用任务导向训练法，让热成像与可见光图像点特征更好匹配。
Learning Cross-Spectral Point Features with Task-Oriented Training
- 在匹配与配准任务上训练特征网络，提升跨谱特征质量。
- 在MultiPoint数据集上，75%以上的配准误差低于10像素。
- 可兼容经典流程，适合无人机低能见度导航应用。
无人飞行器（UAV）可在偏远危险环境执行任务，但依赖可见光相机的导航系统在低能见度条件下表现不佳。热成像相机通过捕捉长波红外辐射，能在黑暗和烟雾中正常工作，而可见光相机则失效。本文探索学习跨谱（热-可见）点特征，以将热成像融入现有基于相机的导航系统。现有方法通常直接训练特征网络的检测与描述输出，易聚焦于热成像与可见光图像外观相似区域。为更充分使用数据，我们提出在匹配与配准任务上训练特征网络：对热-可见图像对运行特征网络，再将输出输入可微分配准流水线，对匹配与配准估计施加损失。所选模型在匹配任务上训练，在MultiPoint数据集上实现超过75%的估计配准误差（角点误差）低于10像素。此外，该模型也可用于经典匹配与配准流水线。
原文摘要 · Abstract (English)
Unmanned aerial vehicles (UAVs) enable operations in remote and hazardous environments, yet the visible-spectrum, camera-based navigation systems often relied upon by UAVs struggle in low-visibility conditions. Thermal cameras, which capture long-wave infrared radiation, are able to function effectively in darkness and smoke, where visible-light cameras fail. This work explores learned cross-spectral (thermal-visible) point features as a means to integrate thermal imagery into established camera-based navigation systems. Existing methods typically train a feature network's detection and description outputs directly, which often focuses training on image regions where thermal and visible-spectrum images exhibit similar appearance. Aiming to more fully utilize the available data, we propose a method to train the feature network on the tasks of matching and registration. We run our feature network on thermal-visible image pairs, then feed the network response into a differentiable registration pipeline. Losses are applied to the matching and registration estimates of this pipeline. Our selected model, trained on the task of matching, achieves a registration error (corner error) below 10 pixels for more than 75% of estimates on the MultiPoint dataset. We further demonstrate that our model can also be used with a classical pipeline for matching and registration.
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。