Remote Sensing for Natural and Urban Scene Understanding and Applications

Dear Colleagues,

In recent years, advancements in technologies such as laser scanning, unmanned aerial photogrammetry, and ubiquitous collection have facilitated the acquisition of geographic information. The spatial data obtained from these sources, both directly and indirectly, are becoming increasingly significant within geographic information science. Point clouds derived from diverse origins exhibit characteristics such as extensive feature sets, irregular spatial distributions, and cross-scale variations, posing challenges for efficient processing. Furthermore, the rapid advancement of intelligent processing technologies for spatial data (e.g., image, point cloud) necessitates addressing the characterization of multi-level features in point clouds, 3D information extraction and fusion, and on-demand structured representations. Consequently, constructing intelligent and effective processing methods for spatial data is important.

Significant advancements have been made in the intelligent processing technologies for spatial data: (1) Existing point cloud feature descriptors are primarily constructed using manually designed features and deep learning techniques; however, further research is necessary to enhance high-level feature descriptions. (2) Most methods mainly rely on feature descriptor-based and deep learning approaches for semantic extraction, so there is a need for improvements in both network architecture design and the quality of training samples for deep learning networks. (3) Current research focuses on LOD modeling and façade reconstruction of buildings. However, the intelligent understanding of point cloud scenes requires further development in high-level feature extraction to effectively interpret large-scale point cloud scenes.

This Special Issue primarily focuses on integrating methods such as artificial intelligence and deep learning to establish object-oriented deep learning networks for spatial data. It aims to achieve precise scene understanding for regional and individual objects through new methods and technologies. We hope to provide valuable technical references for this field and promote research on intelligent processing models and methods for 3D dense point clouds. Articles may cover, but are not limited to, the following subjects:

(1) Advanced algorithms for point cloud registration and alignment;

(2) Object extraction and classification techniques applicable to natural and urban environments;

(3) Three-dimensional modeling of urban scenes;

(4) Applications of intelligent processing in environmental monitoring and disaster management.

Dr. Yufu Zang
Dr. Jinhu Wang
Dr. Yueqian Shen
Prof. Dr. Haiyan Guan
Dr. Dong Chen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.