Target tracking algorithm combined part-based and redetection for UAV

Target tracking algorithm combined part-based and redetection for UAV
复制标题

基于部分和重检测相结合的无人机目标跟踪算法

DOI:
10.1186/s13638-020-01696-3
复制
发表时间:
2020-05
影响因子:
2.6
通讯作者:
Yao Yanxin
Yao Yanxin
中科院分区:
计算机科学4区
文献类型:
--
作者:
He Qiusheng;Zhang Weifeng;Chen Wei;Xie Gang;Yao Yanxin

文献摘要

参考文献

相似文献

在无人机视频图像的目标跟踪过程中,由于目标遮挡和尺度变化,跟踪算法的性能下降甚至跟踪失败。在分析核相关滤波器跟踪框架的基础上,提出了一种改进的目标跟踪算法。首先,围绕目标中心的中心划分四个子块。一个融合了HOG特征和CN特征的相关滤波器分别跟踪每个目标子块。根据子块的空间结构特征,估计目标的中心位置和尺度。其次,通过全局滤波确定目标的正确中心位置;然后,提出了一种跟踪故障检测方法。当跟踪失败时,启动目标重检测模块,使用归一化互相关算法(NCC)获得重检测区域内的候选目标集。此外,该算法利用全局滤波从候选集中获得真实目标。同时,该算法根据检测结果对分类器的学习率进行分段调整。最后,在UAV123数据集上验证了该算法的性能。结果表明,与几种主流方法相比,该算法在处理目标尺度变化和遮挡时的识别效率有显著提高。
In the process of target tracking for UAV video images, the performance of the tracking algorithm declines or even the tracking fails due to target occlusion and scale variation. This paper proposes an improved target tracking algorithm based on the analysis of the tracking framework of the kernel correlation filter. First, four subblocks around the center of the target center are divided. A correlation filter fusing Histogram of Oriented Gradient (HOG) feature and Color Name (CN) feature tracks separately each target subblocks. According to the spatial structure characteristics in the subblocks, the center location and scale of the target are estimated. Secondly, the correct center location of target is determined by the global filter. Then, a tracking fault detection method is proposed. When tracking fails, the target redetection module which uses the normalized cross-correlation algorithm (NCC) to obtain the candidate target set in the re-detection area is started. Besides, this algorithm uses the global filter to obtain real target from the candidate set. In the meanwhile, this algorithm adjusts sectionally the learning rate of the classifiers according to detection results. Lastly, the performance of this algorithm is verified on the UAV123 dataset. The results show that compared with several mainstream methods, that of this algorithm is significantly improved when dealing with target scale variation and occlusion.
基于递归正交最小二乘法的视觉目标跟踪双向跟踪方案
DOI: 10.1109/access.2019.2951056
发表时间: 2019
期刊: IEEE Access
影响因子: 3.9
作者:
Zhiyong Huang;Yuanlong Yu;Miaoxing Xu
通讯作者: Miaoxing Xu
基于神经网络的概率密度函数发生器
DOI: 10.1016/j.physa.2019.123344
发表时间: 2020-03-01
影响因子: 3.3
作者:
Chen, Chi-Hua;Song, Fangying;Wu, Ling
通讯作者: Wu, Ling
DOI: 10.1109/tmc.2016.2592915
发表时间: 2017-05-01
影响因子: 7.9
作者:
Lin, Dan;Kang, Jian;Tonguz, Ozan
通讯作者: Tonguz, Ozan
DOI: --
发表时间: --
期刊: --
影响因子: --
作者:
João F. Henriques;Rui Caseiro;P. Martins;Jorge Batista
通讯作者: João F. Henriques;Rui Caseiro;P. Martins;Jorge Batista
DOI: 10.1109/tcyb.2017.2716101
发表时间: 2016-05
影响因子: 11.8
作者:
A. Lukežič;Luka Čehovin Zajc;M. Kristan
通讯作者: A. Lukežič;Luka Čehovin Zajc;M. Kristan