2018 IEEE/ION Position, Location and Navigation Symposium (PLANS) 2018
DOI: 10.1109/plans.2018.8373383
|View full text |Cite
|
Sign up to set email alerts
|

Improvements in pedestrian movement prediction by considering multiple intentions in a Multi-Hypotheses filter

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
5
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 16 publications
0
5
0
Order By: Relevance
“…The prediction of pedestrian behaviour is becoming an increasingly popular research field (Ridel, Rehder, Lauer, Stiller, & Wolf, 2018). It is assessed using different general and more sophisticated methods known in traffic planning theory (Fang, Li, Yu, Guo, & Ma, 2019;Hartmann, Ferrara, & Watzenig, 2018;Hartmann, Stolz, & Watzenig, 2018;Particke, Hiller, Feist, & Thielecke, 2018;Wu, Ruenz, & Althoff, 2018). The pedestrian movement, however, is less predictive than motorised traffic.…”
Section: Perceived Benefits From Adding New Pedestrian Bridges To Eximentioning
confidence: 99%
“…The prediction of pedestrian behaviour is becoming an increasingly popular research field (Ridel, Rehder, Lauer, Stiller, & Wolf, 2018). It is assessed using different general and more sophisticated methods known in traffic planning theory (Fang, Li, Yu, Guo, & Ma, 2019;Hartmann, Ferrara, & Watzenig, 2018;Hartmann, Stolz, & Watzenig, 2018;Particke, Hiller, Feist, & Thielecke, 2018;Wu, Ruenz, & Althoff, 2018). The pedestrian movement, however, is less predictive than motorised traffic.…”
Section: Perceived Benefits From Adding New Pedestrian Bridges To Eximentioning
confidence: 99%
“…As the transition model involves highly nonlinear GPFA, we employ a Multi-hypothesis Particle Filter to estimate the likely intent [29]. Initially, each particle sampled will be assigned a hypothesis on pedestrian intent I i .…”
Section: Pedestrian Intent Estimation (Pie ) Modulementioning
confidence: 99%
“…In contrast to the method presented in [29], the weights of particles with the same intent hypothesis are summed to generate the probability distribution of different intents at that time stamp. Sequential importance re-sampling is implemented after the weights are updated.…”
Section: Pedestrian Intent Estimation (Pie ) Modulementioning
confidence: 99%
See 2 more Smart Citations