Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 1685-1692 |
| Seitenumfang | 8 |
| Fachzeitschrift | International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives |
| Jahrgang | XLVIII-1 |
| Ausgabenummer | W2-2023 |
| Publikationsstatus | Veröffentlicht - 14 Dez. 2023 |
| Veranstaltung | ISPRS Geospatial Week 2023 - Kairo, Ägypten Dauer: 2 Sept. 2023 → 7 Sept. 2023 |
Abstract
For conventional SfM pipeline, image matching is enduring limitation when considering the time efficiency. In the last few years, to speed up image matching procedure, many image retrieval works were proposed to fast find overlapping image pairs, e.g., bag-of-word that clusters hand-crafted local features in a hierarchical way for efficient similar image retrieval, or learning-based global features (such as, VGG or ResNet) are used to represent image in a global compact manner. However, there are rarely benchmarks with referenced overlapping information to: first, evaluate the retrieval performance; second, fine tune deep-learning models along the direction that is more capable to deal with overlapping image pairs. In this work, based on traditional photogrammetric procedures, relevant photogrammetric information is obtained including image orientation parameters, 3D mesh model and etc., we then generate a benchmark for determining Overlapping Images - BeDOI, in which referenced pairwise overlapping relationships are estimated via rigorous photogrammetric geometry. To extend the generality, in total, BeDOI contains 13667 images which are basically UAV and close-range images of various scene categories, e.g., urban cities, campus, village, historical relics, green land, buildings and etc.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Information systems
- Sozialwissenschaften (insg.)
- Geografie, Planung und Entwicklung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, Jahrgang XLVIII-1, Nr. W2-2023, 14.12.2023, S. 1685-1692.
Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review
}
TY - JOUR
T1 - Bedoi
T2 - ISPRS Geospatial Week 2023
AU - Zhan, H.
AU - Yu, Y. F.
AU - Hou, Q. B.
AU - Xia, R.
AU - Feng, Y.
AU - Zhan, Z. Q.
AU - Hänsch, R.
AU - Heipke, C.
AU - Gruber, Michael
AU - Xu, Y.W.
AU - Wang, Xin
AU - Li, M.L.
N1 - Funding Information: This work was supported by ISPRS Scientific Initiatives 2023, Natural Science Foundation of Hubei Province, China (No. 2022CFB727) and National Natural Science Foundation of China (No. 61871295).
PY - 2023/12/14
Y1 - 2023/12/14
N2 - For conventional SfM pipeline, image matching is enduring limitation when considering the time efficiency. In the last few years, to speed up image matching procedure, many image retrieval works were proposed to fast find overlapping image pairs, e.g., bag-of-word that clusters hand-crafted local features in a hierarchical way for efficient similar image retrieval, or learning-based global features (such as, VGG or ResNet) are used to represent image in a global compact manner. However, there are rarely benchmarks with referenced overlapping information to: first, evaluate the retrieval performance; second, fine tune deep-learning models along the direction that is more capable to deal with overlapping image pairs. In this work, based on traditional photogrammetric procedures, relevant photogrammetric information is obtained including image orientation parameters, 3D mesh model and etc., we then generate a benchmark for determining Overlapping Images - BeDOI, in which referenced pairwise overlapping relationships are estimated via rigorous photogrammetric geometry. To extend the generality, in total, BeDOI contains 13667 images which are basically UAV and close-range images of various scene categories, e.g., urban cities, campus, village, historical relics, green land, buildings and etc.
AB - For conventional SfM pipeline, image matching is enduring limitation when considering the time efficiency. In the last few years, to speed up image matching procedure, many image retrieval works were proposed to fast find overlapping image pairs, e.g., bag-of-word that clusters hand-crafted local features in a hierarchical way for efficient similar image retrieval, or learning-based global features (such as, VGG or ResNet) are used to represent image in a global compact manner. However, there are rarely benchmarks with referenced overlapping information to: first, evaluate the retrieval performance; second, fine tune deep-learning models along the direction that is more capable to deal with overlapping image pairs. In this work, based on traditional photogrammetric procedures, relevant photogrammetric information is obtained including image orientation parameters, 3D mesh model and etc., we then generate a benchmark for determining Overlapping Images - BeDOI, in which referenced pairwise overlapping relationships are estimated via rigorous photogrammetric geometry. To extend the generality, in total, BeDOI contains 13667 images which are basically UAV and close-range images of various scene categories, e.g., urban cities, campus, village, historical relics, green land, buildings and etc.
KW - Image Matching
KW - Image Retrieval
KW - Overlapping image pairs
KW - Photogrammetric Information
KW - Structure from Motion (SfM)
UR - http://www.scopus.com/inward/record.url?scp=85183290467&partnerID=8YFLogxK
U2 - 10.5194/isprs-archives-XLVIII-1-W2-2023-1685-2023
DO - 10.5194/isprs-archives-XLVIII-1-W2-2023-1685-2023
M3 - Conference article
AN - SCOPUS:85183290467
VL - XLVIII-1
SP - 1685
EP - 1692
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
SN - 1682-1750
IS - W2-2023
Y2 - 2 September 2023 through 7 September 2023
ER -