Background:
Photogrammetry for mapping has experienced a substantial breakthrough in conjunction with the development of the recent vision-based algorithms and deep learning methods. It has geared towards faster, more accurate, and more automated processes in producing geoinformation at various levels of details and scales, such as LoD models, semantic segmentation, robotic mapping, image interpretation, and scene understanding. We hence invite contributions focusing on image-based data processing with photogrammetric and computer vision methods for deriving and analyzing 3D geoinformation products.
Topics of the Special Issue include but are not limited to:
1. Structure from motion, SLAM, and aerial/satellite photogrammetric mapping
2. Comparative studies of photogrammetry and vision algorithms
3. Path planning, advanced onboard perception, and 3D mapping with unmanned vehicles
4. Machine/Deep learning methods to boost photogrammetric methods for the generation of 3D geoinformation products
5. Semantic segmentation for aerial and satellite images
6. Image-based object modeling, city modeling, and LoD2 model generation
7. Accuracy analysis of any subtopic under the umbrella of photogrammetry and vision-based mapping
8. Reviews of current status and trends in photogrammetry and computer vision for 3D mapping
Paper Submissions Deadline
You are warmly invited to consider submitting your paper before July 31, 2022, to this special issue. Please note: This paper is submitted for the Special Issue "Photogrammetric and Computer Vision for 3D Geoinformation ".
Guest Editors
Rongjun QIN
Department of Civil, Environmental and Geodetic Engineering
The Ohio State University, United States
Fabio Remondino
3D Optical Metrology unit
Fondazione Bruno Kessler (FBK), Italy
Francesco Nex
Department of Earth Observation Science
University of Twente, The Netherlands
Devrim Acka
Department of Civil Engineering
Isik University, Turkey