Uncertainty-Aware Keypoint Guidance and Fractional Fourier Feature Enhancement for Multi-Class SAR Aircraft Detection.
Saved in:
| Title: | Uncertainty-Aware Keypoint Guidance and Fractional Fourier Feature Enhancement for Multi-Class SAR Aircraft Detection. |
|---|---|
| Authors: | Qiu, Yu1,2 (AUTHOR), Zou, Bin1,2 (AUTHOR) zoubin@hit.edu.cn, Han, Fangzhou3 (AUTHOR), Zhang, Lamei1 (AUTHOR), Mallorqui, Jordi J.2 (AUTHOR) |
| Source: | Remote Sensing. Jun2026, Vol. 18 Issue 12, p1969. 38p. |
| Subjects: | Attention, Fourier transforms, Object recognition (Computer vision), Signal detection, Speckle interference |
| Abstract: | Highlights: What are the main findings? An SAR aircraft detection framework is developed to jointly exploit uncertainty-aware spatial guidance and fractional spectral feature enhancement. On the SAR-AIRcraft-1.0 dataset, the proposed method improves the Nano baseline from 0.810 to 0.867 in the mAP50 and from 0.637 to 0.655 in the mAP50:95. What are the implications of the main findings? Center-keypoint uncertainty can serve as an effective spatial attention cue for improved localization robustness without requiring additional annotations. Fractional Fourier feature modeling helps to suppress speckle noise and enhance edge- and orientation-sensitive representations in complex SAR airport scenes. Aircraft targets in SAR imagery often exhibit discrete scattering characteristics, significant variations in pose and scale, strong speckle noise in background clutter, and complex background interference, which jointly hinder stable structural feature extraction and accurate target localization. Existing detectors for SAR aircraft recognition primarily rely on bounding-box regression and classification; they do not completely exploit target structural cues, spatial attention, and frequency-domain information. To address these limitations, we propose a collaborative detection framework that integrates an uncertainty-aware keypoint-driven module (UAKM) with a fractional Fourier convolution backbone (S-FRConv). UAKM introduces a center-keypoint regression branch that jointly predicts keypoint coordinates and Laplacian scale parameters and employs a 2D Laplace negative log-likelihood loss to estimate uncertainty. The derived dense uncertainty heatmap is then used as spatial attention weights to guide distribution-based regression and multi-scale feature re-weighting, without requiring any additional annotations. S-FRConv embeds the Fractional Fourier Transform into shallow backbone layers and C2f modules, enabling joint spatial–spectral feature modeling that suppresses speckle noise and enhances edge and orientation representations. Experiments on the public SAR-AIRcraft-1.0 dataset demonstrate that the proposed method systematically improves the detection performance. For the Nano model, the overall mAP50 increases from 0.810 to 0.867, and the mAP 50:95 improves from 0.637 to 0.655 compared with the baseline, corresponding to gains of 5.7 and 1.8 percentage points, respectively. These results validate the effectiveness and generalization potential of combining uncertainty-driven spatial attention with fractional spectral feature enhancement for SAR aircraft target detection. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? An SAR aircraft detection framework is developed to jointly exploit uncertainty-aware spatial guidance and fractional spectral feature enhancement. On the SAR-AIRcraft-1.0 dataset, the proposed method improves the Nano baseline from 0.810 to 0.867 in the mAP50 and from 0.637 to 0.655 in the mAP50:95. What are the implications of the main findings? Center-keypoint uncertainty can serve as an effective spatial attention cue for improved localization robustness without requiring additional annotations. Fractional Fourier feature modeling helps to suppress speckle noise and enhance edge- and orientation-sensitive representations in complex SAR airport scenes. Aircraft targets in SAR imagery often exhibit discrete scattering characteristics, significant variations in pose and scale, strong speckle noise in background clutter, and complex background interference, which jointly hinder stable structural feature extraction and accurate target localization. Existing detectors for SAR aircraft recognition primarily rely on bounding-box regression and classification; they do not completely exploit target structural cues, spatial attention, and frequency-domain information. To address these limitations, we propose a collaborative detection framework that integrates an uncertainty-aware keypoint-driven module (UAKM) with a fractional Fourier convolution backbone (S-FRConv). UAKM introduces a center-keypoint regression branch that jointly predicts keypoint coordinates and Laplacian scale parameters and employs a 2D Laplace negative log-likelihood loss to estimate uncertainty. The derived dense uncertainty heatmap is then used as spatial attention weights to guide distribution-based regression and multi-scale feature re-weighting, without requiring any additional annotations. S-FRConv embeds the Fractional Fourier Transform into shallow backbone layers and C2f modules, enabling joint spatial–spectral feature modeling that suppresses speckle noise and enhances edge and orientation representations. Experiments on the public SAR-AIRcraft-1.0 dataset demonstrate that the proposed method systematically improves the detection performance. For the Nano model, the overall mAP50 increases from 0.810 to 0.867, and the mAP 50:95 improves from 0.637 to 0.655 compared with the baseline, corresponding to gains of 5.7 and 1.8 percentage points, respectively. These results validate the effectiveness and generalization potential of combining uncertainty-driven spatial attention with fractional spectral feature enhancement for SAR aircraft target detection. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18121969 |
