MSP-Net：用于高光谱目标跟踪的流形引导光谱提示网络
MSP-Net: Manifold-Guided Spectral Prompt Network for Hyperspectral Object Tracking
浏览论文内容
中文总结 AI 辅助
针对现有高光谱目标跟踪方法泛化性差、表征能力不足的问题，提出MSP-Net，通过流形路由构建动态光谱提示，在HOT2020/2023上实现AUC超0.80、精度超0.96，鲁棒性优异。
中文摘要 AI 辅助
高光谱目标跟踪利用丰富的光谱信息，为复杂场景中的目标判别提供独特优势。然而，现有方法通常将高光谱图像视为RGB图像的多通道扩展，按固定波段顺序进行特征融合。这种方法导致模型依赖特定传感器配置，同时忽略波段间的流形关系，难以泛化到异构传感器。此外，波段的判别贡献会随目标属性和场景变化动态改变，进一步限制了静态融合策略的表征能力。为解决这些问题，我们提出流形引导光谱提示网络（MSP-Net）。该网络首先通过图驱动的流形路由重构波段关系，形成自适应光谱分组，随后将分组后的光谱统计量与模板外观联合整合，构建与目标相关的动态条件提示，增强目标特征的同时抑制背景干扰。此外，随着跟踪的推进，光谱条件会根据中间目标表示持续演变，使目标提示能实时适应外观和场景变化。同时，可靠的历史状态用于约束目标定位和尺度波动，显著提升跨传感器跟踪的时间稳定性。在HOT2020和HOT2023数据集上的实验表明，MSP-Net的AUC（曲线下面积）和精度分别超过0.80和0.96，在异构传感器、目标变形和复杂背景条件下表现出卓越的鲁棒性。代码将在该https链接发布。
英文摘要
Hyperspectral object tracking leverages abundant spectral information to provide unique advantages for target discrimination in complex scenes. However, existing methods typically treat hyperspectral images as multi-channel extensions of RGB images, performing feature fusion in fixed band order. This approach leads to models dependent on specific sensor configurations while neglecting manifold relationships between bands, making generalization to heterogeneous sensors difficult. Moreover, the discriminative contribution of bands dynamically changes with target attributes and scene variations, further limiting the representational capacity of static fusion strategies. To address this, we propose the Manifold-Guided Spectral Prompt Network (MSP-Net). This network first reconstructs band relationships and forms adaptive spectral grouping through graph-driven manifold routing, then jointly integrates grouped spectral statistics with template appearance to construct target-related dynamic conditional prompts, enhancing target features while suppressing background interference. Furthermore, as tracking progresses, spectral conditions continuously evolve based on intermediate target representations, enabling target prompts to adapt in real-time to appearance and scene changes. Meanwhile, reliable historical states are used to constrain target localization and scale fluctuations, significantly improving temporal stability in cross-sensor tracking. Experiments on HOT2020 and HOT2023 demonstrate that MSP-Net achieves AUC and Precision exceeding 0.80 and 0.96, respectively, exhibiting exceptional robustness under heterogeneous sensors, target deformation, and complex background conditions. The code will be released at https://github.com/GGML668897/MSP-Net.
