研究人员开发了一种基于图的语义校准网络（GSCNet），以改进无人机（UAV）捕获的未对齐RGB-Thermal（RGBT）图像的语义分割。该网络解决了传感器数据之间的空间不对齐以及空中视角下细粒度物体之间的混淆等挑战。GSCNet包含一个特征解耦与对齐模块，用于稳健的空间校正，以及一个语义图校准模块，用于利用类别关系来提高预测精度。此外，还创建了一个新的大规模基准URTF，以促进该领域的研究。 AI
影响 引入了一种新的RGBT图像分割方法和基准，有望改善全天候无人机场景理解。
排序理由 学术论文，介绍了一种新的网络架构和基准数据集。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Fine-grained RGBT image semantic segmentation is crucial for all-weather unmanned aerial vehicle (UAV) scene understanding. However, UAV RGBT semantic segmentation faces two coupled challenges: cross-modal spatial misalignment caused by sensor parallax and platform vibration, and…
arXiv:2604.26893v1 Announce Type: new Abstract: Fine-grained RGBT image semantic segmentation is crucial for all-weather unmanned aerial vehicle (UAV) scene understanding. However, UAV RGBT semantic segmentation faces two coupled challenges: cross-modal spatial misalignment cause…
Fine-grained RGBT image semantic segmentation is crucial for all-weather unmanned aerial vehicle (UAV) scene understanding. However, UAV RGBT semantic segmentation faces two coupled challenges: cross-modal spatial misalignment caused by sensor parallax and platform vibration, and…