Single online visual object tracking with enhanced tracking and detection learning

Single online visual object tracking with enhanced tracking and detection learning
复制标题

具有增强跟踪和检测学习功能的单一在线视觉对象跟踪

DOI:
10.1007/s11042-018-6787-6
复制
发表时间:
2018-10
影响因子:
3.6
通讯作者:
Zheng Zhenxian
Zheng Zhenxian
中科院分区:
计算机科学4区
文献类型:
--
作者:
Yi Yang;Luo Liping;Zheng Zhenxian

文献摘要

参考文献

相似文献

单个在线视觉目标跟踪因其在各种任务中的广泛应用而成为一个活跃的研究课题。本文提出了一种新的框架和相关方法来解决这一问题,包括增强的跟踪和检测学习。在增强跟踪部分,采用了具有深度CNN特征的基于相关滤波的外观模型和基于改进金字塔光流法的动态跟踪模型。两个模型共同描述目标的外观和轨迹,为检测学习提供训练样本。在检测学习部分,当模型发生漂移时,采用级联分类器和P-N学习策略重新初始化跟踪。在几个具有挑战性的基准上的数据实验表明,所提出的方法与最先进的方法相媲美。
Single online visual object tracking has been an active research topic for its wide application on various tasks. In this paper, a new framework and related approaches are proposed to solve this problem consisting of enhanced tracking and detection learning. In the enhanced tracking part, an appearance model based on correlation filter with deep CNN features and a dynamic model using improved pyramid optical flow method are employed. Two models cooperate together to depict object appearance and capture target trajectory, which also contribute to provide training samples for detection learning. In the detection learning part, a cascade classifier and P-N learning scheme are employed to reinitialize tracking when model drift occurs. Data experiments on several challenging benchmarks show that the presented method is comparable to the state-of-the-art.
DOI: --
发表时间: 2015-02
期刊: --
影响因子: --
作者:
Seunghoon Hong;Tackgeun You;Suha Kwak;Bohyung Han
通讯作者: Seunghoon Hong;Tackgeun You;Suha Kwak;Bohyung Han
DOI: 10.1109/wacv.2017.26
发表时间: 2017-01
期刊: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
影响因子: --
作者:
Jue Wang;A. Cherian;F. Porikli
通讯作者: Jue Wang;A. Cherian;F. Porikli
DOI: 10.1016/j.image.2012.10.005
发表时间: 2013
期刊: Signal Process. Image Commun.
影响因子: --
作者:
Yang Yi;Jia Ding;Jieling Lai
通讯作者: Yang Yi;Jia Ding;Jieling Lai
DOI: 10.1109/cvpr.2017.441
发表时间: 2016-11
期刊: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子: --
作者:
Xizhou Zhu;Yuwen Xiong;Jifeng Dai;Lu Yuan;Yichen Wei
通讯作者: Xizhou Zhu;Yuwen Xiong;Jifeng Dai;Lu Yuan;Yichen Wei
DOI: --
发表时间: 2013-12
期刊: --
影响因子: --
作者:
Naiyan Wang;D. Yeung
通讯作者: Naiyan Wang;D. Yeung