Unlock instant, AI-driven research and patent intelligence for your innovation.

Building extraction algorithm combining elevation map Gabor texture features and LiDAR point cloud features

A texture feature and elevation map technology, which is applied in the field of algorithm research for building extraction, can solve the problems of reduced classification accuracy, large feature dimensions, and increased calculation amount, and achieves the effect of reducing errors.

Inactive Publication Date: 2019-11-05
WUHAN UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this will also increase the dimensionality of the obtained features, which will not only increase the amount of calculation, but may also reduce the classification accuracy due to the existence of some features that are not conducive to classification. Therefore, feature selection can be performed on the obtained features.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Building extraction algorithm combining elevation map Gabor texture features and LiDAR point cloud features
  • Building extraction algorithm combining elevation map Gabor texture features and LiDAR point cloud features
  • Building extraction algorithm combining elevation map Gabor texture features and LiDAR point cloud features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present embodiment will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0049] Such as figure 1 As shown, this embodiment converts the point cloud into an elevation map by calculating the feature value, elevation and density of the point cloud, uses Gabor transform to extract the texture features of the elevation map, and assigns the feature to the point cloud, and then uses the BPSO algorithm Feature selection and SVM classification parameter optimization are carried out to realize the extraction of buildings. Gabor transform is used to obtain the texture features of LiDAR elevation map, and then point cloud classification and building extraction are carried out by combining the features of point cloud itself. Due to the large number of calculated feature values, the BPSO algorithm is used to optimize the features involved in the classification and the parameters of the SVM method simultaneously, so as to realiz...

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

No PUM Login to View More

Abstract

The invention relates to a building extraction algorithm combining elevation map Gabor texture features and LiDAR point cloud features. Firstly, image information corresponding to point cloud data isobtained by converting point cloud into an elevation map; then, texture features of the elevation map are extracted through Gabor transformation, features corresponding to different spatial frequencies (scales) and directions are captured, the obtained image features have discrimination performance and are high in dimensionality, and more reliable information can be provided for building extraction. The point cloud features and the elevation map texture features are fused, and information data is provided for building extraction from more different angles. A BPSO algorithm is adopted to perform feature selection on high-dimensional features to obtain an optimized feature combination, and the accuracy of a building extraction result is improved while the building extraction efficiency is improved. In addition, the BPSO algorithm can also optimize kernel function parameters in the SVM classification algorithm used for extracting the building, so that the building extraction efficiency and precision are further improved.

Description

technical field [0001] The invention belongs to the field of LiDAR data processing and application, in particular for the algorithm research of building extraction by using LiDAR point cloud. Background technique [0002] In recent years, the application of remote sensing images in environmental monitoring, military reconnaissance, precision agriculture and other fields has become increasingly important. In addition to color and grayscale information, image data can also provide texture information for related research. Commonly used texture extraction methods include gray level co-occurrence matrix (GLCM), local binary patterns (LBP) and histogram of oriented gradients. LiDAR is a measurement method that measures the distance of a target by irradiating it with a pulsed laser light and measuring the reflected pulse with a sensor. It can be used in geodesy, geostatistics, archaeology, geography, and the control and navigation of autonomous vehicles. Compared with images tha...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/40G06K9/46G06K9/62
CPCG06V20/64G06V20/176G06V10/30G06V10/50G06F18/2411
Inventor 赖旭东杨婧如李咏旭
Owner WUHAN UNIV