arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01222cs.CV
收藏

基于Siamese网络的多卷积特征目标跟踪

Multiple Convolutional Features in Siamese Networks for Object Tracking

Polytechnique Montreal(蒙特利尔理工学院);TELUQ University(魁北克大学泰勒斯分校)

Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir

摘要:

Siamese跟踪器在目标跟踪方面表现出了很高的性能,因为它们在准确性和速度之间取得了平衡。与基于分类的CNN不同,深度相似性网络是专门为解决图像相似性问题而设计的,因此本质上更适合于跟踪任务。然而,暹罗跟踪器主要使用最后的卷积层进行相似性分析和目标搜索,这限制了它们的性能。在本文中,我们认为使用单个卷积层作为特征表示不是深度相似性框架中的最佳选择。我们提出了一个多个神经元暹罗跟踪器(MFST),一种新的跟踪算法,利用几个层次的功能强大的跟踪地图。由于卷积层在表征对象时提供了几个抽象级别,因此融合分层特征可以获得更丰富和更有效的目标表示。此外,我们通过校准从两个不同的CNN模型提取的深度特征来处理目标外观变化。基于这种先进的特征表示,我们的方法实现了高跟踪精度,同时优于标准的暹罗跟踪对象跟踪基准。源代码和训练模型可在https://github.com/zhenxili96/MFST上获得。

英文摘要:

Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed. Unlike classification-based CNNs, deep similarity networks are specifically designed to address the image similarity problem, and thus are inherently more appropriate for the tracking task. However, Siamese trackers mainly use the last convolutional layers for similarity analysis and target search, which restricts their performance. In this paper, we argue that using a single convolutional layer as feature representation is not an optimal choice in a deep similarity framework. We present a Multiple Features-Siamese Tracker (MFST), a novel tracking algorithm exploiting several hierarchical feature maps for robust tracking. Since convolutional layers provide several abstraction levels in characterizing an object, fusing hierarchical features allows to obtain a richer and more efficient representation of the target. Moreover, we handle the target appearance variations by calibrating the deep features extracted from two different CNN models. Based on this advanced feature representation, our method achieves high tracking accuracy, while outperforming the standard siamese tracker on object tracking benchmarks. The source code and trained models are available at https://github.com/zhenxili96/MFST.

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。

↑