Dataset Open Access
Remote Sensing VQA - Low Resolution (RSVQA LR)
Sylvain Lobry;
Diego Marcos;
Jesse Murray;
Devis Tuia
Remote sensing images contain a wealth of information which can be useful for a wide range of tasks including land cover classification, object counting or detection. However, most of the available methodologies are task-specific, thus inhibiting generic and easy access to the information contained in remote sensing data. As a consequence, accurate remote sensing product generation still requires expert knowledge. With RSVQA, we propose a system to extract information from remote sensing data that is accessible to every user: we use questions formulated in natural language and use them to interact with the images. With the system, images can be queried to obtain high level information specific to the image content or relational dependencies between objects visible in the images. Using an automatic method, we built two datasets (using low and high resolution data) of image/question/answer triplets. The information required to build the questions and answers is queried from OpenStreetMap (OSM). The datasets can be used to train (when using supervised methods) and evaluate models to solve the RSVQA task.
This page concerns the low resolution dataset.
| Name | Size | |
|---|---|---|
|
all_answers.json
md5:9042f398d25413a10ea530b7b2a94dd2 |
9.2 MB | Download |
|
all_questions.json
md5:fed409776edd11790c596ea0848984c7 |
15.3 MB | Download |
|
Images_LR.zip
md5:2329258d74d54600628b8652a0e42672 |
95.0 MB | Download |
|
LR_split_test_answers.json
md5:f925d70eb74bb4094966670cb4c2f840 |
1.9 MB | Download |
|
LR_split_test_images.json
md5:4a5ae90a5686bbcffd1d7ec06ddbb692 |
123.3 kB | Download |
|
LR_split_test_questions.json
md5:9bddc53d7399a43378f743ec0ff1f95f |
2.7 MB | Download |
|
LR_split_train_answers.json
md5:a5ff787f9977b0050b9bbf4e32bbb533 |
7.4 MB | Download |
|
LR_split_train_images.json
md5:7d1e7c099c65e39b3e773578cdabe79a |
585.1 kB | Download |
|
LR_split_train_questions.json
md5:935d59a05d126496fe61c541b4ab2d55 |
11.9 MB | Download |
|
LR_split_val_answers.json
md5:61ba49ece26c989f81a9a1e2fe0d475b |
2.7 MB | Download |
|
LR_split_val_images.json
md5:7a9f267d2cd106025c45a2b68dce5351 |
123.3 kB | Download |
|
LR_split_val_questions.json
md5:67b99979ebd468330355d656bf4d6d29 |
3.5 MB | Download |
| All versions | This version | |
|---|---|---|
| Views | 349 | 349 |
| Downloads | 926 | 926 |
| Data volume | 15.4 GB | 15.4 GB |
| Unique views | 286 | 286 |
| Unique downloads | 135 | 135 |
- Publication date:
- March 10, 2022
- DOI:
-
- Keyword(s):
- Remote sensing Sentinel-2 Visual Question Answering
- Related identifiers:
- Documented by
- 10.1109/TGRS.2020.2988782 (Journal article)
- License (for files):
- Creative Commons Attribution 4.0 International