Weakly Supervised Object Detection for Remote Sensing Images: A Survey
The rapid development of remote sensing technologies and the availability of many satellite and aerial sensors have boosted the collection of large volumes of high-resolution images, promoting progress in a wide range of applications. As a consequence, Object detection (OD) in aerial images has gain...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/21/5362 |
| _version_ | 1797466619442626560 |
|---|---|
| author | Corrado Fasana Samuele Pasini Federico Milani Piero Fraternali |
| author_facet | Corrado Fasana Samuele Pasini Federico Milani Piero Fraternali |
| author_sort | Corrado Fasana |
| collection | DOAJ |
| description | The rapid development of remote sensing technologies and the availability of many satellite and aerial sensors have boosted the collection of large volumes of high-resolution images, promoting progress in a wide range of applications. As a consequence, Object detection (OD) in aerial images has gained much interest in the last few years. However, the development of object detectors requires a massive amount of carefully labeled data. Since annotating datasets is very time-consuming and may require expert knowledge, a consistent number of weakly supervised object localization (WSOL) and detection (WSOD) methods have been developed. These approaches exploit only coarse-grained metadata, typically whole image labels, to train object detectors. However, many challenges remain open due to the missing location information in the training process of WSOD approaches and to the complexity of remote sensing images. Furthermore, methods studied for natural images may not be directly applicable to remote sensing images (RSI) and may require carefully designed adaptations. This work provides a comprehensive survey of the recent achievements of remote sensing weakly supervised object detection (RSWSOD). An analysis of the challenges related to RSWSOD is presented, the advanced techniques developed to improve WSOD are summarized, the available benchmarking datasets are described and a discussion of future directions of RSWSOD research is provided. |
| first_indexed | 2024-03-09T18:42:15Z |
| format | Article |
| id | doaj.art-9b1b127718c446b98c7c753c61790284 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:42:15Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-9b1b127718c446b98c7c753c617902842023-11-24T06:37:58ZengMDPI AGRemote Sensing2072-42922022-10-011421536210.3390/rs14215362Weakly Supervised Object Detection for Remote Sensing Images: A SurveyCorrado Fasana0Samuele Pasini1Federico Milani2Piero Fraternali3Department of Electronics Information and Bioengineering, Politecnico di Milano, 20133 Milano, ItalyDepartment of Electronics Information and Bioengineering, Politecnico di Milano, 20133 Milano, ItalyDepartment of Electronics Information and Bioengineering, Politecnico di Milano, 20133 Milano, ItalyDepartment of Electronics Information and Bioengineering, Politecnico di Milano, 20133 Milano, ItalyThe rapid development of remote sensing technologies and the availability of many satellite and aerial sensors have boosted the collection of large volumes of high-resolution images, promoting progress in a wide range of applications. As a consequence, Object detection (OD) in aerial images has gained much interest in the last few years. However, the development of object detectors requires a massive amount of carefully labeled data. Since annotating datasets is very time-consuming and may require expert knowledge, a consistent number of weakly supervised object localization (WSOL) and detection (WSOD) methods have been developed. These approaches exploit only coarse-grained metadata, typically whole image labels, to train object detectors. However, many challenges remain open due to the missing location information in the training process of WSOD approaches and to the complexity of remote sensing images. Furthermore, methods studied for natural images may not be directly applicable to remote sensing images (RSI) and may require carefully designed adaptations. This work provides a comprehensive survey of the recent achievements of remote sensing weakly supervised object detection (RSWSOD). An analysis of the challenges related to RSWSOD is presented, the advanced techniques developed to improve WSOD are summarized, the available benchmarking datasets are described and a discussion of future directions of RSWSOD research is provided.https://www.mdpi.com/2072-4292/14/21/5362weakly supervised object detection (WSOD)remote sensingsatellite imagesaerial imagerysurvey |
| spellingShingle | Corrado Fasana Samuele Pasini Federico Milani Piero Fraternali Weakly Supervised Object Detection for Remote Sensing Images: A Survey Remote Sensing weakly supervised object detection (WSOD) remote sensing satellite images aerial imagery survey |
| title | Weakly Supervised Object Detection for Remote Sensing Images: A Survey |
| title_full | Weakly Supervised Object Detection for Remote Sensing Images: A Survey |
| title_fullStr | Weakly Supervised Object Detection for Remote Sensing Images: A Survey |
| title_full_unstemmed | Weakly Supervised Object Detection for Remote Sensing Images: A Survey |
| title_short | Weakly Supervised Object Detection for Remote Sensing Images: A Survey |
| title_sort | weakly supervised object detection for remote sensing images a survey |
| topic | weakly supervised object detection (WSOD) remote sensing satellite images aerial imagery survey |
| url | https://www.mdpi.com/2072-4292/14/21/5362 |
| work_keys_str_mv | AT corradofasana weaklysupervisedobjectdetectionforremotesensingimagesasurvey AT samuelepasini weaklysupervisedobjectdetectionforremotesensingimagesasurvey AT federicomilani weaklysupervisedobjectdetectionforremotesensingimagesasurvey AT pierofraternali weaklysupervisedobjectdetectionforremotesensingimagesasurvey |