摘要
为解决卷积特征目标跟踪算法精确度和速度相互制约的问题,文中提出了一种基于峰值旁瓣比的自适应位置切换的相关滤波目标跟踪算法。将Pool4和Conv5-3层作为特征提取层,通过特征能量均值比获取有效的卷积特征,提高算法的速度;然后利用不同样本分布训练多个相关滤波器,并根据峰值旁瓣比筛选出最适分类器进行位置预测,提高了跟踪器的泛化能力;最后利用稀疏模型更新策略更新滤波器模板,减小过拟合现象的同时进一步提高算法的速度。在OTB100标准数据集上测试该算法,实验结果表明,文中所提算法的精确度为88.8%,较原分层卷积跟踪算法提高了6.1%;跟踪速度为47.5帧/s,是原算法的5倍,显示了良好的实时性能。
To solve the problem of constrains between the accuracy and speed for convolutional features for visual tracking methods, an algorithm namely adaptive position switching based on correlation filters was proposed. Pool4 and Conv5-3 layers were selected for features extraction. At the same time, effective features were obtained by the average feature energy ratio, which improved the tracking speed. Then it trained correlation filters with different Gaussian distributions of samples. Therefore, the best classifier was selected to predict the position according to the peak-side-lobe ratio, with a promotion in the generalization ability of the tracker. Finally, the sparse model update strategy was adopted to reduce the over-fitting and further speed up the algorithm. This algorithm was tested on OTB100 benchmark dataset. Tracking results demonstrated that the accuracy was 88.8%, 6.1% higher than the hierarchical convolutional features for visual tracking method. The tracking speed was 47.5 frames per second, which was 5 times than the original method, and showed favorable real-time performance.
作者
王润玲
滕硕
WANG Runling;TENG Shuo(School of Sciences,North China University of Technology,Beijing 100144,China)
出处
《电子科技》
2019年第9期10-14,31,共6页
Electronic Science and Technology
基金
国家重点研发计划(2017YFC0821102)~~
关键词
视觉跟踪
自适应特征
相关滤波
峰值旁瓣比
模型更新
高斯分布
visual tracking
adaptive features
correlation filter
peak-side-lobe ratio
model update
Gaussian distribution
