UAVDB-TwoFrame: An Extension of UAVDB with Consecutive Frame Pairs
- zenodo.org
zipUpdated May 30, 2025
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteYu-Hsi Chen; Yu-Hsi Chen (2025). UAVDB-TwoFrame: An Extension of UAVDB with Consecutive Frame Pairs [Dataset]. http://doi.org/10.5281/zenodo.15549514zipAvailable download formatsUnique identifierhttps://doi.org/10.5281/zenodo.15549514Dataset updatedMay 30, 2025AuthorsYu-Hsi Chen; Yu-Hsi ChenLicenseAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automaticallyDescriptionThis dataset is an extension of the UAVDB, organized as consecutive frame pairs to support tasks involving temporal information. It includes:
- 10,763 * 2 images in train/
- 2,720 * 2 images in val/
- 4,578 * 2 images in test/
Each frame pair is stored using the naming pattern:
d{a}c{b}_{n}.jpg, d{a}c{b}_{n+1}.jpg
For example, files in the train/ folder include:
d1c0_0.jpg, d1c0_1.jpg
d1c0_10.jpg, d1c0_11.jpg
...
d4c5_25211.jpg, d4c5_25212.jpgThis format enables optical flow estimation and temporal deep learning applications, offering enhanced flexibility for training, evaluation, or reproduction of motion-aware vision tasks.
DPFlow on UAVDB
- zenodo.org
Updated Jun 17, 2025ShareFacebookTwitterEmailClick to copy linkLink copiedCiteYu-Hsi Chen; Yu-Hsi Chen (2025). DPFlow on UAVDB [Dataset]. http://doi.org/10.5281/zenodo.15679582Unique identifierhttps://doi.org/10.5281/zenodo.15679582Dataset updatedJun 17, 2025AuthorsYu-Hsi Chen; Yu-Hsi ChenLicenseAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automaticallyDescriptionSEA-RAFT on UAVDB
- zenodo.org
Updated Jun 10, 2025ShareFacebookTwitterEmailClick to copy linkLink copiedCiteYu-Hsi Chen; Yu-Hsi Chen (2025). SEA-RAFT on UAVDB [Dataset]. http://doi.org/10.5281/zenodo.15628629Unique identifierhttps://doi.org/10.5281/zenodo.15628629Dataset updatedJun 10, 2025AuthorsYu-Hsi Chen; Yu-Hsi ChenLicenseAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automaticallyDescriptionRPKNet on UAVDB
- zenodo.org
Updated Jun 10, 2025ShareFacebookTwitterEmailClick to copy linkLink copiedCiteYu-Hsi Chen; Yu-Hsi Chen (2025). RPKNet on UAVDB [Dataset]. http://doi.org/10.5281/zenodo.15628226Unique identifierhttps://doi.org/10.5281/zenodo.15628226Dataset updatedJun 10, 2025AuthorsYu-Hsi Chen; Yu-Hsi ChenLicenseAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automaticallyDescription
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
This dataset is an extension of the UAVDB, organized as consecutive frame pairs to support tasks involving temporal information. It includes:
- 10,763 * 2 images in train/
- 2,720 * 2 images in val/
- 4,578 * 2 images in test/
Each frame pair is stored using the naming pattern:
d{a}c{b}_{n}.jpg, d{a}c{b}_{n+1}.jpg
For example, files in the train/ folder include:
d1c0_0.jpg, d1c0_1.jpg
d1c0_10.jpg, d1c0_11.jpg
...
d4c5_25211.jpg, d4c5_25212.jpg
This format enables optical flow estimation and temporal deep learning applications, offering enhanced flexibility for training, evaluation, or reproduction of motion-aware vision tasks.