Procedings of the British Machine Vision Conference 2002 2002
DOI: 10.5244/c.16.76
|View full text |Cite
|
Sign up to set email alerts
|

Partial Observation vs. Blind Tracking through Occlusion

Abstract: This paper presents a framework for multi-object tracking from a single fixed camera. The region-based representations of each object are tracked and predicted using a Kalman filter. A scene model is created to help predict and interpret the occluded or exiting objects. Unlike the traditional blind tracking during occlusion, the object states are updated using partial observations whenever available. The observability of each object depends on the predictive measurement of the object, the foreground region mea… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
25
0

Year Published

2004
2004
2011
2011

Publication Types

Select...
3
3
3

Relationship

2
7

Authors

Journals

citations
Cited by 45 publications
(25 citation statements)
references
References 4 publications
0
25
0
Order By: Relevance
“…Borrowing terminology from Ellis & Xu [9], we can expect trajectories to end in a number of different types of situation, or "occlusion": Short Term occlusions, where we can expect the agent to reappear (like a hedge) and other cases (Border occlusions and Long Term occlusions) where the agent has actually left the scene. For the purposes of this study, we treat all three of their cases identically and do not try to unify trajectories in situations with short term occlusions.…”
Section: The Exit Modelmentioning
confidence: 99%
“…Borrowing terminology from Ellis & Xu [9], we can expect trajectories to end in a number of different types of situation, or "occlusion": Short Term occlusions, where we can expect the agent to reappear (like a hedge) and other cases (Border occlusions and Long Term occlusions) where the agent has actually left the scene. For the purposes of this study, we treat all three of their cases identically and do not try to unify trajectories in situations with short term occlusions.…”
Section: The Exit Modelmentioning
confidence: 99%
“…The tracking method described above is an effective and robust method for dealing with partial occlusions when the bounding box of two objects are overlapped in part, and further details on the procedure for splitting two merged objects can be found in [31]. However, if the bounding box of one (smaller) object, such as the ball, is completely contained by another (larger) object's bounding box, then there is no valid observation for the ball, and the estimated state will be updated on prediction only.…”
Section: Tracking Correctionmentioning
confidence: 99%
“…In 8 this Section, separating each group of players, in particular groups of two, are discussed by assuming that each target has a slowly varying height and width [22].…”
Section: Filtering and Categorizing Of Playersmentioning
confidence: 99%