2009 IEEE Conference on Computer Vision and Pattern Recognition 2009
DOI: 10.1109/cvpr.2009.5206801
|View full text |Cite
|
Sign up to set email alerts
|

Discriminatively trained particle filters for complex multi-object tracking

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
61
0

Year Published

2010
2010
2016
2016

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 97 publications
(61 citation statements)
references
References 12 publications
0
61
0
Order By: Relevance
“…The results including the comparison with the method in [9] for pedestrian 1 and pedestrian 2 are demonstrated in Fig. 6 and Fig.…”
Section: Tracking Precision Testmentioning
confidence: 99%
See 2 more Smart Citations
“…The results including the comparison with the method in [9] for pedestrian 1 and pedestrian 2 are demonstrated in Fig. 6 and Fig.…”
Section: Tracking Precision Testmentioning
confidence: 99%
“…11, where the green and red curves are corresponding to the method in [9] and our proposed method, respectively. The results shows that our method has lower error than the method in [9]. Figure 12 depicts the result where a pedestrian moves through 3 different scenes.…”
Section: Object Re-identification Performancementioning
confidence: 99%
See 1 more Smart Citation
“…However, to speed up the process of tracking and to accommodate the non-Gaussianness nature of the problem, a group of sequential Monte Carlo methods, also known as Particle Filters, is utilized (Rothrock and Drummond, 2000, Danescu et al, 2009, Hue et al, 2002. Particle filters can be discriminatively trained for specific environment and different objectsto-be-tracked tasks, as demonstrated by Hess and Fern in (Hess and Fern, 2009). Current approaches in vehicle tracking from aerial or satellite imagery aim at off-line optimization of data association, e.g.…”
Section: Related Workmentioning
confidence: 99%
“…camera motion, illumination changes, and object resolution). Extensive work has been done over the years [1,2], as it is a very complicated and challenging problem. In this paper, we address the problem of robust multi-target tracking within sports videos (e.g.…”
Section: Introductionmentioning
confidence: 99%