A Classification Method of Urban Vegetation Based on UAV Image and Reconstructed Point Cloud
A classification method and unmanned aerial vehicle technology, applied to computer parts, instruments, calculations, etc., can solve the problem of not being able to extract different types of vegetation
Active Publication Date: 2021-05-18
HENAN POLYTECHNIC UNIV
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the past, the characteristics of image spectrum, texture and shape were mostly used in the classification of urban vegetation, and a certain type of vegetation could be extracted well, but it was not possible to further extract different types of vegetation from the large category of vegetation based on height information.
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
[0047] The technical solutions of the present invention will be described in further detail below through specific implementation methods.
[0048] Such as figure 1 and figure 2 As shown, a method for urban vegetation classification based on UAV images and reconstructed point clouds includes the following steps:
[0049] Step 1. Point cloud reconstruction of the original UAV image
[0050] Take the original UAV image of the research area, use the SFM algorithm to obtain the sparse point cloud of the research area, and use the CMVS / PMVS algorithm to expand the sparse point cloud into a dense point cloud;
[0051] Specifically, the SFM algorithm is a camera calibration method that can iteratively solve the camera matrix and three-dimensional point coordinates when the camera parameters and three-dimensional information in the scene are unknown. (that is, calculate the projection matrix), and then use the method of triangulation to restore the scene structure. The theoretica...
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 provides a method for urban vegetation classification based on UAV images and reconstructed point clouds, including: point cloud reconstruction of original UAV images; generation of nDSM information of the research area; vegetation index calculation based on visible light; image objects classification discrimination. The present invention reconstructs the dense point cloud of the research area based on the motion recovery structure (SFM), multi-view clustering (CMVS) and dense matching (PMVS) algorithms based on the patch model; the digital elevation model (DEM) of the research area is generated by filtering and interpolation and Normalized digital surface model (nDSM), combined with image spectral information to classify and extract urban vegetation at different heights; using object-oriented image analysis methods, based on nDSM information and normalized green-red difference index (NGRDI) and visible light band differences Spectral information such as vegetation index (VDVI) realizes the distinction of vegetation types at different heights and greatly improves the accuracy of the distinction.
Description
technical field [0001] The invention relates to a method for classifying urban vegetation, in particular to a method for classifying urban vegetation based on drone images and reconstructed point clouds. Background technique [0002] Vegetation is an important part of the urban ecosystem, which has the functions of absorbing noise, reducing smog and mitigating the urban heat island effect. Studying and accurately grasping the type, area and spatial distribution of urban vegetation can provide a reliable basis for urban planners to optimize the utilization of urban space, which is conducive to improving the urban livability index and promoting urban development. Traditional vegetation surveys mostly use manual methods. Although the survey is detailed and accurate, it consumes a lot of manpower and financial resources and has a long cycle, which cannot meet the needs of rapid update of vegetation information. UAV remote sensing has the characteristics of objectivity and high ...
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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/188G06F18/241
Inventor 于海洋李莹王燕燕吴建鹏杨礼
Owner HENAN POLYTECHNIC UNIV