Saved in:
Bibliographic Details
Main Authors: Pinto, Juliano, Hess, Georg, Xia, Yuxuan, Wymeersch, Henk, Svensson, Lennart
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.17261
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909056767098880
author Pinto, Juliano
Hess, Georg
Xia, Yuxuan
Wymeersch, Henk
Svensson, Lennart
author_facet Pinto, Juliano
Hess, Georg
Xia, Yuxuan
Wymeersch, Henk
Svensson, Lennart
contents Multi-object tracking (MOT) is the task of estimating the state trajectories of an unknown and time-varying number of objects over a certain time window. Several algorithms have been proposed to tackle the multi-object smoothing task, where object detections can be conditioned on all the measurements in the time window. However, the best-performing methods suffer from intractable computational complexity and require approximations, performing suboptimally in complex settings. Deep learning based algorithms are a possible venue for tackling this issue but have not been applied extensively in settings where accurate multi-object models are available and measurements are low-dimensional. We propose a novel DL architecture specifically tailored for this setting that decouples the data association task from the smoothing task. We compare the performance of the proposed smoother to the state-of-the-art in different tasks of varying difficulty and provide, to the best of our knowledge, the first comparison between traditional Bayesian trackers and DL trackers in the smoothing problem setting.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17261
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing
Pinto, Juliano
Hess, Georg
Xia, Yuxuan
Wymeersch, Henk
Svensson, Lennart
Computer Vision and Pattern Recognition
Machine Learning
Multi-object tracking (MOT) is the task of estimating the state trajectories of an unknown and time-varying number of objects over a certain time window. Several algorithms have been proposed to tackle the multi-object smoothing task, where object detections can be conditioned on all the measurements in the time window. However, the best-performing methods suffer from intractable computational complexity and require approximations, performing suboptimally in complex settings. Deep learning based algorithms are a possible venue for tackling this issue but have not been applied extensively in settings where accurate multi-object models are available and measurements are low-dimensional. We propose a novel DL architecture specifically tailored for this setting that decouples the data association task from the smoothing task. We compare the performance of the proposed smoother to the state-of-the-art in different tasks of varying difficulty and provide, to the best of our knowledge, the first comparison between traditional Bayesian trackers and DL trackers in the smoothing problem setting.
title Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2312.17261