Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2503.00545 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911035703689216 |
|---|---|
| author | Lei, Yujie Sun, Wenjie Jia, Sen Li, Qingquan Zhang, Jie |
| author_facet | Lei, Yujie Sun, Wenjie Jia, Sen Li, Qingquan Zhang, Jie |
| contents | Challenges in remote sensing object detection(RSOD), such as high interclass similarity, imbalanced foreground-background distribution, and the small size of objects in remote sensing images, significantly hinder detection accuracy. Moreover, the tradeoff between model accuracy and computational complexity poses additional constraints on the application of RSOD algorithms. To address these issues, this study proposes an efficient and lightweight RSOD algorithm integrating multiscale receptive fields and foreground focus mechanism, named robust foreground weighted network(RFWNet). Specifically, we proposed a lightweight backbone network receptive field adaptive selection network (RFASNet), leveraging the rich context information of remote sensing images to enhance class separability. Additionally, we developed a foreground-background separation module(FBSM)consisting of a background redundant information filtering module (BRIFM) and a foreground information enhancement module (FIEM) to emphasize critical regions within images while filtering redundant background information. Finally, we designed a loss function, the weighted CIoU-Wasserstein loss (LWCW),which weights the IoU-based loss by using the normalized Wasserstein distance to mitigate model sensitivity to small object position deviations. The comprehensive experimental results demonstrate that RFWNet achieved 95.3% and 73.2% mean average precision (mAP) with 6.0 M parameters on the DOTA V1.0 and NWPU VHR-10 datasets, respectively, with an inference speed of 52 FPS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00545 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multiscale Receptive Fields and Foreground Focus Mechanism Lei, Yujie Sun, Wenjie Jia, Sen Li, Qingquan Zhang, Jie Computer Vision and Pattern Recognition Challenges in remote sensing object detection(RSOD), such as high interclass similarity, imbalanced foreground-background distribution, and the small size of objects in remote sensing images, significantly hinder detection accuracy. Moreover, the tradeoff between model accuracy and computational complexity poses additional constraints on the application of RSOD algorithms. To address these issues, this study proposes an efficient and lightweight RSOD algorithm integrating multiscale receptive fields and foreground focus mechanism, named robust foreground weighted network(RFWNet). Specifically, we proposed a lightweight backbone network receptive field adaptive selection network (RFASNet), leveraging the rich context information of remote sensing images to enhance class separability. Additionally, we developed a foreground-background separation module(FBSM)consisting of a background redundant information filtering module (BRIFM) and a foreground information enhancement module (FIEM) to emphasize critical regions within images while filtering redundant background information. Finally, we designed a loss function, the weighted CIoU-Wasserstein loss (LWCW),which weights the IoU-based loss by using the normalized Wasserstein distance to mitigate model sensitivity to small object position deviations. The comprehensive experimental results demonstrate that RFWNet achieved 95.3% and 73.2% mean average precision (mAP) with 6.0 M parameters on the DOTA V1.0 and NWPU VHR-10 datasets, respectively, with an inference speed of 52 FPS. |
| title | RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multiscale Receptive Fields and Foreground Focus Mechanism |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.00545 |