BihoT：用于高光谱伪装目标跟踪的大规模数据集与基准
BihoT: A Large-Scale Dataset and Benchmark for Hyperspectral Camouflaged Object Tracking
AI总结：
本文提出高光谱伪装目标跟踪任务，构建包含49个序列、41,912张图像的BihoT大规模数据集，并设计融合光谱提示与干扰感知的SPDAN基线，取得先进跟踪性能。
摘要：
高光谱目标跟踪（HOT）已在多种应用中展现出潜力，尤其是在目标被伪装的场景中。由于现有HOT数据集存在偏差，其中大多数目标往往具有可区分的视觉外观而非光谱特征，因此现有跟踪器能够通过波段重组有效地检索目标。这种偏差使跟踪器可以直接利用由高光谱图像生成的假彩色图像所获得的视觉特征，而无需提取光谱特征。为解决这一偏差，我们发现当目标外观不可靠时，跟踪器应关注光谱信息。因此，我们提出了一项名为高光谱伪装目标跟踪（HCOT）的新任务，并精心构建了一个大规模HCOT数据集，称为BihoT，该数据集由覆盖49个视频序列的41,912张高光谱图像组成。该数据集涵盖多种人工伪装场景，其中目标具有相似外观、多样光谱和频繁遮挡，使其成为极具挑战性的HCOT数据集。此外，本文提出了一个简单而有效的基线模型，名为基于光谱提示的干扰感知网络（SPDAN），由光谱嵌入网络（SEN）、基于光谱提示的骨干网络（SPBN）和干扰感知模块（DAM）组成。具体而言，SEN通过三维和二维卷积提取光谱-空间特征。随后，SPBN利用光谱提示对强大的RGB跟踪器进行微调，并缓解训练样本不足的问题。此外，DAM利用一种新颖的统计量来捕捉由目标和背景遮挡所造成的干扰。大量实验表明，本文提出的SPDAN在所提出的BihoT及其他HOT数据集上取得了最先进的性能。
英文摘要：
Hyperspectral object tracking (HOT) has exhibited potential in various applications, particularly in scenes where objects are camouflaged. Existing trackers can effectively retrieve objects via band regrouping because of the bias in existing HOT datasets, where most objects tend to have distinguishing visual appearances rather than spectral characteristics. This bias allows the tracker to directly use the visual features obtained from the false-color images generated by hyperspectral images without the need to extract spectral features. To tackle this bias, we find that the tracker should focus on the spectral information when object appearance is unreliable. Thus, we provide a new task called hyperspectral camouflaged object tracking (HCOT) and meticulously construct a large-scale HCOT dataset, termed BihoT, which consists of 41,912 hyperspectral images covering 49 video sequences. The dataset covers various artificial camouflage scenes where objects have similar appearances, diverse spectrums, and frequent occlusion, making it a very challenging dataset for HCOT. Besides, a simple but effective baseline model, named spectral prompt-based distractor-aware network (SPDAN), is proposed, comprising a spectral embedding network (SEN), a spectral prompt-based backbone network (SPBN), and a distractor-aware module (DAM). Specifically, the SEN extracts spectral-spatial features via 3-D and 2-D convolutions. Then, the SPBN fine-tunes powerful RGB trackers with spectral prompts and alleviates the insufficiency of training samples. Moreover, the DAM utilizes a novel statistic to capture the distractor caused by occlusion from objects and background. Extensive experiments demonstrate that our proposed SPDAN achieves state-of-the-art performance on the proposed BihoT and other HOT datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
