[论文解读] Learning Background-Aware Correlation Filters for Visual Tracking

Hamed Kiani Galoogahi, Ashton Fagg+1 more|arXiv (Cornell University)|Mar 14, 2017

Video Surveillance and Tracking Methods参考文献 28被引用 70

一句话总结

本论文提出背景感知相关滤波器（BACF），除了目标还从真实背景补丁中学习，使在手工特征上实现实时、准确的视觉跟踪，而无需大量深度学习。它在傅里叶域中使用基于ADMM的优化，具在线更新能力，并采用 Sherman-Morrison 快速更新以提升效率。

ABSTRACT

Correlation Filters (CFs) have recently demonstrated excellent performance in terms of rapidly tracking objects under challenging photometric and geometric variations. The strength of the approach comes from its ability to efficiently learn - "on the fly" - how the object is changing over time. A fundamental drawback to CFs, however, is that the background of the object is not be modelled over time which can result in suboptimal results. In this paper we propose a Background-Aware CF that can model how both the foreground and background of the object varies over time. Our approach, like conventional CFs, is extremely computationally efficient - and extensive experiments over multiple tracking benchmarks demonstrate the superior accuracy and real-time performance of our method compared to the state-of-the-art trackers including those based on a deep learning paradigm.

研究动机与目标

• motivation and address the limitation of traditional correlation filters that ignore background information during learning.
• Propose BACF to utilize real background patches as negatives for robust discrimination.
• Maintain real-time performance with an efficient optimization framework in the Fourier domain.
• Evaluate BACF across standard tracking benchmarks against state-of-the-art CF-based and deep trackers.

提出的方法

• Formulate BACF as a multi-channel ridge regression that samples patches from the full frame via a cropping operator.
• Replace circular foreground-only training with a background-inclusive objective that uses P x[k] to crop from large-support training samples.
• Solve the resulting optimization with an ADMM approach in the Fourier domain, including an efficient g-h update and Sherman–Morrison-based inverse updates.
• Apply online adaptation for robustness to appearance changes, and perform multi-scale search for detection.
• Evaluate on OTB50/OTB100/Temple-Color128/VOT2015 using IoU-based metrics and AUC of success plots.

实验结果

研究问题

• RQ1 Can learning from real background patches improve CF tracker accuracy without sacrificing real-time performance?
• RQ2 How does BACF perform relative to hand-crafted feature CF trackers, deep-feature CF trackers, and fully deep trackers on standard benchmarks?
• RQ3 Does the proposed ADMM-based BACF framework enable efficient Multi-channel learning in practice on CPU?
• RQ4 What is the impact of online updating and scale/search strategy on tracking robustness across common challenges (occlusion, deformation, background clutter)?

主要发现

• BACF 在 OTB50、OTB100 与 TC128 上的 AUC-based 成功率高于若干手工特征跟踪器。
• BACF 实现了实时 CPU 性能（约 35 FPS），在精度上与深度特征跟踪器如 CCOT 相当，但速度高出数十到数百倍。
• 在 VOT2015 上，BACF 展现出与顶级跟踪器相当的精度与鲁棒性，相较若干基线有精度提升。
• 基于属性的分析表明，BACF 能通过利用背景补丁在混乱、形变、遮挡和光照变化等场景提高性能。
• 与深度特征 CF 跟踪器相比，BACF 在速度上具有显著优势（约 100–170x 速度胜过 CCOT），精度具有竞争力。