IEEE Trans Neural Netw Learn Syst. 2017 Oct;28(10):2357-2370. doi: 10.1109/TNNLS.2016.2586194. Epub 2016 Jul 19.
In this paper, we propose a biologically inspired appearance model for robust visual tracking. Motivated in part by the success of the hierarchical organization of the primary visual cortex (area V1), we establish an architecture consisting of five layers: whitening, rectification, normalization, coding, and pooling. The first three layers stem from the models developed for object recognition. In this paper, our attention focuses on the coding and pooling layers. In particular, we use a discriminative sparse coding method in the coding layer along with spatial pyramid representation in the pooling layer, which makes it easier to distinguish the target to be tracked from its background in the presence of appearance variations. An extensive experimental study shows that the proposed method has higher tracking accuracy than several state-of-the-art trackers.
在本文中，我们提出了一种基于生物学的外观模型，用于鲁棒的视觉跟踪。部分受到初级视觉皮层（V1 区）的分层组织成功的启发，我们建立了一个由五层组成的架构：白化、整流、归一化、编码和池化。前三层源于为对象识别而开发的模型。在本文中，我们的注意力集中在编码和池化层。特别是，我们在编码层中使用了一种有辨别力的稀疏编码方法，在池化层中使用了空间金字塔表示，这使得在存在外观变化的情况下更容易将目标与背景区分开来。广泛的实验研究表明，所提出的方法比几种最先进的跟踪器具有更高的跟踪精度。
