Remote Sensing Object Detection in the Deep Learning Era—A Review
Given the large volume of remote sensing images collected daily, automatic object detection and segmentation have been a consistent need in Earth observation (EO). However, objects of interest vary in shape, size, appearance, and reflecting properties. This is not only reflected by the fact that the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/2/327 |
| _version_ | 1827371182524989440 |
|---|---|
| author | Shengxi Gui Shuang Song Rongjun Qin Yang Tang |
| author_facet | Shengxi Gui Shuang Song Rongjun Qin Yang Tang |
| author_sort | Shengxi Gui |
| collection | DOAJ |
| description | Given the large volume of remote sensing images collected daily, automatic object detection and segmentation have been a consistent need in Earth observation (EO). However, objects of interest vary in shape, size, appearance, and reflecting properties. This is not only reflected by the fact that these objects exhibit differences due to their geographical diversity but also by the fact that these objects appear differently in images collected from different sensors (optical and radar) and platforms (satellite, aerial, and unmanned aerial vehicles (UAV)). Although there exists a plethora of object detection methods in the area of remote sensing, given the very fast development of prevalent deep learning methods, there is still a lack of recent updates for object detection methods. In this paper, we aim to provide an update that informs researchers about the recent development of object detection methods and their close sibling in the deep learning era, instance segmentation. The integration of these methods will cover approaches to data at different scales and modalities, such as optical, synthetic aperture radar (SAR) images, and digital surface models (DSM). Specific emphasis will be placed on approaches addressing data and label limitations in this deep learning era. Further, we survey examples of remote sensing applications that benefited from automatic object detection and discuss future trends of the automatic object detection in EO. |
| first_indexed | 2024-03-08T10:35:33Z |
| format | Article |
| id | doaj.art-8b4037a291bc49a48a988940ca8d1ea7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T10:35:33Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8b4037a291bc49a48a988940ca8d1ea72024-01-26T18:18:20ZengMDPI AGRemote Sensing2072-42922024-01-0116232710.3390/rs16020327Remote Sensing Object Detection in the Deep Learning Era—A ReviewShengxi Gui0Shuang Song1Rongjun Qin2Yang Tang3Geospatial Data Analytics Laboratory, The Ohio State University, Columbus, OH 43210, USAGeospatial Data Analytics Laboratory, The Ohio State University, Columbus, OH 43210, USAGeospatial Data Analytics Laboratory, The Ohio State University, Columbus, OH 43210, USAGeospatial Data Analytics Laboratory, The Ohio State University, Columbus, OH 43210, USAGiven the large volume of remote sensing images collected daily, automatic object detection and segmentation have been a consistent need in Earth observation (EO). However, objects of interest vary in shape, size, appearance, and reflecting properties. This is not only reflected by the fact that these objects exhibit differences due to their geographical diversity but also by the fact that these objects appear differently in images collected from different sensors (optical and radar) and platforms (satellite, aerial, and unmanned aerial vehicles (UAV)). Although there exists a plethora of object detection methods in the area of remote sensing, given the very fast development of prevalent deep learning methods, there is still a lack of recent updates for object detection methods. In this paper, we aim to provide an update that informs researchers about the recent development of object detection methods and their close sibling in the deep learning era, instance segmentation. The integration of these methods will cover approaches to data at different scales and modalities, such as optical, synthetic aperture radar (SAR) images, and digital surface models (DSM). Specific emphasis will be placed on approaches addressing data and label limitations in this deep learning era. Further, we survey examples of remote sensing applications that benefited from automatic object detection and discuss future trends of the automatic object detection in EO.https://www.mdpi.com/2072-4292/16/2/327object detectioninstance segmentationpanoptic segmentationmultispectralSARmulti-modality |
| spellingShingle | Shengxi Gui Shuang Song Rongjun Qin Yang Tang Remote Sensing Object Detection in the Deep Learning Era—A Review Remote Sensing object detection instance segmentation panoptic segmentation multispectral SAR multi-modality |
| title | Remote Sensing Object Detection in the Deep Learning Era—A Review |
| title_full | Remote Sensing Object Detection in the Deep Learning Era—A Review |
| title_fullStr | Remote Sensing Object Detection in the Deep Learning Era—A Review |
| title_full_unstemmed | Remote Sensing Object Detection in the Deep Learning Era—A Review |
| title_short | Remote Sensing Object Detection in the Deep Learning Era—A Review |
| title_sort | remote sensing object detection in the deep learning era a review |
| topic | object detection instance segmentation panoptic segmentation multispectral SAR multi-modality |
| url | https://www.mdpi.com/2072-4292/16/2/327 |
| work_keys_str_mv | AT shengxigui remotesensingobjectdetectioninthedeeplearningeraareview AT shuangsong remotesensingobjectdetectioninthedeeplearningeraareview AT rongjunqin remotesensingobjectdetectioninthedeeplearningeraareview AT yangtang remotesensingobjectdetectioninthedeeplearningeraareview |