BeBaOI: Benchmark and Baseline Methods for determining Overlapping Images, 02.2023 - 01.2024 (finished project)
PI, funded by ISPRS Scientific Initiatives and collaborated with Assistant Professor, Dr.-Ing. Xin Wang, School of Geodesy and Geomatics, Wuhan University. [report]
Fund
EUR 10k
Abstract
Efficient determination of overlapping image pairs is very crucial for large scale SfM (Structure from Motion) or image orientation. This project, BeBaDOI, addresses this challenge via exploring the possibility of learning-based methods.
Research Output
- Hou, Q., Xia, R., Zhang, J., Feng, Y., Zhan, Z., & Wang, X. (2023). Learning visual overlapping image pairs for SfM via CNN fine-tuning with photogrammetric geometry information. International Journal of Applied Earth Observation and Geoinformation, 116, 103162.
- Zhan, H., Yu, Y. F., Xu, Y. W., Hou, Q. B., Xia, R., Wang, X., … & Heipke, C. (2023). Bedoi: Benchmarks For Determining Overlapping Images With Photogrammetric Information. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 48, 1685-1692.