Convolution networks trained offline have recently exhibited promising performance in object tracking tasks. However, offline training is time-consuming and their performance heavily rely on the category of auxiliary training sets. In this paper, we propose a sparse gradient convolution network without pretraining for object tracking. This approach combines shallow convolutional networks and traditional methods (gradient features and sparse representations) to avoid the offline training. In the first frame, we utilize the sparse representation method to learn a series of gradient-based local patches served as fixed filters, and they are used to convolving the input image in the subsequent frames to encode local structural information. Then, we stack all the local structure features to construct global spatial structure features, and the inner geometric layout information is preserved. Moreover, sparse coding and online updating are used to overcome issues related to target appearance variations. Qualitative and quantitative evaluations based on a challenging benchmark dataset demonstrate the effectiveness of the proposed algorithm against several state-of-the-art tracking methods.

离线训练的卷积网络最近在对象跟踪任务中表现出令人鼓舞的性能。但是，离线培训非常耗时，其性能在很大程度上取决于辅助培训集的类别。在本文中，我们提出了一种未经预训练的稀疏梯度卷积网络以进行目标跟踪。这种方法结合了浅层卷积网络和传统方法（梯度特征和稀疏表示），以避免离线训练。在第一帧中，我们利用稀疏表示方法来学习一系列用作固定滤波器的基于梯度的局部斑块，并使用它们将后继帧中的输入图像进行卷积以编码局部结构信息。然后，我们堆叠所有局部结构特征以构建全局空间结构特征，并保留内部几何布局信息。此外，稀疏编码和在线更新用于克服与目标外观变化有关的问题。基于具有挑战性的基准数据集的定性和定量评估证明了该算法针对几种最新跟踪方法的有效性。