arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.02783cs.CV
收藏

显著性增强的鲁棒视觉跟踪

Saliency-Enhanced Robust Visual Tracking

Nokia Technologies(诺基亚技术)

Caglar Aytekin, Francesco Cricri, Emre Aksu

摘要:

基于离散相关滤波器(DCF)的跟踪器在视觉对象跟踪中已经显示出相当大的成功。这些跟踪器通常利用低到中级特征,例如梯度直方图(HoG)和卷积神经网络(CNN)的中间层激活。我们认为,包括语义上更高层次的信息跟踪功能可能会提供进一步的鲁棒性,具有挑战性的情况下,如视点的变化。深度显著目标检测是这种高级特征的一个示例,因为它利用语义信息来突出给定场景中的重要区域。在这项工作中,我们提出了一个改进的DCF为基础的跟踪器相结合的显着性和其他功能为基础的过滤器响应。该组合是利用基于显著性的滤波器响应上的自适应权重来执行的,该自适应权重是根据视觉显著性的时间一致性来自动选择的。我们表明,我们的方法始终提高了基线DCF为基础的跟踪器,特别是在具有挑战性的情况下,并执行优于国家的最先进的。我们改进的跟踪器运行在9.3帧每秒,引入一个小的计算负担超过基线,运行在11帧每秒。

英文摘要:

Discrete correlation filter (DCF) based trackers have shown considerable success in visual object tracking. These trackers often make use of low to mid level features such as histogram of gradients (HoG) and mid-layer activations from convolution neural networks (CNNs). We argue that including semantically higher level information to the tracked features may provide further robustness to challenging cases such as viewpoint changes. Deep salient object detection is one example of such high level features, as it make use of semantic information to highlight the important regions in the given scene. In this work, we propose an improvement over DCF based trackers by combining saliency based and other features based filter responses. This combination is performed with an adaptive weight on the saliency based filter responses, which is automatically selected according to the temporal consistency of visual saliency. We show that our method consistently improves a baseline DCF based tracker especially in challenging cases and performs superior to the state-of-the-art. Our improved tracker operates at 9.3 fps, introducing a small computational burden over the baseline which operates at 11 fps.

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。

↑