Information based distributed multi sensor multi target tracking
Abstract
The objective of this proposal is to develop the underpinning methods required for autonomous distributed sensor managment and fusion in challenging multi target environments. This will involve the development of algorithms that are able to automatically track multiple targets, classify, and allocate resources based on information received from multiple platforms with data association uncertainty and high false alarm rates. Building on recent developments by the investigators in multi target tracking and distributed sensor fusion, this work programme will develop methods for autonomous sensor allocation in large scale multi sensor multi target tracking applications based on information theoretic criteria. This will be achieved by re evaluating the key tools in information theory applied to the challenges of multi target surveillance based on point process theory, which is designed to accommodate uncertainty in the states of individual targets and the target number. The information theoretic methods developed will be applied to multi sensor problems to enable decisions to be made on how to allocate sensor resources in addition to refining the knowledge of the scene. The tools developed will help reduce the labour intensive burden of monitoring single sensor feeds, and enable adaptive decisions to be taken to optimise the operation of multi modal networks and enhance the overall knowledge of the surveillance region. The focus on information theoretic representations of multi target tracking scenarios will enable verification of whether sensor feeds can be reliably fused, to avoid the potential of data corruption. The project will deliver key advanced in intelligent sensing to enable the continuous and adaptive surveillance in dynamic environments. These will be scaleable for large scale tracking of many targets from multiple distributed sensors.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jan 14, 2022
- Source ID
- FA95501917008
Entities
People
- Daniel Clark
Organizations
- Air Force Office of Scientific Research
- United States Air Force