SAR image road extraction method and device based on semantic segmentation and conditional random field
A conditional random field and semantic segmentation technology, applied in the computer field, can solve problems such as the reduction of feature receptive field, the loss of image details, and the segmentation effect does not increase but decreases, so as to improve the loss of image information, improve the extraction performance, and optimize the segmentation results. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0045] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.
[0046] In one of the examples, as figure 1 所示,提供一种基于语义分割和条件随机场的SAR图像道路提取方法,具体步骤如下:
[0047] 步骤102,获取SAR道路图像样本。
[0048] SAR道路图像样本指的是已标注的SAR道路图像,例如:以SAR道路图像和对应的图像真值作为SAR道路图像样本。
[0049] 道路可以是建筑物之间的道路,也可以是机场跑道等,再次不做具体的限制。
[0050] 以高分系列卫星获取的机场道路SAR道路预测概率图进行标注为例,机场道路SAR道路预测概率图中机场道路标注为类别“1”,对应的像素值为“255”,其余背景为类别“0”,对应的像素值为0,从而得到机场道路SAR道路预测概率图的真值。
[0051] 步骤104,将SAR道路图像样本输入预先设置的语义分割模型。
[0052] 语义分割模型包括:空间金字塔编码器和解码器;空间金字塔编码器包括:多层卷积神经网络和空间金字塔模块。
[0053] 初始时,预先设置的语义分割模型中的网络参数为初值,通过样本训练之后,才可以进行图像分割。
[0054] 步骤106,通过多层卷积神经网络对SAR道路图像样本进行特征提取,将提取得到的浅层特征输入解码器的并联通道,将提取得到的深层特征输...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com