Online unsupervised feature learning for visual tracking
Online unsupervised feature learning for visual tracking
复制标题
DOI：
10.1016/j.imavis.2016.04.008
复制
发表时间：
2013-10
期刊：
影响因子：
--
通讯作者：
Fayao Liu;Chunhua Shen;I. Reid;A. Hengel
中科院分区：
文献类型：
--
作者：
Fayao Liu;Chunhua Shen;I. Reid;A. Hengel
提出了一种基于在线特征学习的视觉检测跟踪方法。我们的学习框架针对过完备的词典执行特征编码，然后是空间金字塔池。然后，我们基于所得到的特征编码来学习线性分类器。与以前的工作不同，我们在线学习词典并进行更新，以帮助捕获跟踪目标的外观以及背景。更详细地说，在给定测试图像窗口的情况下，我们从其中提取局部图像块，并相对于字典对每个局部块进行编码。然后，编码的特征被汇集在空间金字塔上以形成聚集的特征向量。最后，用一个简单的线性分类器对这些特征进行了训练。我们的实验表明，提出的跟踪方法虽然简单，但功能强大，性能优于我们测试过的所有最先进的跟踪方法。此外，我们对所提出的跟踪框架中不同的字典学习和特征编码方法的性能进行了评估，并分析了各个组件在跟踪场景中的影响。特别是，我们表明，在线学习和更新的小词典与在线学习的大词典一样有效，效率也更高。我们通过展示如何在结构化学习跟踪框架内使用特征学习来进一步证明特征学习的灵活性。该结果是迄今为止报告的最好的跟踪器之一，它促进了特征学习和结构化输出预测的优势。我们还实现了一个多目标跟踪器，实现了最先进的性能。
We propose a method for visual tracking-by-detection based on online feature learning. Our learning framework performs feature encoding with respect to an over-complete dictionary, followed by spatial pyramid pooling. We then learn a linear classifier based on the resulting feature encoding. Unlike previous work, we learn the dictionary online and update it to help capture the appearance of the tracked target as well as the background. In more detail, given a test image window, we extract local image patches from it and each local patch is encoded with respect to the dictionary. The encoded features are then pooled over a spatial pyramid to form an aggregated feature vector. Finally, a simple linear classifier is trained on these features.Our experiments show that the proposed powerful—albeit simple—tracker, outperforms all the state-of-the-art tracking methods that we have tested. Moreover, we evaluate the performance of different dictionary learning and feature encoding methods in the proposed tracking framework, and analyze the impact of each component in the tracking scenario. In particular, we show that a small dictionary, learned and updated online is as effective and more efficient than a huge dictionary learned offline. We further demonstrate the flexibility of feature learning by showing how it can be used within a structured learning tracking framework. The outcome is one of the best trackers reported to date, which facilitates the advantages of both feature learning and structured output prediction. We also implement a multi-object tracker, which achieves state-of-the-art performance.