A Dual-Input Moving Object Detection Method in Remote Sensing Image Sequences via Temporal Semantics
Moving object detection in remote sensing image sequences has been widely used in military and civilian fields. However, the complex background of remote sensing images and the small sizes of moving objects bring great difficulties for effective detection. To solve this problem, we propose a real-ti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/9/2230 |
| _version_ | 1797601796167827456 |
|---|---|
| author | Bo Wang Jinghong Liu Shengjie Zhu Fang Xu Chenglong Liu |
| author_facet | Bo Wang Jinghong Liu Shengjie Zhu Fang Xu Chenglong Liu |
| author_sort | Bo Wang |
| collection | DOAJ |
| description | Moving object detection in remote sensing image sequences has been widely used in military and civilian fields. However, the complex background of remote sensing images and the small sizes of moving objects bring great difficulties for effective detection. To solve this problem, we propose a real-time moving object detection method for remote sensing image sequences. This method works by fusing the semantic information from a single image extracted by the object detection branch with the motion information of multiple frames extracted by the motion detection branch. Specifically, in the motion detection branch, we design a motion feature enhancement module (MFE) to improve the interframe motion information. Then, we design a Motion Information Extraction network (MIE) to extract motion information. Finally, the moving object information is directly output by fusing the motion and semantic information extracted by the object detection branch. Based on the experimental results of the two datasets, the proposed method achieves an accuracy rate of 93.21%, a recall rate of 92.72%, an average frame rate of 25.25 frames (fps), and a performance of 96.71% in terms of AP@0.5. The performance of the proposed method is better than that of other methods, and the overall detection effect is better; therefore, it meets the needs of the detection task. |
| first_indexed | 2024-03-11T04:08:57Z |
| format | Article |
| id | doaj.art-397bca3cd5284abf9f10620f49967234 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:08:57Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-397bca3cd5284abf9f10620f499672342023-11-17T23:37:17ZengMDPI AGRemote Sensing2072-42922023-04-01159223010.3390/rs15092230A Dual-Input Moving Object Detection Method in Remote Sensing Image Sequences via Temporal SemanticsBo Wang0Jinghong Liu1Shengjie Zhu2Fang Xu3Chenglong Liu4Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaMoving object detection in remote sensing image sequences has been widely used in military and civilian fields. However, the complex background of remote sensing images and the small sizes of moving objects bring great difficulties for effective detection. To solve this problem, we propose a real-time moving object detection method for remote sensing image sequences. This method works by fusing the semantic information from a single image extracted by the object detection branch with the motion information of multiple frames extracted by the motion detection branch. Specifically, in the motion detection branch, we design a motion feature enhancement module (MFE) to improve the interframe motion information. Then, we design a Motion Information Extraction network (MIE) to extract motion information. Finally, the moving object information is directly output by fusing the motion and semantic information extracted by the object detection branch. Based on the experimental results of the two datasets, the proposed method achieves an accuracy rate of 93.21%, a recall rate of 92.72%, an average frame rate of 25.25 frames (fps), and a performance of 96.71% in terms of AP@0.5. The performance of the proposed method is better than that of other methods, and the overall detection effect is better; therefore, it meets the needs of the detection task.https://www.mdpi.com/2072-4292/15/9/2230remote sensing image sequencesmoving cameramoving object detection (MOD)convolutional neural network (CNN) |
| spellingShingle | Bo Wang Jinghong Liu Shengjie Zhu Fang Xu Chenglong Liu A Dual-Input Moving Object Detection Method in Remote Sensing Image Sequences via Temporal Semantics Remote Sensing remote sensing image sequences moving camera moving object detection (MOD) convolutional neural network (CNN) |
| title | A Dual-Input Moving Object Detection Method in Remote Sensing Image Sequences via Temporal Semantics |
| title_full | A Dual-Input Moving Object Detection Method in Remote Sensing Image Sequences via Temporal Semantics |
| title_fullStr | A Dual-Input Moving Object Detection Method in Remote Sensing Image Sequences via Temporal Semantics |
| title_full_unstemmed | A Dual-Input Moving Object Detection Method in Remote Sensing Image Sequences via Temporal Semantics |
| title_short | A Dual-Input Moving Object Detection Method in Remote Sensing Image Sequences via Temporal Semantics |
| title_sort | dual input moving object detection method in remote sensing image sequences via temporal semantics |
| topic | remote sensing image sequences moving camera moving object detection (MOD) convolutional neural network (CNN) |
| url | https://www.mdpi.com/2072-4292/15/9/2230 |
| work_keys_str_mv | AT bowang adualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics AT jinghongliu adualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics AT shengjiezhu adualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics AT fangxu adualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics AT chenglongliu adualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics AT bowang dualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics AT jinghongliu dualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics AT shengjiezhu dualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics AT fangxu dualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics AT chenglongliu dualinputmovingobjectdetectionmethodinremotesensingimagesequencesviatemporalsemantics |