全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于多目标检测与跟踪的密集客流检测

DOI: 10.11834/jig.20091030

Keywords: 梯度方向直方图,支持向量机,Mean,Shift跟踪,客流计数

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对密集交通场景中的客流检测问题,提出了基于支持向量机(SVM)多目标检测与MeanShift跟踪相结合的方法。首先采用自适应检测窗口提取梯度方向直方图,经过SVM分类和聚类算法,得到头部图像初始假设。然后采用MeanShift算法,对头部假设进行跟踪,得到连续的头部图像序列。通过SVM分类器对序列图像进行整体判断,得到客流信息。实验结果表明,自适应滑动窗口的方法减少了特征提取阶段的处理时间,提高了检测速度;同时,通过对得到的跟踪序列进行整体判别,客流量的检测精度得到了提高。

References

[1]  Marana A N.Real-time crowd density estimation using images[J].Advances in visual computing,2005,3804:355-362.
[2]  Dan Kong,Doug Gray,Hai Tao.A viewpoint invariant approach for crowd counting[A].In:Proceedings of the 18th International Conference on Pattern Recognition[C],Hong Kong,China,2006:1187-1190.
[3]  David G.Lows.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004:91-110.
[4]  Dorin Comaniciu,Visvanathan Ramesh,Peter Meer.Kernel-based object tracking[J].IEEE Trosactions on Pattern Analysis and Machine Intelligence,2003,25 (5):564-577.
[5]  Bastian Leibe,Edgar Seemann,Beret Schiele.Pedestrian detection in crowded scenes[A].In:Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C],San Diego,CA,USA,2005:878-885.
[6]  Rabaud V,Belongie S.Counting crowded moving objects[A].In:Proceedings of the IEEE Computer Society Conference on Computer Vision and patlern Recognition[C],New York,NY,USA,2006:705-711.
[7]  Navneet Dalal,Bill Triggs.Histograms of oriented gradients for human detection[A].In:Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C],San Diego,CA,USA,2005:886-893.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133