A building contour automatic extraction algorithm based on a convolutional neural network and polygon regularization

A neural network, automatic extraction technology, applied in computing, image analysis, instruments, etc., can solve problems such as inability to truly automate, and achieve the effect of reducing workload and strong robustness

Active Publication Date: 2019-06-18
WUHAN UNIV
View PDF10 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, this method of empirically designing features can of

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
  • A building contour automatic extraction algorithm based on a convolutional neural network and polygon regularization
  • A building contour automatic extraction algorithm based on a convolutional neural network and polygon regularization
  • A building contour automatic extraction algorithm based on a convolutional neural network and polygon regularization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0051] see figure 1 and figure 2 , the present invention uses a multi-scale fusion full convolutional neural network (Multi-scaleAggregation Full Convolutional Neural Network, MA-FCN) to learn building features in high-resolution remote sensing images, and then performs pixel-level prediction of building coverage in remote sensing images. In order to train the neural network model, it is first necessary to obtain training samples, attached figure 1 Shows the process of building a training sample library. Firstly, the remote sensing images are cropped and resampled to obtain an image range with appropriate resolution and building coverage data. The corresponding building vector data within the image extent is then rasterized to match the image resolution. Finally, the remote sensing images and corresponding label data are divided into sample blocks of appropriate size (such as 256×256 pixels, or 512×512 pixels) in combination with factors such as computer performance and th...

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 discloses an automatic building contour extraction algorithm based on a convolutional neural network and polygon regularization. The automatic building contour extraction algorithm comprises the following steps: constructing a sample library according to an existing image and a building coverage vector file; Constructing a multi-scale fusion full convolutional neural network, training the multi-scale fusion full convolutional neural network through a sample library, and predicting the remote sensing image by using the trained network model to obtain a segmentation result coveredby the surface building of the remote sensing image; Performing building edge initialization based on the building semantic segmentation result, and obtaining an initial vector polygon; Removing wrongpolygons and wrong edges and nodes of the polygons by using a coarse adjustment algorithm; conducting regularization on the vector polygons through a regularization algorithm, and obtaining regular building vector edges. According to the method, the multi-scale fusion full convolutional neural network is high in scale robustness, the regularization algorithm can adapt to vector edges under various conditions, and the workload of manually drawing building edges is greatly reduced.

Description

technical field [0001] The invention relates to a deep learning method for extracting buildings from remote sensing images and a regularization algorithm for polygonal contours of buildings, which can be used for building extraction from remote sensing images, building vector edge generation, building change detection, and the like. Background technique [0002] Automatic extraction of buildings from remote sensing images is of great significance in applications such as urban planning, population estimation, map making and updating. Traditionally, the main work of extracting buildings from aerial / aerospace images focuses on: empirically designing an appropriate feature to express "what is a building", and creating corresponding features for automatic recognition and extraction of buildings. Commonly used metrics include pixels, spectra, lengths, edges, shapes, textures, shadows, heights, semantics, and more. However, these indicators will change significantly with seasons, ...

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
IPC IPC(8): G06T7/13G06T7/11G06T7/187G06T7/136
Inventor 季顺平魏世清
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products