2019 IEEE International Conference on Industrial Cyber Physical Systems (ICPS) 2019
DOI: 10.1109/icphys.2019.8780330
|View full text |Cite
|
Sign up to set email alerts
|

Comparative Study of Track-to-Track Fusion Methods for Cooperative Tracking with Bearings-only Measurements

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
6
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
2
1

Relationship

2
6

Authors

Journals

citations
Cited by 18 publications
(6 citation statements)
references
References 23 publications
0
6
0
Order By: Relevance
“…Thus, it is also of interest to evaluate the filter’s performance in real-world tasks. Potential application scenarios include orientation estimation using omnidirectional vision [ 5 ], visual tracking on unit hyperspheres [ 39 ], bearing-only localization in sensor networks [ 40 ], wavefront orientation estimation in the surveillance field [ 29 ] and sound source localization [ 41 ].…”
Section: Discussionmentioning
confidence: 99%
“…Thus, it is also of interest to evaluate the filter’s performance in real-world tasks. Potential application scenarios include orientation estimation using omnidirectional vision [ 5 ], visual tracking on unit hyperspheres [ 39 ], bearing-only localization in sensor networks [ 40 ], wavefront orientation estimation in the surveillance field [ 29 ] and sound source localization [ 41 ].…”
Section: Discussionmentioning
confidence: 99%
“…It is thus valuable to further investigate the difference between drawing samples from the approximated density and the true one. Moreover, by applying the proposed sampling approach to the Bingham-based pose filtering frameworks [4], [6], [34]- [36], a better performance regarding the tracking accuracy, efficiency, and robustness can be expected.…”
Section: Discussionmentioning
confidence: 99%
“…To be scalable with respect to the data load on the network, these approaches share preprocessed object lists rather than raw data. These object lists then are merged using a track-to-track (T2T) approach [26]. However, T2T fusion suffers from the problem that the incoming data has already been filtered and is therefore no longer statistically independent, as most Bayesian approaches require.…”
Section: A Related Workmentioning
confidence: 99%
“…However, T2T fusion suffers from the problem that the incoming data has already been filtered and is therefore no longer statistically independent, as most Bayesian approaches require. Hence, optimal T2T fusion requires effortful correction mechanisms [26]. In contrast, typically used sub-optimal fusion methods overestimate the covariance of the states of the objects.…”
Section: A Related Workmentioning
confidence: 99%