arXiv subjects

Jennifer Bondarchuk

Publications and source records attributed to Jennifer Bondarchuk.

4 recordsLinked to original sources

arXiv2025

Efficient Implementation of Multi-sensor Adaptive Birth Samplers for Labeled Random Finite Set Tracking

Adaptive track initiation remains a crucial component of many modern multi-target tracking systems. For labeled random finite sets multi-object filters, prior work has been established to construct a labeled multi-object birth density using measurements from multiple sensors. A naive construction of this adaptive birth set density results in an exponential number of newborn components in the number of sensors. A truncation procedure was provided that leverages a Gibbs sampler to truncate the birth density, reducing the complexity to quadratic in the number of sensors. However, only a limited discussion has been provided on additional algorithmic techniques that can be employed to substantially reduce the complexity in practical tracking applications. In this paper, we propose five efficiency enhancements for the labeled random finite sets multi-sensor adaptive birth procedure. Simulation results are provided to demonstrate their computational benefits and show that they result in a negligible change to the multi-target tracking performance.

eess.SP↗

arXiv2023

Multi-Target Tracking with Transferable Convolutional Neural Networks

Multi-target tracking (MTT) is a classical signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. In this paper, we revisit MTT from a deep learning perspective and propose a convolutional neural network (CNN) architecture to tackle it. We represent the target states and sensor measurements as images and recast the problem as an image-to-image prediction task. Then we train a fully convolutional model at small tracking areas and transfer it to much larger areas with numerous targets and sensors. This transfer learning approach enables MTT at a large scale and is also theoretically supported by our novel analysis that bounds the generalization error. In practice, the proposed transferable CNN architecture outperforms random finite set filters on the MTT task with 10 targets and transfers without re-training to a larger MTT task with 250 targets with a 29% performance improvement.

eess.SP↗

arXiv2023

Transferability of Convolutional Neural Networks in Stationary Learning Tasks

Recent advances in hardware and big data acquisition have accelerated the development of deep learning techniques. For an extended period of time, increasing the model complexity has led to performance improvements for various tasks. However, this trend is becoming unsustainable and there is a need for alternative, computationally lighter methods. In this paper, we introduce a novel framework for efficient training of convolutional neural networks (CNNs) for large-scale spatial problems. To accomplish this we investigate the properties of CNNs for tasks where the underlying signals are stationary. We show that a CNN trained on small windows of such signals achieves a nearly performance on much larger windows without retraining. This claim is supported by our theoretical analysis, which provides a bound on the performance degradation. Additionally, we conduct thorough experimental analysis on two tasks: multi-target tracking and mobile infrastructure on demand. Our results show that the CNN is able to tackle problems with many hundreds of agents after being trained with fewer than ten. Thus, CNN architectures provide solutions to these problems at previously computationally intractable scales.

cs.LG↗

arXiv2023

Deterministic Multi-sensor Measurement-adaptive Birth using Labeled Random Finite Sets

Measurement-adaptive track initiation remains a critical design requirement of many practical multi-target tracking systems. For labeled random finite sets multi-object filters, prior work has been established to construct a labeled multi-object birth density using measurements from multiple sensors. A truncation procedure has also been provided that leverages a stochastic Gibbs sampler to truncate the birth density for scalability. In this work, we introduce a deterministic herded Gibbs sampling truncation solution for efficient multi-sensor adaptive track initialization. Removing the stochastic behavior of the track initialization procedure without impacting average tracking performance enables a more robust tracking solution more suitable for safety-critical applications. Simulation results for linear sensing scenarios are provided to verify performance.

eess.SP↗