Related papers: On point processes in multitarget tracking
In this paper, we propose a highly practical fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed method is based on the Gaussian mixture probability hypothesis…
Instance perception tasks (object detection, instance segmentation, pose estimation, counting) play a key role in industrial applications of visual models. As supervised learning methods suffer from high labeling cost, few-shot learning…
We propose an efficient random finite set (RFS) based algorithm for multiobject tracking in which the object states are modeled by a combination of a labeled multi-Bernoulli (LMB) RFS and a Poisson RFS. The less computationally demanding…
A Multiple Target, Multiple Type Filtering (MTMTF) algorithm is developed using Random Finite Set (RFS) theory. First, we extend the standard Probability Hypothesis Density (PHD) filter for multiple types of targets, each with distinct…
The pair correlation function is introduced to target tracking filters that use a finite point process target model as a means to investigate interactions in the Bayes posterior target process. It is shown that the Bayes posterior target…
FSS(Few-shot segmentation) aims to segment a target class using a small number of labeled images(support set). To extract information relevant to the target class, a dominant approach in best-performing FSS methods removes background…
In this work, we develop tracking and estimation techniques relevant to underwater targets. Particularly, we explore particle filtering techniques for target tracking. It is a numerical approximation method for implementing a recursive…
Modern deep learning systems are increasingly deployed in situations such as personalization and federated learning where it is necessary to support i) learning on small amounts of data, and ii) communication efficient distributed training…
We employ electrostatic conversion drift calculations to match CCD pixel signal covariances observed in flat field exposures acquired using candidate sensor devices for the LSST Camera. We thus constrain pixel geometry distortions present…
Estimation of the Fisher Information Metric (FIM-estimation) is an important task that arises in unsupervised learning of phase transitions, a problem proposed by physicists. This work completes the definition of the task by defining…
We propose a solution of the multiple target tracking (MTT) problem based on sets of trajectories and the random finite set framework. A full Bayesian approach to MTT should characterise the distribution of the trajectories given the…
The objective of Few-shot learning is to fully leverage the limited data resources for exploring the latent correlations within the data by applying algorithms and training a model with outstanding performance that can adequately meet the…
In this paper, we explore incremental few-shot object detection (iFSD), which incrementally learns novel classes using only a few examples without revisiting base classes. Previous iFSD works achieved the desired results by applying…
Targets that generate multiple measurements at a given instant in time are commonly known as extended targets. These present a challenge for many tracking algorithms, as they violate one of the key assumptions of the standard measurement…
The objective of traffic prediction is to accurately forecast and analyze the dynamics of transportation patterns, considering both space and time. However, the presence of distribution shift poses a significant challenge in this field, as…
Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL). While the concept of FSL is not new in tracking and has been previously applied by prior works, most of them are tailored to fit specific types of FSL…
In radar systems, tracking targets in low signal-to-noise ratio (SNR) environments is a very important task. There are some algorithms designed for multitarget tracking. Their performances, however, are not satisfactory in low SNR…
This paper tackles one of the most fundamental goals in functional time series analysis which is to provide reliable predictions for future functions. Existing methods for predicting a complete future functional observation use only…
Accurate traffic flow prediction remains a fundamental challenge in intelligent transportation systems, particularly in cross-domain, data-scarce scenarios where limited historical data hinders model training and generalisation. The complex…
Discriminative Correlation Filters based tracking algorithms exploiting conventional handcrafted features have achieved impressive results both in terms of accuracy and robustness. Template handcrafted features have shown excellent…