297 citations · 1.6k across the 43 of their papers we have counts for
47 papers
Poisson multi-Bernoulli mixture filter with general target-generated measurements and arbitrary clutter
Ángel F. García-Fernández, Yuxuan Xia, Lennart Svensson
This paper shows that the Poisson multi-Bernoulli mixture (PMBM) density is a multi-target conjugate prior for general target-generated measurement distributions and arbitrary clut…
Deep Fusion of Multi-Object Densities Using Transformer
Lechi Li, Chen Dai, Yuxuan Xia +1
In this paper, we demonstrate that deep learning based method can be used to fuse multi-object densities. Given a scenario with several sensors with possibly different field-of-vie…
A comparison between PMBM Bayesian track initiation and labelled RFS adaptive birth
Ángel F. García-Fernández, Yuxuan Xia, Lennart Svensson
This paper provides a comparative analysis between the adaptive birth model used in the labelled random finite set literature and the track initiation in the Poisson multi-Bernoull…
Trajectory PMB Filters for Extended Object Tracking Using Belief Propagation
Yuxuan Xia, Ángel F. García-Fernández, Florian Meyer +3
In this paper, we propose a Poisson multi-Bernoulli (PMB) filter for extended object tracking (EOT), which directly estimates the set of object trajectories, using belief propagati…
Multiple Object Trajectory Estimation Using Backward Simulation
Yuxuan Xia, Lennart Svensson, Ángel F. García-Fernández +3
This paper presents a general solution for computing the multi-object posterior for sets of trajectories from a sequence of multi-object (unlabelled) filtering densities and a mult…
DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision
Erik Wallin, Lennart Svensson, Fredrik Kahl +1
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular. SSL is a family of methods, which in addition to a labeled traini…
PMBM-based SLAM Filters in 5G mmWave Vehicular Networks
Hyowon Kim, Karl Granström, Lennart Svensson +2
Radio-based vehicular simultaneous localization and mapping (SLAM) aims to localize vehicles while mapping the landmarks in the environment. We propose a sequence of three Poisson…
Object Detection as Probabilistic Set Prediction
Georg Hess, Christoffer Petersson, Lennart Svensson
Accurate uncertainty estimates are essential for deploying deep object detectors in safety-critical systems. The development and evaluation of probabilistic object detectors have b…
Can Deep Learning be Applied to Model-Based Multi-Object Tracking?
Juliano Pinto, Georg Hess, William Ljungbergh +3
Multi-object tracking (MOT) is the problem of tracking the state of an unknown and time-varying number of objects using noisy measurements, with important applications such as auto…
Tracking multiple spawning targets using Poisson multi-Bernoulli mixtures on sets of tree trajectories
Ángel F. García-Fernández, Lennart Svensson
This paper proposes a Poisson multi-Bernoulli mixture (PMBM) filter on the space of sets of tree trajectories for multiple target tracking with spawning targets. A tree trajectory…
A time-weighted metric for sets of trajectories to assess multi-object tracking algorithms
Ángel F. García-Fernández, Abu Sajana Rahmathullah, Lennart Svensson
This paper proposes a metric for sets of trajectories to evaluate multi-object tracking algorithms that includes time-weighted costs for localisation errors of properly detected ta…
An Uncertainty-Aware Performance Measure for Multi-Object Tracking
Juliano Pinto, Yuxuan Xia, Lennart Svensson +1
Evaluating the performance of multi-object tracking (MOT) methods is not straightforward, and existing performance measures fail to consider all the available uncertainty informati…
Extended Object Tracking Using Sets Of Trajectories with a PHD Filter
Jakob Sjudin, Martin Marcusson, Lennart Svensson +1
PHD filtering is a common and effective multiple object tracking (MOT) algorithm used in scenarios where the number of objects and their states are unknown. In scenarios where each…
Next Generation Multitarget Trackers: Random Finite Set Methods vs Transformer-based Deep Learning
Juliano Pinto, Georg Hess, William Ljungbergh +3
Multitarget Tracking (MTT) is the problem of tracking the states of an unknown number of objects using noisy measurements, with important applications to autonomous driving, survei…
A Poisson multi-Bernoulli mixture filter for coexisting point and extended targets
Ángel F. García-Fernández, Jason L. Williams, Lennart Svensson +1
This paper proposes a Poisson multi-Bernoulli mixture (PMBM) filter for coexisting point and extended targets, i.e., for scenarios where there may be simultaneous point and extende…
Backward Simulation for Sets of Trajectories
Yuxuan Xia, Lennart Svensson, Ángel F. García-Fernández +2
This paper presents a solution for recovering full trajectory information, via the calculation of the posterior of the set of trajectories, from a sequence of multitarget (unlabell…
DACS: Domain Adaptation via Cross-domain Mixed Sampling
Wilhelm Tranheden, Viktor Olsson, Juliano Pinto +1
Semantic segmentation models based on convolutional neural networks have recently displayed remarkable performance for a multitude of applications. However, these models typically…
ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning
Viktor Olsson, Wilhelm Tranheden, Juliano Pinto +1
The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, p…
Exploiting Diffuse Multipath in 5G SLAM
Yu Ge, Hyowon Kim, Fuxi Wen +3
5G millimeter wave (mmWave) signals can be used to jointly localize the receiver and map the propagation environment in vehicular networks, which is a typical simultaneous localiza…
Trajectory Poisson multi-Bernoulli filters
Ángel F. García-Fernández, Lennart Svensson, Jason L. Williams +2
This paper presents two trajectory Poisson multi-Bernoulli (TPMB) filters for multi-target tracking: one to estimate the set of alive trajectories at each time step and another to…
Spatiotemporal Constraints for Sets of Trajectories with Applications to PMBM Densities
Karl Granström, Lennart Svensson, Yuxuan Xia +2
In this paper we introduce spatiotemporal constraints for trajectories, i.e., restrictions that the trajectory must be in some part of the state space (spatial constraint) at some…
A general framework for ensemble distribution distillation
Jakob Lindqvist, Amanda Olmin, Fredrik Lindsten +1
Ensembles of neural networks have been shown to give better performance than single networks, both in terms of predictions and uncertainty estimation. Additionally, ensembles allow…
Bayesian Linear Regression on Deep Representations
John Moberg, Lennart Svensson, Juliano Pinto +1
A simple approach to obtaining uncertainty-aware neural networks for regression is to do Bayesian linear regression (BLR) on the representation from the last hidden layer. Recent w…
Poisson Multi-Bernoulli Mixtures for Sets of Trajectories
Karl Granström, Lennart Svensson, Yuxuan Xia +2
The Poisson Multi-Bernoulli Mixture (PMBM) density is a conjugate multi-target density for the standard point target model with Poisson point process birth. This means that both th…