arXiv：cs.AI· Thomas Goudemant, Aur\'elien Bobey, Omar Hlimi, Marjorie Bellizzi·· 3 小时前
基于 AI 的星载海事目标检测：在 Versal 嵌入式硬件上实现地球观测载荷数据缩减
AI-Based On-Board Maritime Object Detection for Earth Observation Payload Data Reduction on Versal Embedded Hardware
AI 导读
研究将 YOLOX-S 检测器量化部署到 Versal VC1902 的 DPU 上，用于星载船只检测以实现内容驱动的数据下传，单景处理耗时数秒且检测质量损失有限。团队基于 68 幅 Maxar 标注场景、43 类船只构建数据集，并提出多种下传模式。在密集港口与海岸场景中，tiles 模式以 29% 的数据量保留 98% 的船只，crops 模式则以 3% 的数据量保留 83%。
正文
Abstract:Very-high-resolution Earth-observation satellites acquire more data than they can store and downlink, while in maritime surveillance the vessels cover a tiny fraction of each scene. We study onboard vessel detection as a way to select what is downlinked, which reduces the data according to its content rather than coding every pixel; it is complementary to conventional onboard compression. The work follows three axes. (i) Data and algorithm: a controlled dataset is generated from 68 annotated Maxar scenes with 43 vessel classes, and a YOLOX-S detector is trained on it. (ii) Embedded deployment: the detector is quantized and deployed on the DPU of a Versal VC1902, with a limited loss of detection quality and a processing time of a few seconds per scene. (iii) Data reduction: we propose several downlink modes, from metadata only (box, class and score of each detection) to image crops around vessels, tiles holding detections, or the whole scene with a degraded background, and estimate from the measured detection errors the trade-off each offers between the vessels kept and the volume downlinked. On our dense harbor and coastal scenes, tiles keep 98% of the vessels with 29% of the scene volume, and crops 83% with 3%.
| Comments: | 8 pages. Accepted at the 10th On-Board Payload Data Compression Workshop (OBPDC 2026), Barcelona, Spain, 12-14 October 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| ACM classes: | I.4.8; I.2.10; C.3 |
| Cite as: | arXiv:2610.12182 [cs.CV] |
| (or arXiv:2610.12182v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12182 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.5281/zenodo.23242463
DOI(s) linking to related resources |
Submission history
From: Thomas Goudemant [view email]
[v1]
Thu, 8 Oct 2026 15:48:00 UTC (1,106 KB)
来源：arXiv：cs.AI · arxiv.org