2015/05/07 by Mark R. Leonard, Abdelhak M. Zoubir, Leonard, Mark R. +1
Computer Science · #68 #Applications (stat.AP) #Distributed Sensor Networks and Detection Algorithms #FOS: Computer and information sciences #FOS: Electrical engineering #Multiagent Systems (cs.MA) #Systems and Control (eess.SY) #Target Tracking and Data Fusion in Sensor Networks #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1505.01668
openalex publication_date 2015/05/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Multi-target tracking is an important problem in civilian and military\napplications. This paper investigates multi-target tracking in distributed\nsensor networks. Data association, which arises particularly in multi-object\nscenarios, can be tackled by various solutions. We consider sequential Monte\nCarlo implementations of the Probability Hypothesis Density (PHD) filter based\non random finite sets. This approach circumvents the data association issue by\njointly estimating all targets in the region of interest. To this end, we\ndevelop the Diffusion Particle PHD Filter (D-PPHDF) as well as a centralized\nversion, called the Multi-Sensor Particle PHD Filter (MS-PPHDF). Their\nperformance is evaluated in terms of the Optimal Subpattern Assignment (OSPA)\nmetric, benchmarked against a distributed extension of the Posterior\nCram 'er-Rao Lower Bound (PCRLB), and compared to the performance of an\nexisting distributed PHD Particle Filter. Furthermore, the robustness of the\nproposed tracking algorithms against outliers and their performance with\nrespect to different amounts of clutter is investigated.\n