中文摘要：

现有的在线跟踪算法在应对目标复杂形变时易出现跟踪偏差．文中通过寻找鲁棒的特征去刻画目标外观来解决这一问题，即模拟人眼视皮层腹侧通路感知机制，引入具有位置尺度不变性、复杂形状选择特性的C2特征，建立一个基于认知碎片集进行C2特征识别的在线目标跟踪模型，并根据认知碎片在目标识别中所起的作用对其重要性进行评估，依据评估结果实现认知碎片的在线淘汰与更新，同时引入在线目标／背景分类器，对新加入认知碎片记忆池的碎片进行筛选，解决了跟踪到的目标区域中的背景部分参与模型更新可能造成的误差累积问题．仿真实验结果表明：该算法在应对目标复杂形变和严重遮挡时，具有一定的鲁棒性与有效性．

英文摘要：

In the existing online object tracking algorithms, tracking deviation commonly occurs when there exists a complex deformation of object appearance. In order to solve this problem, this paper employs robust features to de- scribe the object appearance. First, the perception mechanism of the ventral pathway of human visual cortex is imi- tated, and C2 feature, which is invariant to position and scale and can distinguish complex shapes, is introduced. Then, a novel online object-tracking model based on a cognitive patch set is put forward to recognize C2 feature. In this model, the importance of a cognitive patch is estimated according to its role in the object recognition, and based on the estimated results, online elimination and update of cognitive patches are realized. Meanwhile, an on- line object/background classifier is adopted to distinguish new candidate patches, thus solving the problem of the error accumulation resulting from the participation of the background part of the object region in the model adjust- ment. Simulated results indicate that the proposed method is robust and effective in the presence of complex object deformation and severe occlusion.