crack detection using random structured forests | |
| Hu et al. | Road centerline extraction in complex urban scenes from LiDAR data based on multiple features | |
| Zamir et al. | Accurate image localization based on google maps street view | |
| CN105335966B (en) | Multiscale morphology image division method based on local homogeney index | |
| CN107392968B (en) | Image saliency detection method fused with color contrast map and color space distribution map | |
| CN106157323B (en) | A kind of insulator division and extracting method of dynamic division threshold value and block search combination | |
| CN106683102B (en) | SAR image segmentation method based on ridge ripple filter and convolutional coding structure learning model | |
| CN110363053B (en) | Method and device for extracting residential area of remote sensing image | |
| Yuan et al. | Learning to count buildings in diverse aerial scenes | |
| CN103345760B (en) | A kind of automatic generation method of medical image object shapes template mark point | |
| CN108710862B (en) | High-resolution remote sensing image water body extraction method | |
| CN105825169A (en) | Road-image-based pavement crack identification method | |
| CN110348478A (en) | It is a kind of based on Shape Classification and trees extracting method in the outdoor point cloud scene combined | |
| CN108664983A (en) | A kind of scale and the adaptive SURF characteristic point matching methods of characteristic strength | |
| Ni et al. | Joint clusters and iterative graph cuts for ALS point cloud filtering | |
| Zou et al. | Path voting based pavement crack detection from laser range images | |
| CN103310456B (en) | Multidate/multi-modal remote sensing image registration method based on Gaussian-Hermite square | |
| CN106940782B (en) | High-resolution SAR newly-added construction land extraction software based on variation function | |
| CN118628682A (en) | Automatic modeling method of building 3D model based on 3D point cloud | |
| CN104268565A (en) | Scene Matching Area Selection Method Based on Regression Learning | |
| CN114742968B (en) | A method for generating elevation map based on building elevation point cloud | |
| Prerna et al. | Evaluation of LiDAR and image segmentation based classification techniques for automatic building footprint extraction for a segment of Atlantic County, New Jersey | |
| US20170053399A1 (en) | Method and apparatus for processing block to be processed of urine sediment image | |
| CN104794723A (en) | Remote-sensing image building location detection method based on probability |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20210326 Termination date:20210809 |