结合学习率调整的自适应特征融合相关滤波跟踪算法

针对单一特征存在的缺陷和目标快速变化时易跟丢的问题，提出了一种结合学习率调整的自适应特征融合相关滤波跟踪算法。算法采用互补的梯度特征和颜色特征进行特征融合，通过计算滤波响应的大小来决定下一帧在融合特征中各自所占的权重，凸显优势特征，使目标与背景更具区分度。提取目标后需要更新滤波器，为了避免滤波器跟不上目标变化的情况发生，引入学习率调整机制，使滤波器更新速度能够随目标外观变化进行在线调整。因此，相较同类特征融合算法，本算法准确高效，且对于快速形变目标的鲁棒性更强。实验证明，本算法在精度和成功率上都比现有相关滤波算法更优，具有一定的应用价值。

Adaptive feature fusion correlation filter tracking algorithm combined with learning rate adjustment

In view of the defects of single feature and the problem of easy to miss when the target is fast changing, this paper proposes an adaptive feature fusion correlation filter tracking algorithm based on learning rate adjustment. The algorithm used complementary gradient features and color features to do the feature fusion, and decides the weights of the features in the fusion feature in next frame by calculating the size of the filter response of each feature, so as to highlight the dominant features and make the target and background more discriminative. After extracting the target, we need to update the filter. In order to avoid the situation that filter can not keep up with the change of the target, the learning rate adjustment mechanism is introduced, so that the update speed of the filter can be adjusted online with the appearance of the target. Therefore, compared with the similar feature fusion algorithm, our algorithm is more accurate and efficient, and the robustness of the fast deformation target is stronger. The experiment shows that our algorithm is better than the existing correlation filter algorithms in accuracy and success rate, and has a certain application price.