College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou 310027, China.
Sensors (Basel). 2020 Apr 10;20(7):2137. doi: 10.3390/s20072137.
In the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-learning problem. However, experiments showed that SiamFC was not so robust in some complex environments. This may be because the tracker lacked enough prior information about the target. Inspired by the key idea of a Staple tracker and Kalman filter, we constructed two more models to help compensate for SiamFC's disadvantages. One model contained the target's prior color information, and the other the target's prior trajectory information. With these two models, we design a novel and robust tracking framework on the basis of SiamFC. We call it Histogram-Kalman SiamFC (HKSiamFC). We also evaluated HKSiamFC tracker's performance on dataset of the online object tracking benchmark (OTB) and Temple Color (TC128), and it showed quite competitive performance when compared with the baseline tracker and several other state-of-the-art trackers.
在视觉跟踪领域，基于卷积神经网络（CNN）的跟踪器取得了重大成就。全卷积 Siam（SiamFC）跟踪器是这些 CNN 跟踪器的典型代表，引起了广泛关注。它将视觉跟踪建模为相似性学习问题。然而，实验表明，SiamFC 在某些复杂环境中不够稳健。这可能是因为跟踪器缺乏关于目标的足够先验信息。受 Staple 跟踪器和卡尔曼滤波器关键思想的启发，我们构建了另外两个模型来帮助弥补 SiamFC 的缺点。一个模型包含目标的先验颜色信息，另一个模型包含目标的先验轨迹信息。基于这两个模型，我们在 SiamFC 的基础上设计了一个新颖而强大的跟踪框架。我们称之为直方图-卡尔曼 SiamFC（HKSiamFC）。我们还在在线目标跟踪基准（OTB）和 Temple Color（TC128）数据集上评估了 HKSiamFC 跟踪器的性能，与基线跟踪器和其他几个最先进的跟踪器相比，它表现出相当有竞争力的性能。
