Coarse-to-Fine Deep Metric Learning for Remote Sensing Image Retrieval
Remote sensing image retrieval (RSIR) is the process of searching for identical areas by investigating the similarities between a query image and the database images. RSIR is a challenging task owing to the time difference, viewpoint, and coverage area depending on the shooting circumstance, resulti...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/2/219 |
| _version_ | 1828143535539355648 |
|---|---|
| author | Min-Sub Yun Woo-Jeoung Nam Seong-Whan Lee |
| author_facet | Min-Sub Yun Woo-Jeoung Nam Seong-Whan Lee |
| author_sort | Min-Sub Yun |
| collection | DOAJ |
| description | Remote sensing image retrieval (RSIR) is the process of searching for identical areas by investigating the similarities between a query image and the database images. RSIR is a challenging task owing to the time difference, viewpoint, and coverage area depending on the shooting circumstance, resulting in variations in the image contents. In this paper, we propose a novel method based on a coarse-to-fine strategy, which makes a deep network more robust to the variations in remote sensing images. Moreover, we propose a new triangular loss function to consider the whole relation within the tuple. This loss function improves the retrieval performance and demonstrates better performance in terms of learning the detailed information in complex remote sensing images. To verify our methods, we experimented with the Google Earth South Korea dataset, which contains 40,000 images, using the evaluation metric Recall@n. In all experiments, we obtained better performance results than those of the existing retrieval training methods. Our source code and Google Earth South Korea dataset are available online. |
| first_indexed | 2024-04-11T19:58:48Z |
| format | Article |
| id | doaj.art-2595ee84cd9b474fb97d865ee949bb25 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T19:58:48Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2595ee84cd9b474fb97d865ee949bb252022-12-22T04:05:42ZengMDPI AGRemote Sensing2072-42922020-01-0112221910.3390/rs12020219rs12020219Coarse-to-Fine Deep Metric Learning for Remote Sensing Image RetrievalMin-Sub Yun0Woo-Jeoung Nam1Seong-Whan Lee2Department of Brain and Cognitive Engineering, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, KoreaDepartment of Computer and Radio Communication Engineering, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, KoreaDepartment of Brain and Cognitive Engineering, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, KoreaRemote sensing image retrieval (RSIR) is the process of searching for identical areas by investigating the similarities between a query image and the database images. RSIR is a challenging task owing to the time difference, viewpoint, and coverage area depending on the shooting circumstance, resulting in variations in the image contents. In this paper, we propose a novel method based on a coarse-to-fine strategy, which makes a deep network more robust to the variations in remote sensing images. Moreover, we propose a new triangular loss function to consider the whole relation within the tuple. This loss function improves the retrieval performance and demonstrates better performance in terms of learning the detailed information in complex remote sensing images. To verify our methods, we experimented with the Google Earth South Korea dataset, which contains 40,000 images, using the evaluation metric Recall@n. In all experiments, we obtained better performance results than those of the existing retrieval training methods. Our source code and Google Earth South Korea dataset are available online.https://www.mdpi.com/2072-4292/12/2/219remote sensing image retrieval (rsir)deep metric learningconvolutional neural networkscontents based image retrieval (cbir)deep learning |
| spellingShingle | Min-Sub Yun Woo-Jeoung Nam Seong-Whan Lee Coarse-to-Fine Deep Metric Learning for Remote Sensing Image Retrieval Remote Sensing remote sensing image retrieval (rsir) deep metric learning convolutional neural networks contents based image retrieval (cbir) deep learning |
| title | Coarse-to-Fine Deep Metric Learning for Remote Sensing Image Retrieval |
| title_full | Coarse-to-Fine Deep Metric Learning for Remote Sensing Image Retrieval |
| title_fullStr | Coarse-to-Fine Deep Metric Learning for Remote Sensing Image Retrieval |
| title_full_unstemmed | Coarse-to-Fine Deep Metric Learning for Remote Sensing Image Retrieval |
| title_short | Coarse-to-Fine Deep Metric Learning for Remote Sensing Image Retrieval |
| title_sort | coarse to fine deep metric learning for remote sensing image retrieval |
| topic | remote sensing image retrieval (rsir) deep metric learning convolutional neural networks contents based image retrieval (cbir) deep learning |
| url | https://www.mdpi.com/2072-4292/12/2/219 |
| work_keys_str_mv | AT minsubyun coarsetofinedeepmetriclearningforremotesensingimageretrieval AT woojeoungnam coarsetofinedeepmetriclearningforremotesensingimageretrieval AT seongwhanlee coarsetofinedeepmetriclearningforremotesensingimageretrieval |