arXiv 1811.098552018-11cs.CV

FANet：一种用于鲁棒RGB-T跟踪的质量感知特征聚合网络

FANet: Quality-Aware Feature Aggregation Network for Robust RGB-T Tracking

Anhui University（安徽大学）

Yabin Zhu, Chenglong Li, Bin Luo, Jin Tang

摘要：

本文研究了如何在恶劣和具有挑战性的条件下使用互补的视觉和热红外数据（RGBT跟踪）进行鲁棒的视觉跟踪。我们提出了一种新的深度网络架构，称为质量感知特征聚合网络（FANet），用于鲁棒的RGBT跟踪。与现有的RGBT跟踪器不同，我们的FANet在每种模式中聚合了层次化的深度特征，以应对由变形、低光照、背景杂乱和遮挡引起的显著外观变化的挑战。特别地，我们采用最大池化操作将这些分层和多分辨率特征转换到具有相同分辨率的均匀空间中，并使用1x1卷积操作来压缩特征维度，以实现更有效的分层特征聚合。为了对RGB和热模态之间的相互作用进行建模，我们精心设计了一个自适应聚合子网络，以根据其可靠性整合来自不同模态的特征，从而能够减轻低质量源引入的噪声影响。整个FANet以端到端的方式进行训练。在大规模基准数据集上的大量实验证明了与其他最先进的RGBT跟踪方法相比的高精度性能。

英文摘要：

This paper investigates how to perform robust visual tracking in adverse and challenging conditions using complementary visual and thermal infrared data (RGBT tracking). We propose a novel deep network architecture called qualityaware Feature Aggregation Network (FANet) for robust RGBT tracking. Unlike existing RGBT trackers, our FANet aggregates hierarchical deep features within each modality to handle the challenge of significant appearance changes caused by deformation, low illumination, background clutter and occlusion. In particular, we employ the operations of max pooling to transform these hierarchical and multi-resolution features into uniform space with the same resolution, and use 1x1 convolution operation to compress feature dimensions to achieve more effective hierarchical feature aggregation. To model the interactions between RGB and thermal modalities, we elaborately design an adaptive aggregation subnetwork to integrate features from different modalities based on their reliabilities and thus are able to alleviate noise effects introduced by low-quality sources. The whole FANet is trained in an end-to-end manner. Extensive experiments on large-scale benchmark datasets demonstrate the high-accurate performance against other state-of-the-art RGBT tracking methods.

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。

摘要：

英文摘要：

相关论文