Remote sensing image sample labeling method based on ArcMap
A sample labeling and remote sensing image technology, applied in the field of remote sensing information, can solve the problems of not having the sample labeling function, unable to meet the needs of remote sensing image labeling, etc., and achieve the effect of improving efficiency
Active Publication Date: 2022-05-13
北京市遥感信息研究所
View PDF14 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005]
In view of the above analysis, the present invention aims to provide an ArcMap-based remote sensing image sample labeling method to solve the problem that the current commercial software for remote sensing image processing generally does not have the sample labeling function and cannot meet the needs of remote sensing image labeling
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] Preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of the application and together with the embodiments of the present invention are used to explain the principle of the present invention and are not intended to limit the scope of the present invention.
[0031] Technical idea of the present invention: Due to the lack of effective remote sensing image sample labeling tools, the following methods are usually used for remote sensing image sample labeling: first, the huge remote sensing image area is cut and saved as an ordinary picture without geographical information, Limited by image browser tools and memory, the cropped images are usually below 100MB; after that, use PhotoShop or other professional image processing tools to process the images separately, and save the annotation results; finally, synthesize the annotation results to obtain the...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a remote sensing image sample labeling method based on ArcMap, and belongs to the technical field of remote sensing information. The method comprises the following steps: S1, an Add-In plug-in tool for installing ArcMap creates a labeling environment, wherein the plug-in tool comprises an installation file and a configuration file; the plug-in tool generates an annotation file from a record which is stored in an annotation process and contains a category name; s2, generating a corresponding Shp file layer according to the configuration file and a target category in the existing labeled file, and loading the Shp file layer; s3, opening a remote sensing image sample file, selecting a target category and a labeling shape of an added sample by using a vector editing tool of ArcMap, and performing sample labeling editing; and S4, storing a sample labeling result, and clearing an intermediate result file in the editing process to complete sample labeling. Aiming at the problem that current machine learning image sample labeling software cannot support remote sensing image sample labeling, remote sensing image target labeling is realized based on an Add-In tool, and the remote sensing image sample labeling efficiency is effectively improved.
Description
technical field [0001] The invention relates to the technical field of remote sensing information, in particular to an ArcMap-based remote sensing image sample labeling method. Background technique [0002] Annotated samples, that is, a collection of images and attributes that have attached target attribute information to a given area on the image, are the data basis for supervised learning in the field of machine learning and the basis for algorithm training. In recent years, machine learning technology represented by deep learning has been widely used in all walks of life, which has greatly promoted the development of speech recognition, image recognition, target detection, scene understanding and other technologies. The effectiveness and application effect of the deep learning model is also based on the training of a large number of labeled samples. Therefore, the quantity and quality of labeled samples directly determine the effect of the algorithm. Usually, the annota...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F9/445G06V10/774G06K9/62
CPCG06F9/44526G06F9/44505G06F18/214Y02D10/00
Inventor 孟钢李晓斌田菁戴桦宇杨渊博岳文振尹璐
Owner 北京市遥感信息研究所