2008
DOI: 10.1109/jstsp.2008.2001310
|View full text |Cite
|
Sign up to set email alerts
|

Distributed Object Tracking Using a Cluster-Based Kalman Filter in Wireless Camera Networks

Abstract: Abstract-Local data aggregation is an effective means to save sensor node energy and prolong the lifespan of wireless sensor networks. However, when a sensor network is used to track moving objects, the task of local data aggregation in the network presents a new set of challenges, such as the necessity to estimate, usually in real time, the constantly changing state of the target based on information acquired by the nodes at different time instants. To address these issues, we propose a distributed object tra… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
93
0

Year Published

2011
2011
2023
2023

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 141 publications
(93 citation statements)
references
References 31 publications
0
93
0
Order By: Relevance
“…Also, multiple camera information such as epipolar geometry is used for target initialization and for the detection of loss of tracking that may call for reinitialization. In [8], Kalman filter based multicamera collaboration was proposed. In this application, a 2D estimate of each view is transformed to the world coordinate plane by a homography.…”
Section: G(·)mentioning
confidence: 99%
See 3 more Smart Citations
“…Also, multiple camera information such as epipolar geometry is used for target initialization and for the detection of loss of tracking that may call for reinitialization. In [8], Kalman filter based multicamera collaboration was proposed. In this application, a 2D estimate of each view is transformed to the world coordinate plane by a homography.…”
Section: G(·)mentioning
confidence: 99%
“…Let us say a camera cluster is formed with the purpose of tracking an object, so that a camera node in the cluster is elected as the cluster head, and the other camera nodes are assigned as cluster members. As described in [7,8], we assume that cluster members are one hop neighbors of the cluster head but are not necessarily within single hop communication range of one another. In this environment, the cluster head estimates the global posterior probability of the target object by combining the local information transmitted from member cameras.…”
Section: Resource-aware Distributed Particle Filter In Wireless Camermentioning
confidence: 99%
See 2 more Smart Citations
“…Such tasks would require cluster-based distributed implementations of the algorithms. 12,13 The collaborative processing required by such algorithms is usually carried out with the help of clusters that consist of nodes that can capture some sensory information related to the event. Such collaborative computations typically require intensive message exchanges within a cluster, resulting in highly bursty communications that, unless the communication protocol parameters are changed in a timely manner, may be characterized by frequent packet collisions that may result in waste of energy and failure in transmitting critical data.…”
Section: Event-driven Wireless Sensor Networkmentioning
confidence: 99%