Localization and Tracking of Uncontrollable Underwater Agents: Particle Filter Based Fusion of On-Body IMUs and Stationary Cameras
Ding Zhang · Joaquin Gabaldon · L. Lauderdale · M. Johnson-Roberson · L. Miller · K. Barton · K. A. Shorter
TL;DR
A particle filter fuses on-body motion tags with overhead cameras to localize and track free-swimming dolphins, even when camera views are sparse.
BRIEF
Tracking animals that no one can steer is hard, especially underwater where cameras see them only some of the time. This work locates dolphins in a known habitat by combining two sources: a tag on each animal that records motion, speed and depth, and a pair of cameras mounted above the habitat. A particle filter with a fuzzy observation model decides which camera detection belongs to which tagged animal. It handles nonlinear motion, non-Gaussian noise and sparse camera views while keeping the position estimate reliable over long periods of free movement.
Abstract
Tracking of uncontrollable agents in a controlled environment is an important research question for the coordination of controllable and uncontrollable agents and bio-inspired multi-agent control. This paper presents a framework that approaches the multiagent tracking problem from a localization perspective, utilizing a combination of wearable sensors and stationary cameras. Specifically, this framework was applied to localize uncontrollable biological agents (dolphins) in a well defined environment. The biological agents were outfitted with wearable sensors (IMU, speed, depth) and were free to move in their three dimensional habitat. The dynamic data collected by the wearable sensors was supplemented with image data collected using a pair of cameras mounted above the habitat. The framework presented in this paper combines data from these sensor streams to calculate an accurate estimate of the animal’s location during extended periods of free movement. The associations between camera detections and tagged agents are handled using a particle filter embedded with a fuzzy observation concept. The platform is readily implementable in similar water / land environments, and is able to handle nonlinear agent dynamics, non-Gaussian noise, and sparse camera observations while maintaining robust agent localization and tracking.