Full View Maximum Coverage of Camera Sensors: Moving Object Monitoring

The study focuses on achieving full view coverage in a camera sensor network to effectively monitor moving objects from multiple perspectives. Three key issues are addressed: camera direction selection, location selection, and moving object monitoring. There are three steps to maximize coverage of m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:ACM transactions on sensor networks 2024-04, Vol.20 (3), p.1-23, Article 63
Hauptverfasser: Du, Hongwei, Su, Jingfang, Zhang, Zhao, Duan, Zhenhua, Tian, Cong, Du, Ding-Zhu
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The study focuses on achieving full view coverage in a camera sensor network to effectively monitor moving objects from multiple perspectives. Three key issues are addressed: camera direction selection, location selection, and moving object monitoring. There are three steps to maximize coverage of moving targets. The first step involves proposing the Maximum Group Set Coverage (MGSC) algorithm, which selects the camera sensor direction for traditional target coverage. In the second step, a composed target merged from a set of fixed directional targets represents multiple views of a moving object. Building upon the MGSC algorithm, the Maximum Group Set Coverage with Composed Targets (MGSC-CT) algorithm is presented to determine camera sensor directions that cover subsets of fixed directional targets. Additionally, a constraint on the number of cameras is imposed for camera location selection, leading to the study of the Maximum Group Set Coverage with Size Constraint (MGSC-SC) algorithm. Each of these steps formulates a problem on group set coverage and provides an algorithmic solution. Furthermore, improved versions of MGSC-CT and MGSC-SC are developed to enhance the coverage speed. Computer simulations are employed to demonstrate the significant performance of the algorithms.
ISSN:1550-4859
1550-4867
DOI:10.1145/3649314