V-RSIR: A WEB-BASED TOOL AND BENCHMARK DATASET FOR REMOTE SENSING IMAGE RETRIEVAL
Benchmark datasets play an important role in evaluating remote sensing image retrieval methods. Current benchmark datasets are mostly collected through the Google Map API or other desktop tools. However, the Google Map API requires the users to have programming skills and other collection tools are...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2019-06-01
|
Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W13/1545/2019/isprs-archives-XLII-2-W13-1545-2019.pdf |
id |
doaj-93546cf5913843a3a7b57c3de0cb54e1 |
---|---|
record_format |
Article |
spelling |
doaj-93546cf5913843a3a7b57c3de0cb54e12020-11-25T01:49:48ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342019-06-01XLII-2-W131545154910.5194/isprs-archives-XLII-2-W13-1545-2019V-RSIR: A WEB-BASED TOOL AND BENCHMARK DATASET FOR REMOTE SENSING IMAGE RETRIEVALD. Hou0D. Hou1H. Xing2School of Geosciences and Info-Physics, Central South University, Changsha, Hunan, ChinaCollege of Geography and Environment, Shandong Normal University, Jinan, Shandong, ChinaSchool of Surveying and Geo-informatics, Shandong Jianzhu University, Jinan, Shandong, ChinaBenchmark datasets play an important role in evaluating remote sensing image retrieval methods. Current benchmark datasets are mostly collected through the Google Map API or other desktop tools. However, the Google Map API requires the users to have programming skills and other collection tools are not publicly available, which may hinder the development of new benchmark datasets. This paper develops an open access web-based tool V-RSIR to help users generating new benchmark datasets with volunteers for remote sensing image retrieval. Using this tool, a new benchmark dataset V-RSIR that contains 38 classes with at least 1500 images per class is created by 32 volunteers. A handcrafted low-level feature method and a deep learning high-level feature method are used to test the dataset. The evaluation results are consistent with our perception. This shows that the tool can help users effectively creating benchmark datasets for RSIR.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W13/1545/2019/isprs-archives-XLII-2-W13-1545-2019.pdf |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
D. Hou D. Hou H. Xing |
spellingShingle |
D. Hou D. Hou H. Xing V-RSIR: A WEB-BASED TOOL AND BENCHMARK DATASET FOR REMOTE SENSING IMAGE RETRIEVAL The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
author_facet |
D. Hou D. Hou H. Xing |
author_sort |
D. Hou |
title |
V-RSIR: A WEB-BASED TOOL AND BENCHMARK DATASET FOR REMOTE SENSING IMAGE RETRIEVAL |
title_short |
V-RSIR: A WEB-BASED TOOL AND BENCHMARK DATASET FOR REMOTE SENSING IMAGE RETRIEVAL |
title_full |
V-RSIR: A WEB-BASED TOOL AND BENCHMARK DATASET FOR REMOTE SENSING IMAGE RETRIEVAL |
title_fullStr |
V-RSIR: A WEB-BASED TOOL AND BENCHMARK DATASET FOR REMOTE SENSING IMAGE RETRIEVAL |
title_full_unstemmed |
V-RSIR: A WEB-BASED TOOL AND BENCHMARK DATASET FOR REMOTE SENSING IMAGE RETRIEVAL |
title_sort |
v-rsir: a web-based tool and benchmark dataset for remote sensing image retrieval |
publisher |
Copernicus Publications |
series |
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
issn |
1682-1750 2194-9034 |
publishDate |
2019-06-01 |
description |
Benchmark datasets play an important role in evaluating remote sensing image retrieval methods. Current benchmark datasets are mostly collected through the Google Map API or other desktop tools. However, the Google Map API requires the users to have programming skills and other collection tools are not publicly available, which may hinder the development of new benchmark datasets. This paper develops an open access web-based tool V-RSIR to help users generating new benchmark datasets with volunteers for remote sensing image retrieval. Using this tool, a new benchmark dataset V-RSIR that contains 38 classes with at least 1500 images per class is created by 32 volunteers. A handcrafted low-level feature method and a deep learning high-level feature method are used to test the dataset. The evaluation results are consistent with our perception. This shows that the tool can help users effectively creating benchmark datasets for RSIR. |
url |
https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W13/1545/2019/isprs-archives-XLII-2-W13-1545-2019.pdf |
work_keys_str_mv |
AT dhou vrsirawebbasedtoolandbenchmarkdatasetforremotesensingimageretrieval AT dhou vrsirawebbasedtoolandbenchmarkdatasetforremotesensingimageretrieval AT hxing vrsirawebbasedtoolandbenchmarkdatasetforremotesensingimageretrieval |
_version_ |
1725004869402624000 |