利用无人机图像和深度学习语义分割技术自动提取真实道路场景并进行三维建模

IF 3.7 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

International Journal of Digital Earth Pub Date : 2024-06-19 DOI:10.1080/17538947.2024.2365970

Zhen Liu, Wenxiu Wu, Danyu Wang, Bingyan Cui, Xingyu Gu

引用次数: 0

摘要

从无人机图像中提取道路面临着光照、噪声、遮挡物和类似非道路物体的挑战，使得高质量的道路提取变得困难。为了解决这些问题，本...

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Automatic extraction and 3D modeling of real road scenes using UAV imagery and deep learning semantic segmentation

The extraction of roads from UAV images is challenged by lighting, noise, occlusions, and similar non-road objects, making high-quality road extraction difficult. To addressing these issues, this s...

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

International Journal of Digital Earth 地学-遥感

CiteScore

6.50

自引率

3.90%

发文量

审稿时长

3 months

期刊介绍： The International Journal of Digital Earth is a response to this initiative. This peer-reviewed academic journal (SCI-E) focuses on the theories, technologies, applications, and societal implications of Digital Earth and those visionary concepts that will enable a modeled virtual world. The journal encourages papers that: Progress visions for Digital Earth frameworks, policies, and standards; Explore geographically referenced 3D, 4D, or 5D models to represent the real planet, and geo-data-intensive science and discovery; Develop methods that turn all forms of geo-referenced data, from scientific to social, into useful information that can be analyzed, visualized, and shared; Present innovative, operational applications and pilots of Digital Earth technologies at a local, national, regional, and global level; Expand the role of Digital Earth in the fields of Earth science, including climate change, adaptation and health related issues,natural disasters, new energy sources, agricultural and food security, and urban planning; Foster the use of web-based public-domain platforms, social networks, and location-based services for the sharing of digital data, models, and information about the virtual Earth; and Explore the role of social media and citizen-provided data in generating geo-referenced information in the spatial sciences and technologies.