MSP-Net: Manifold-Guided Spectral Prompt Network for Hyperspectral Object Tracking
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address problems in tracking objects using hyperspectral images by noting that existing methods ignore how different spectral bands relate and change. They propose MSP-Net, a model that dynamically groups spectral bands based on their relationships and adapts over time to changes in the target and scene. This helps better distinguish the target from the background and improves stability when using different sensors. Their experiments show good tracking accuracy and robustness in challenging conditions.
Hyperspectral imagingObject trackingSpectral bandsFeature fusionManifold learningGraph routingDynamic promptingCross-sensor trackingTemporal stabilityTarget discrimination
Authors
Juliu Li, Hanlin Qin, Shuowen Yang, Jingjing Li, Yuedong Tan, Shuai Yuan, Huixin Zhou
Abstract
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.