Multilevel Object Tracking in Wireless Multimedia Sensor Networks for Surveillance Applications Using Graph-Based Big Data

Cihan Kucukkececi, Adnan Yazici

Research output: Contribution to journalArticle

Abstract

Wireless Multimedia Sensor Networks (WMSN), for object tracking, have been used as an emerging technology in different application areas, such as health care, surveillance, and traffic control. In surveillance applications, sensor nodes produce data almost in real-time while tracking the objects in a critical area or monitoring border activities. The generated data is generally treated as big data and stored in NoSQL databases. In this paper, we present a new object tracking approach for surveillance applications developed using a big data model based on graphs and a multilevel fusion. Our approach consists of three main steps: intra-node fusion, inter-node fusion, and object trajectory construction. Intra-node fusion exploits the detection and tracking of objects in each sensor, while inter-node fusion uses spatio-temporal data and neighboring sensors. Then, the fused data of all sensor nodes are combined to construct global trajectories of the detected objects in the monitored area on the WMSN. We implemented a prototype system and evaluated the performance of the proposed approach with both a real dataset and a synthetic dataset. The results of our experiments on the two datasets show that the use of third-level fusion in addition to inter-node and intra-node fusions provides significantly better performance for object tracking in the WMSN applications.

Original languageEnglish
Article number8721634
Pages (from-to)67818-67832
Number of pages15
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - Jan 1 2019

Fingerprint

Sensor networks
Fusion reactions
Sensor nodes
Trajectories
Traffic control
Sensors
Big data
Health care
Data structures
Monitoring
Experiments

Keywords

  • Big data
  • graph model
  • multilevel fusion
  • object tracking
  • wireless multimedia sensor networks

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Multilevel Object Tracking in Wireless Multimedia Sensor Networks for Surveillance Applications Using Graph-Based Big Data. / Kucukkececi, Cihan; Yazici, Adnan.

In: IEEE Access, Vol. 7, 8721634, 01.01.2019, p. 67818-67832.

Research output: Contribution to journalArticle

@article{90b10a1876554131b4ee4954c35329d0,
title = "Multilevel Object Tracking in Wireless Multimedia Sensor Networks for Surveillance Applications Using Graph-Based Big Data",
abstract = "Wireless Multimedia Sensor Networks (WMSN), for object tracking, have been used as an emerging technology in different application areas, such as health care, surveillance, and traffic control. In surveillance applications, sensor nodes produce data almost in real-time while tracking the objects in a critical area or monitoring border activities. The generated data is generally treated as big data and stored in NoSQL databases. In this paper, we present a new object tracking approach for surveillance applications developed using a big data model based on graphs and a multilevel fusion. Our approach consists of three main steps: intra-node fusion, inter-node fusion, and object trajectory construction. Intra-node fusion exploits the detection and tracking of objects in each sensor, while inter-node fusion uses spatio-temporal data and neighboring sensors. Then, the fused data of all sensor nodes are combined to construct global trajectories of the detected objects in the monitored area on the WMSN. We implemented a prototype system and evaluated the performance of the proposed approach with both a real dataset and a synthetic dataset. The results of our experiments on the two datasets show that the use of third-level fusion in addition to inter-node and intra-node fusions provides significantly better performance for object tracking in the WMSN applications.",
keywords = "Big data, graph model, multilevel fusion, object tracking, wireless multimedia sensor networks",
author = "Cihan Kucukkececi and Adnan Yazici",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2019.2918765",
language = "English",
volume = "7",
pages = "67818--67832",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Multilevel Object Tracking in Wireless Multimedia Sensor Networks for Surveillance Applications Using Graph-Based Big Data

AU - Kucukkececi, Cihan

AU - Yazici, Adnan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Wireless Multimedia Sensor Networks (WMSN), for object tracking, have been used as an emerging technology in different application areas, such as health care, surveillance, and traffic control. In surveillance applications, sensor nodes produce data almost in real-time while tracking the objects in a critical area or monitoring border activities. The generated data is generally treated as big data and stored in NoSQL databases. In this paper, we present a new object tracking approach for surveillance applications developed using a big data model based on graphs and a multilevel fusion. Our approach consists of three main steps: intra-node fusion, inter-node fusion, and object trajectory construction. Intra-node fusion exploits the detection and tracking of objects in each sensor, while inter-node fusion uses spatio-temporal data and neighboring sensors. Then, the fused data of all sensor nodes are combined to construct global trajectories of the detected objects in the monitored area on the WMSN. We implemented a prototype system and evaluated the performance of the proposed approach with both a real dataset and a synthetic dataset. The results of our experiments on the two datasets show that the use of third-level fusion in addition to inter-node and intra-node fusions provides significantly better performance for object tracking in the WMSN applications.

AB - Wireless Multimedia Sensor Networks (WMSN), for object tracking, have been used as an emerging technology in different application areas, such as health care, surveillance, and traffic control. In surveillance applications, sensor nodes produce data almost in real-time while tracking the objects in a critical area or monitoring border activities. The generated data is generally treated as big data and stored in NoSQL databases. In this paper, we present a new object tracking approach for surveillance applications developed using a big data model based on graphs and a multilevel fusion. Our approach consists of three main steps: intra-node fusion, inter-node fusion, and object trajectory construction. Intra-node fusion exploits the detection and tracking of objects in each sensor, while inter-node fusion uses spatio-temporal data and neighboring sensors. Then, the fused data of all sensor nodes are combined to construct global trajectories of the detected objects in the monitored area on the WMSN. We implemented a prototype system and evaluated the performance of the proposed approach with both a real dataset and a synthetic dataset. The results of our experiments on the two datasets show that the use of third-level fusion in addition to inter-node and intra-node fusions provides significantly better performance for object tracking in the WMSN applications.

KW - Big data

KW - graph model

KW - multilevel fusion

KW - object tracking

KW - wireless multimedia sensor networks

UR - http://www.scopus.com/inward/record.url?scp=85067191564&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067191564&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2918765

DO - 10.1109/ACCESS.2019.2918765

M3 - Article

VL - 7

SP - 67818

EP - 67832

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8721634

ER -