轻量级模型实现航天器多任务感知，精度高且适合星上部署。
Segmentation-based Detection for Efficient Multi-Task Spacecraft Perception
- 用MobileNetV3+U-Net结构，通过组件掩码合并实现检测
- 分类、检测、分割任务得分分别达1.0000、0.9788、0.8917
- 适合资源受限的星上视觉系统，兼顾效率与精度
基于视觉的感知对空间态势感知和自主在轨操作（如交会对接、服务与导航）至关重要。然而，该领域进展受限于标注空间图像稀缺，以及光照剧烈变化、信噪比低、对比度高等挑战。我们针对SPARK 2026挑战赛第一赛道，提出一个单模型解决方案，实现多类航天器的分类、检测与细粒度部件分割。方法采用MobileNetV3编码器与U-Net风格解码器结合，兼顾计算效率与密集预测精度。在单航天器场景下，检测通过预测部件掩码的并集解析得出，无需独立的边界框回归头。最终模型在排行榜上总得分为0.9482，其中分类0.9788、检测1.0000、分割0.8917。该方法在SPARK 2026挑战赛中排名第二，证明轻量级编码器-解码器架构可为实际星上视觉系统提供强大多任务性能。
原文摘要 · Abstract (English)
Vision-based perception is fundamental to Space Situational Awareness and autonomous on-orbit operations such as rendezvous, docking, servicing, and navigation. However, progress in this area is limited by the scarcity of annotated space imagery and by challenging visual-domain characteristics including severe illumination changes, low signal-to-noise ratio, and high contrast. We address Stream 1 of the SPARK 2026 Challenge, which requires a single model for spacecraft classification, detection, and fine-grained component segmentation across multiple target types. We propose a compact architecture that integrates a MobileNetV3 encoder with a U-Net-style decoder, combining computational efficiency with accurate dense prediction. Detection is derived analytically from the union of predicted component masks, avoiding a separate bounding-box regression head in the single-spacecraft setting. Our method achieved an overall leaderboard score of 0.9482, with task-specific scores of 1.0000 in classification, 0.9788 in detection, and 0.8917 in segmentation. The proposed approach ranked second overall in the SPARK 2026 Challenge, demonstrating that lightweight encoder-decoder architectures can deliver strong multi-task performance for practical onboard space vision systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。