A Ranking Based Attention Approach for Visual Tracking
A Ranking Based Attention Approach for Visual Tracking
复制标题
DOI：
10.1109/icip.2019.8803358
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
Shenhui Peng;S. Kamata;T. Breckon
中科院分区：
文献类型：
--
作者：
Shenhui Peng;S. Kamata;T. Breckon
相关滤波器（CF）与预训练的卷积神经网络（CNN）特征提取器相结合，在视觉对象跟踪中显示出令人钦佩的准确性和速度。然而，现有的基于CNN-CF的方法仍然受到背景干扰和边界效应的影响，即使当引入余弦窗口时。本文提出了一种基于排序或引导的注意方法，可以减少背景干扰，只有前向传播。该排名存储多个卷积核并对其进行评分。随后，使用卷积长短时间记忆网络（ConvLSTM）来更新该排名，这使其对变化和遮挡更具鲁棒性。此外，提出了一种基于部分的多通道卷积跟踪器，以获得最终的响应图。我们在已建立的基准数据集上进行的广泛实验表明，与当代跟踪方法相比，性能相当。
Correlation filters (CF) combined with pre-trained convolutional neural network (CNN) feature extractors have shown an admirable accuracy and speed in visual object tracking. However, existing CNN-CF based methods still suffer from the background interference and boundary effects, even when a cosine window is introduced. This paper proposes a ranking based or guided attention approach which can reduce background interference with only forward propagation. This ranking stores several convolution kernels and scores them. Subsequently, a convolutional Long Short Time Memory network (ConvLSTM) is used to update this ranking, which makes it more robust to the variation and occlusion. Moreover, a part-based multi-channel convolutional tracker is proposed to obtain the final response map. Our extensive experiments on established benchmark datasets show comparable performance against contemporary tracking approaches.