石韫开,
云霄,,
朱绪冉,
王赛楠
中国矿业大学信息与控制工程学院 ??徐州 ??221116
基金项目:江苏省自然科学基金青年基金(BK20180640, BK20150204)，江苏省重点研发计划(BE2015040)，国家重点研发计划(2016YFC0801403)，国家自然科学基金(51504214, 51504255, 51734009, 61771417)
详细信息
作者简介:孙彦景：男，1977年生，教授，博士生导师，研究方向为无线传感器网络、视频目标跟踪、人工智能、信息物理系统
石韫开：男，1993年生，硕士生，研究方向为视频目标跟踪和人工智能
云霄：女，1986年生，讲师，研究方向为视频目标跟踪和人工智能
朱绪冉：女，1993年生，硕士生，研究方向为目标检测与识别
王赛楠：女，1992年生，硕士生，研究方向为视频目标跟踪
通讯作者:云霄 yxztong@163.com
中图分类号:TP391.4计量
文章访问数:2446
HTML全文浏览量:1178
PDF下载量:126
被引次数:0
出版历程
收稿日期:2018-10-17
修回日期:2019-02-26
网络出版日期:2019-03-16
刊出日期:2019-10-01
Adaptive Strategy Fusion Target Tracking Based on Multi-layer Convolutional Features
Yanjing SUN,Yunkai SHI,
Xiao YUN,,
Xuran ZHU,
Sainan WANG
School of Information and Control Engineering, China University of Mining Technology, Xuzhou 221116, China
Funds:The Natural Science Foundation of Jiangsu Province (BK20180640, BK20150204), The Research Development Programme of Jiangsu Province (BE2015040), The State Key Research Development Program (2016YFC0801403), The National Natural Science Foundation of China (51504214, 51504255, 51734009, 61771417)
摘要
摘要:针对目标快速运动、遮挡等复杂视频场景中目标跟踪鲁棒性差和跟踪精度低的问题，该文提出一种基于多层卷积特征的自适应决策融合目标跟踪算法(ASFTT)。首先提取卷积神经网络(CNN)中帧图像的多层卷积特征，避免网络单层特征表征目标信息不全面的缺陷，增强算法的泛化能力；使用多层特征计算帧图像相关性响应，提高算法的跟踪精度；最后该文使用自适应决策融合算法将所有响应中目标位置决策动态融合以定位目标，融合算法综合考虑生成响应的各跟踪器的历史决策信息和当前决策信息，以保证算法的鲁棒性。采用标准数据集OTB2013对该文算法和6种当前主流跟踪算法进行了仿真对比，结果表明该文算法具有更加优秀的跟踪性能。
关键词:目标跟踪/
卷积神经网络/
相关性响应/
决策融合
Abstract:To solve the problems of low robustness and tracking accuracy in target tracking when interference factors occur such as target fast motion and occlusion in complex video scenes, an Adaptive Strategy Fusion Target Tracking algorithm (ASFTT) is proposed based on multi-layer convolutional features. Firstly, the multi-layer convolutional features of frame images in Convolutional Neural Network(CNN) are extracted, which avoids the defect that the target information of the network is not comprehensive enough, so as to increase the generalization ability of the algorithm. Secondly, in order to improve the tracking accuracy of the algorithm, the multi-layer features are performed to calculate the correlation responses, which improves the tracking accuracy. Finally, the target position strategy in all responses are dynamically merged to locate the target through the adaptive strategy fusion algorithm in this paper. It comprehensively considers the historical strategy information and current strategy information of each responsive tracker to ensure the robustness. Experiments performed on the OTB2013 evaluation benchmark show that that the performance of the proposed algorithm are better than those of the other six state-of-the-art methods.
Key words:Target tracking/
Convolutional Neural Network(CNN)/
Correlation response/
Strategy fusion
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=5c6a8917-c391-40ac-9120-60f4ef038b4a
