Hough Forest-based Association Framework with Occlusion Handling for Multi-Target Tracking

Hough Forest-based Association Framework with Occlusion Handling for Multi-Target Tracking
复制标题

基于霍夫森林的关联框架与多目标跟踪的遮挡处理

DOI:
10.1109/lsp.2015.2512878
复制
发表时间:
2016-02
影响因子:
3.9
通讯作者:
Gao, Changxin
Gao, Changxin
中科院分区:
工程技术2区
文献类型:
--
作者:
Sang, Nong;Hou, Jianhua;Huang, Rui;Gao, Changxin

文献摘要

参考文献

被引文献

相似文献

这封信提出了一种新的多目标跟踪方法,包括两个部分。第一部分是基于检测的全局航迹关联。首先生成简短但可靠的轨迹片段。通过有效地结合外观和运动信息,Hough森林学习框架的构建,以获得更有区别的亲和力模型,并产生更长的轨迹之间的关联。在第二部分中,为了将孤立的检测点连接起来以保证轨迹的一致性,我们提出了一种基于相互遮挡推理的外观相似性模型。设计了一种新的融合特征模板,精确计算每个孤立检测与目标的匹配得分。实验结果表明,我们的方法相比,几个国家的最先进的方法显着改善。
This letter presents a novel multi-target tracking approach consisting of two parts. The first part is the detection based association to form global tracks. Short yet reliable tracklets are firstly generated. By effectively combining appearance and motion information, a Hough forest learning framework is constructed to obtain a more discriminative affinity model and produce longer association between tracklets. In the second part, in order to connect isolate detections for trajectory consistency, we present an appearance similarity model based on mutual occlusion reasoning. A novel fusion feature template is designed to accurately compute the matching score between each isolated detection and target. Experimental results show significant improvements of our method when compared with several state-of-the-art methods.
DOI: 10.1007/978-3-642-33709-3_25
发表时间: 2012-10
期刊: --
影响因子: --
作者:
Amir Zamir;Afshin Dehghan;M. Shah
通讯作者: Amir Zamir;Afshin Dehghan;M. Shah
DOI: 10.1109/cvpr.2009.5206735
发表时间: 2009-06
期刊: 2009 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Yuan Li;Chang Huang;R. Nevatia
通讯作者: Yuan Li;Chang Huang;R. Nevatia
DOI: 10.1109/tpami.2013.103
发表时间: 2014-01-01
影响因子: 23.6
作者:
Milan, Anton;Roth, Stefan;Schindler, Konrad
通讯作者: Schindler, Konrad
DOI: 10.1109/cvpr.2008.4587584
发表时间: 2008-06
期刊: 2008 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Li Zhang;Yuan Li;R. Nevatia
通讯作者: Li Zhang;Yuan Li;R. Nevatia
DOI: 10.1109/tip.2014.2324292
发表时间: 2014-05
影响因子: 10.6
作者:
A. Heili;Adolfo López;J. Odobez
通讯作者: A. Heili;Adolfo López;J. Odobez