A Gaussian Process Convolution Particle Filter for Multiple Extended Objects Tracking with Non-Regular Shapes

Abstract

Extended object tracking has become an integral part of various autonomous systems in diverse fields. Although it has been extensively studied over the past decade, many complex challenges remain in the context of extended object tracking. In this paper, a new method for tracking multiple irregularly shaped extended objects using surface measurements is proposed. The Gaussian Process Convolution Particle Filter proposed in [1], designed to track a single extended/group object, is enhanced for tracking multiple extended objects. A convolution kernel is proposed to estimate the multi-object likelihood. A target birth/death model based on the proposed method is also introduced for automatic initiation and deletion of the objects. The proposed approach is validated on real-world LiDAR data which shows that the method is efficient in tracking multiple irregularly shaped extended objects in challenging scenarios involving occlusion, dense clutter and low object detection.

Gaussian‐like measurement likelihood based particle filter for extended target tracking

“…The combination of Rao-Blackwellised particle filter with Gaussian process regression for shape estimation is given in [22]. Moreover, a measurement likelihood based on the areas of the target's shape and surveillance region is adopted into the kernel function of the convolution particle filter [23]. A closed-form measurement likelihood (CL) for particle filters based on the Fourier series expansion has been derived in [24].…”

Tracking of Maneuvering Star-Convex Extended Target Using Modified Adaptive Extended Kalman Filter

“…In [18], a Rao-Blackwellized particle filter is designed to exploit the conditional linear Gaussian structure of the GP parameters. In addition, Aftab [19] proposed a Gaussian process convolution particle filter that does not depend on any prior knowledge of the measurement statistics and an analytical expression of the likelihood function. Freitas [20] designed the box particle filter, which replaces traditional multiple measurements with a rectangular region of the nonzero volume in the state space to deal with extended targets; however, the computational complexity of these filters increases rapidly with increasing state dimension.…”

On the Impact of Different Kernels and Training Data on a Gaussian Process Approach for Target Tracking

“…Historically, model-based approaches have been applied for solving target tracking problems. Recently, machine-learning based model-free methods have been proposed either as a complete solution [6] or in a hybrid setup [7], [8]. Hybrid methods combine model-based and model-free methods for target tracking.…”