Visual tracking via shallow and deep collaborative model
Visual tracking via shallow and deep collaborative model
复制标题
DOI：
10.1016/j.neucom.2016.08.070
复制
发表时间：
2016-07
期刊：
影响因子：
--
通讯作者：
Bohan Zhuang;Lijun Wang;Huchuan Lu
中科院分区：
文献类型：
--
作者：
Bohan Zhuang;Lijun Wang;Huchuan Lu
在本文中，我们提出了一种基于产生式模型和判别分类器的稳健跟踪方法，其中特征分别通过浅层和深层结构学习。对于生成模型，我们引入了一种基于块的增量学习方案，其中构造了一个局部二值掩码来处理遮挡问题。将局部块与其对应的子空间之间的相似度进行综合，形成更准确的全局外观模型。在判别模型中，我们利用深度学习体系结构的进步来学习对背景杂波和前景外观变化都具有健壮性的通用特征。为此，我们首先从辅助视频序列中构造区分训练集。然后在该训练集上离线训练深度分类神经网络。通过在线微调，分层特征提取和分类器都可以适应目标的外观变化，从而实现有效的在线跟踪。这两个模型的协作在处理遮挡和目标外观变化方面取得了很好的平衡，这是视觉跟踪中两个相互矛盾的挑战因素。对挑战图像序列的几种最新算法的定量和定性评估都证明了所提出的跟踪器的准确性和稳健性。
In this paper, we propose a robust tracking method based on the collaboration of a generative model and a discriminative classifier, where features are learned by shallow and deep architectures, respectively. For the generative model, we introduce a block-based incremental learning scheme, in which a local binary mask is constructed to deal with occlusion. The similarity degrees between the local patches and their corresponding subspace are integrated to formulate a more accurate global appearance model. In the discriminative model, we exploit the advances of deep learning architectures to learn generic features which are robust to both background clutters and foreground appearance variations. To this end, we first construct a discriminative training set from auxiliary video sequences. A deep classification neural network is then trained offline on this training set. Through online fine-tuning, both the hierarchical feature extractor and the classifier can be adapted to the appearance change of the target for effective online tracking. The collaboration of these two models achieves a good balance in handling occlusion and target appearance change, which are two contradictory challenging factors in visual tracking. Both quantitative and qualitative evaluations against several state-of-the-art algorithms on challenging image sequences demonstrate the accuracy and the robustness of the proposed tracker.