Multi-sensor tracking with partly overlapping FoV using detection field of probability modeling and the GLMB filter

Liu, Weifeng; Liu, Qiliang; Chen, Yimei; Cui, Hui

doi:10.1186/s13634-022-00962-4

Cited by 3 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shen K et al [39] proposed the construction of extended label space mapping in his research, which overcomes the phenomenon of "label space mismatch" and uses labeled multi Bernoulli (LMB) filters to solve the problem of different perspectives in distributed sensor networks. Gostar A. K et al [40] proposed a novel consen-sus-based LMB filter that overcomes label space mismatch and is suitable for sensor multi-target differential perspective tracking; Nguyen H.V et al [41] improved tracking accuracy by considering the tracking error of multiple-target optimal sub-pattern as-signment (OSPA2); Wang X et al [42] conducted a Cauchy Schwarz divergence evaluation on each LMB component of the multi-sensor; and Liu W et al [43] used probability modeling detection fields and GLMB filters to improve the effectiveness of filters in the dis-tributed fusion of multiple sensors. Some scholars have made improvements in fusion methods.…”

Section: Introductionmentioning

confidence: 99%

Stochastic Outlier Selection via GM-CPHD Fusion for Multitarget Tracking Using Sensors With Different Fields of View

Wang,

Chen,

Zhang

et al. 2024

IEEE Sensors J.

View full text Add to dashboard Cite

In response to the issue of different perspectives affecting fusion accuracy in distributed multi-sensor multi-target tracking (DMMT), this study investigates the fusion strategies for multi-target tracking with different field-of-view sensors. We explore the impacts of different fields of view (FoVs) on the multi-sensor Geometric Average/Arithmetic Average (GA/AA), generalized covariance intersection (GCI) fusion strategies, and differential perspective boundary segmentation using examples. A Gaussian mixture cardinalized probability hypothesis density (GM-CPHD) fusion method for selecting random outliers in multi-target tracking based on limited perspective sensors is proposed. The boundary is segmented according to different perspectives, and the posterior intensity function is decomposed into multiple sub-intensities using Stochastic Outlier Selection(SOS) clustering. The distribution of the number of targets in the corresponding region is characterized using a multi Bernoulli reconstruction cardinal distribution. The complexity of the validation algorithm is sim-ilar to that of CPHD filtering. A simulation verifies the robustness and effectiveness of this method. By calculating OSPA(Optimal Sub-Pattern Assignment) and algorithm runtime, it can be verified that:the algorithm is more robust based on the reduction in detection probability and the increase in the clutter rate.

show abstract

Section: Introductionmentioning

confidence: 99%

Stochastic Outlier Selection via GM-CPHD Fusion for Multitarget Tracking Using Sensors With Different Fields of View

Wang,

Chen,

Zhang

et al. 2024

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

Simulation-based validation of process monitoring tasks in assembly

Gonnermann,

Kurscheid,

Schmucker

et al. 2024

Prod. Eng. Res. Devel.

View full text Add to dashboard Cite

The importance of process monitoring has increased significantly in today’s manufacturing landscape due to several factors. These factors include stricter quality standards, the presence of complex and diverse processes for customized products, and a focus on sustainability in energy and material consumption. In order to seamlessly integrate process monitoring into the production planning process, it is essential to automate the monitoring process planning while also taking into account production planning. Given the increasing importance of high-quality processes and products, assembly processes have become critical, as errors in assembly can lead to expensive production costs. However, generating and validating different process monitoring alternatives in assembly planning can be challenging because different processes and resources exist for different assembly plans. This research aims to solve this problem by providing a method to validate process monitoring alternatives more efficiently, thereby reducing the amount of manual effort and expert knowledge. This goal is achieved through automated validation using two simulation approaches: Collision Testing and Ray Casting. The results of this study are presented to demonstrate the effectiveness of the proposed solution.

show abstract

Multisensor Multitarget Tracking and Collision Avoidance Based on the Labeled RFS Void Probability and KL-PaC Cost Function

Liu

Zhao

et al. 2023

IEEE Sensors J.

View full text Add to dashboard Cite

Multi-sensor tracking with partly overlapping FoV using detection field of probability modeling and the GLMB filter

Cited by 3 publications

References 41 publications

Stochastic Outlier Selection via GM-CPHD Fusion for Multitarget Tracking Using Sensors With Different Fields of View

Stochastic Outlier Selection via GM-CPHD Fusion for Multitarget Tracking Using Sensors With Different Fields of View

Simulation-based validation of process monitoring tasks in assembly

Multisensor Multitarget Tracking and Collision Avoidance Based on the Labeled RFS Void Probability and KL-PaC Cost Function

Contact Info

Product

Resources

About