LEGNet: A Lightweight Edge-Gaussian Network for Low-Quality Remote Sensing Image Object Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908608059408384 |
|---|---|
| author | Lu, Wei Chen, Si-Bao Li, Hui-Dong Shu, Qing-Ling Ding, Chris H. Q. Tang, Jin Luo, Bin |
| author_facet | Lu, Wei Chen, Si-Bao Li, Hui-Dong Shu, Qing-Ling Ding, Chris H. Q. Tang, Jin Luo, Bin |
| contents | Remote sensing object detection (RSOD) often suffers from degradations such as low spatial resolution, sensor noise, motion blur, and adverse illumination. These factors diminish feature distinctiveness, leading to ambiguous object representations and inadequate foreground-background separation. Existing RSOD methods exhibit limitations in robust detection of low-quality objects. To address these pressing challenges, we introduce LEGNet, a lightweight backbone network featuring a novel Edge-Gaussian Aggregation (EGA) module specifically engineered to enhance feature representation derived from low-quality remote sensing images. EGA module integrates: (a) orientation-aware Scharr filters to sharpen crucial edge details often lost in low-contrast or blurred objects, and (b) Gaussian-prior-based feature refinement to suppress noise and regularize ambiguous feature responses, enhancing foreground saliency under challenging conditions. EGA module alleviates prevalent problems in reduced contrast, structural discontinuities, and ambiguous feature responses prevalent in degraded images, effectively improving model robustness while maintaining computational efficiency. Comprehensive evaluations across five benchmarks (DOTA-v1.0, v1.5, DIOR-R, FAIR1M-v1.0, and VisDrone2019) demonstrate that LEGNet achieves state-of-the-art performance, particularly in detecting low-quality objects.The code is available at https://github.com/AeroVILab-AHU/LEGNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14012 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LEGNet: A Lightweight Edge-Gaussian Network for Low-Quality Remote Sensing Image Object Detection Lu, Wei Chen, Si-Bao Li, Hui-Dong Shu, Qing-Ling Ding, Chris H. Q. Tang, Jin Luo, Bin Computer Vision and Pattern Recognition Remote sensing object detection (RSOD) often suffers from degradations such as low spatial resolution, sensor noise, motion blur, and adverse illumination. These factors diminish feature distinctiveness, leading to ambiguous object representations and inadequate foreground-background separation. Existing RSOD methods exhibit limitations in robust detection of low-quality objects. To address these pressing challenges, we introduce LEGNet, a lightweight backbone network featuring a novel Edge-Gaussian Aggregation (EGA) module specifically engineered to enhance feature representation derived from low-quality remote sensing images. EGA module integrates: (a) orientation-aware Scharr filters to sharpen crucial edge details often lost in low-contrast or blurred objects, and (b) Gaussian-prior-based feature refinement to suppress noise and regularize ambiguous feature responses, enhancing foreground saliency under challenging conditions. EGA module alleviates prevalent problems in reduced contrast, structural discontinuities, and ambiguous feature responses prevalent in degraded images, effectively improving model robustness while maintaining computational efficiency. Comprehensive evaluations across five benchmarks (DOTA-v1.0, v1.5, DIOR-R, FAIR1M-v1.0, and VisDrone2019) demonstrate that LEGNet achieves state-of-the-art performance, particularly in detecting low-quality objects.The code is available at https://github.com/AeroVILab-AHU/LEGNet. |
| title | LEGNet: A Lightweight Edge-Gaussian Network for Low-Quality Remote Sensing Image Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.14012 |