中南民族大学学报（自然科学版）2018，Vol.37Issue(2)：67-73,7.
基于深度特征和相关滤波器的视觉目标跟踪
Visual Object Tracking Based on Deep Features and Correlation Filter
摘要
Abstract
Conventional correlation filter methods employ hand-crafted features to extract training samples,which limits the further promotion of tracking performance.Under the framework of correlation filter,this paper has investigated tracking effect of features from different convolutional layers in deep neural network VGG-16.It is shown in our research that deep features extracted from VGG-16 have a significant advantage compared to conventional hand-crafted ones,and the best results are obtained using features in the first and fifth layers.Based on the above observation,we proposed to train correlation filters separately in the first and fifth layers,and localize the target precisely by weighting response maps produced by the both correlation filters.The experimental results on the OTB2013 dataset demonstrate that the proposed method has improved the tracking accuracy and robustness.关键词
目标跟踪/相关滤波器/响应图/目标定位/深度特征Key words
object tracking/correlation filter/response map/object location/deep feature分类
信息技术与安全科学引用本文复制引用
侯建华,邓雨,陈思萌,项俊..基于深度特征和相关滤波器的视觉目标跟踪[J].中南民族大学学报（自然科学版）,2018,37(2):67-73,7.基金项目
国家自然科学基金资助项目(61671484,61701548) （61671484,61701548）
中南民族大学中央高校基本科研业务费专项资金(CZY18046,CZZ18001) （CZY18046,CZZ18001）
