用深度网络融合多帧图像，提升高超音速平台的鲁棒导航能力

Deep Learning-Based Robust Optical Guidance for Hypersonic Platforms

• 通过深度网络编码多帧场景图像实现导航
• 在双模场景（如有雪/无雪）下表现更稳定
• 适合高超音速飞行器等极端环境导航

基于传感器的制导对远程平台至关重要。为突破传统参考图像框架下图像配准的结构限制，本文提出将场景的一组图像堆叠输入深度网络进行编码。实验表明，采用图像堆叠方式在双模场景（如场景可能有雪或无雪）中具有显著优势，提升了制导系统的鲁棒性。

原文摘要 · Abstract (English)

Sensor-based guidance is required for long-range platforms. To bypass the structural limitation of classical registration on reference image framework, we offer in this paper to encode a stack of images of the scene into a deep network. Relying on a stack is showed to be relevant on bimodal scene (e.g. when the scene can or can not be snowy).

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。