An Efficient Feature Pyramid Network for Object Detection in Remote Sensing Imagery
Scale diversity, small target, and power limitation have made remote sensing imagery a challenging field in object detection on satellites. Aiming at the aspects of scale diversity and small target, this paper provides a novel feature pyramid network with Adaptive Residual Spatial Bi-Fusion (ARSF) a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9091190/ |
| _version_ | 1818618501866192896 |
|---|---|
| author | Fang Qingyun Zhang Lin Wang Zhaokui |
| author_facet | Fang Qingyun Zhang Lin Wang Zhaokui |
| author_sort | Fang Qingyun |
| collection | DOAJ |
| description | Scale diversity, small target, and power limitation have made remote sensing imagery a challenging field in object detection on satellites. Aiming at the aspects of scale diversity and small target, this paper provides a novel feature pyramid network with Adaptive Residual Spatial Bi-Fusion (ARSF) as a solution. ARSF nets introduce a robust fusion of multi-scale semantic information and fine spatial details. A spatial feature fusion module designed in networks with ARSF adapts to object size variation by learning the most crucial feature maps. Comparing to the original feature pyramid network, a shorter critical path for information transmission is formed in our method. Experiments show that a validation instance of YOLOv3-ARSF can achieve a state-of-the-art performance of 85.8 mAP on the NWPU-VHR10 dataset. YOLOv3-ARSF only 3MB larger than YOLOv3 but far exceeds YOLOv3 by 2.3% mAP, which shows our ARSF is efficient. As for the last challenge, two lightweight versions, ARSF(lite) and ARSF(lite+) are also validated for future research of online object detection on satellites in aerospace engineering. Visualizations and details are provided for a more comprehensive understanding. |
| first_indexed | 2024-12-16T17:22:36Z |
| format | Article |
| id | doaj.art-5042c9c789c14873a9d14ee82789e95d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T17:22:36Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5042c9c789c14873a9d14ee82789e95d2022-12-21T22:23:08ZengIEEEIEEE Access2169-35362020-01-018930589306810.1109/ACCESS.2020.29939989091190An Efficient Feature Pyramid Network for Object Detection in Remote Sensing ImageryFang Qingyun0https://orcid.org/0000-0002-7858-1525Zhang Lin1Wang Zhaokui2School of Aerospace Engineering, Tsinghua University, Beijing, ChinaDepartment of Aerospace Engineering and Engineering Mechanics, University of Cincinnati, Cincinnati, OH, USASchool of Aerospace Engineering, Tsinghua University, Beijing, ChinaScale diversity, small target, and power limitation have made remote sensing imagery a challenging field in object detection on satellites. Aiming at the aspects of scale diversity and small target, this paper provides a novel feature pyramid network with Adaptive Residual Spatial Bi-Fusion (ARSF) as a solution. ARSF nets introduce a robust fusion of multi-scale semantic information and fine spatial details. A spatial feature fusion module designed in networks with ARSF adapts to object size variation by learning the most crucial feature maps. Comparing to the original feature pyramid network, a shorter critical path for information transmission is formed in our method. Experiments show that a validation instance of YOLOv3-ARSF can achieve a state-of-the-art performance of 85.8 mAP on the NWPU-VHR10 dataset. YOLOv3-ARSF only 3MB larger than YOLOv3 but far exceeds YOLOv3 by 2.3% mAP, which shows our ARSF is efficient. As for the last challenge, two lightweight versions, ARSF(lite) and ARSF(lite+) are also validated for future research of online object detection on satellites in aerospace engineering. Visualizations and details are provided for a more comprehensive understanding.https://ieeexplore.ieee.org/document/9091190/Computer visionobject detectionremote sensingsatellitesaerospace engineering |
| spellingShingle | Fang Qingyun Zhang Lin Wang Zhaokui An Efficient Feature Pyramid Network for Object Detection in Remote Sensing Imagery IEEE Access Computer vision object detection remote sensing satellites aerospace engineering |
| title | An Efficient Feature Pyramid Network for Object Detection in Remote Sensing Imagery |
| title_full | An Efficient Feature Pyramid Network for Object Detection in Remote Sensing Imagery |
| title_fullStr | An Efficient Feature Pyramid Network for Object Detection in Remote Sensing Imagery |
| title_full_unstemmed | An Efficient Feature Pyramid Network for Object Detection in Remote Sensing Imagery |
| title_short | An Efficient Feature Pyramid Network for Object Detection in Remote Sensing Imagery |
| title_sort | efficient feature pyramid network for object detection in remote sensing imagery |
| topic | Computer vision object detection remote sensing satellites aerospace engineering |
| url | https://ieeexplore.ieee.org/document/9091190/ |
| work_keys_str_mv | AT fangqingyun anefficientfeaturepyramidnetworkforobjectdetectioninremotesensingimagery AT zhanglin anefficientfeaturepyramidnetworkforobjectdetectioninremotesensingimagery AT wangzhaokui anefficientfeaturepyramidnetworkforobjectdetectioninremotesensingimagery AT fangqingyun efficientfeaturepyramidnetworkforobjectdetectioninremotesensingimagery AT zhanglin efficientfeaturepyramidnetworkforobjectdetectioninremotesensingimagery AT wangzhaokui efficientfeaturepyramidnetworkforobjectdetectioninremotesensingimagery |