Computer Vision – ACCV 2007
DOI: 10.1007/978-3-540-76386-4_49
|View full text |Cite
|
Sign up to set email alerts
|

Fragments Based Parametric Tracking

Abstract: The paper proposes a parametric approach for color based tracking. The method fragments a multimodal color object into multiple homogeneous, unimodal, fragments. The fragmentation process consists of multi level thresholding of the object color space followed by an assembling. Each homogeneous region is then modelled using a single parametric distribution and the tracking is achieved by fusing the results of the multiple parametric distributions. The advantage of the method lies in tracking complex objects wit… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
1
0

Publication Types

Select...
2
1
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(4 citation statements)
references
References 9 publications
0
1
0
Order By: Relevance
“…Fragments [6], Multiple Instance Learning for trakcing (MIL) [4], PROST [7] and Online Nearest Neighbor (ONN) [8]. We directly cited the results from [8].…”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…Fragments [6], Multiple Instance Learning for trakcing (MIL) [4], PROST [7] and Online Nearest Neighbor (ONN) [8]. We directly cited the results from [8].…”
Section: Methodsmentioning
confidence: 99%
“…In a recent examples of tracking-by-detection [2,3,4,5,6,7,8], H. Grabner [2,3] extended offline boosting approach into online learning for object detection and tracking. The main idea in online boosting is to treat learning as feature selection.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…These descriptors have been used for texture segmentation and classification [4,6], detection of pedestrians [7], and other objects [8]. Region covariances have also been used extensively for object tracking [9,10] and for image retrieval and recognition in a surveillance setting [11,12]. [13,14] use Gabor-based region covariances for face recognition, and in [2,15] Guo et al use derivatives of optical flow for action recognition.…”
Section: Related Workmentioning
confidence: 99%