Cell Multi-Bernoulli (Cell-MB) Sensor Control for Multi-object Search-While-Tracking (SWT)

TL;DR

This paper introduces a computationally efficient approximation for information gain in multi-object tracking, accounting for realistic measurement imperfections, and demonstrates its effectiveness in real-world search-while-tracking scenarios.

Contribution

It presents a novel, tractable approximation of RFS expected information gain that incorporates noise, missed detections, false alarms, and object dynamics for sensor control.

Findings

Effective in multi-vehicle search-while-tracking experiments

Handles noisy measurements and false alarms robustly

Improves sensor control decisions in complex environments

Abstract

Information-driven control can be used to develop intelligent sensors that can optimize their measurement value based on environmental feedback. In object tracking applications, sensor actions are chosen based on the expected reduction in uncertainty also known as information gain. Random finite set (RFS) theory provides a formalism for quantifying and estimating information gain in multi-object tracking problems. However, estimating information gain in these applications remains computationally challenging. This paper presents a new tractable approximation of the RFS expected information gain applicable to sensor control for multi-object search and tracking. Unlike existing RFS approaches, the information gain approximation presented in this paper considers the contributions of non-ideal noisy measurements, missed detections, false alarms, and object appearance/disappearance. The effectiveness of the information-driven sensor control is demonstrated through two multi-vehicle search-while-tracking experiments using real video data from remote terrestrial and satellite sensors.