2014 IEEE Intelligent Vehicles Symposium Proceedings 2014
DOI: 10.1109/ivs.2014.6856554
|View full text |Cite
|
Sign up to set email alerts
|

Hybrid sampling Bayesian Occupancy Filter

Abstract: Abstract-Modeling and monitoring dynamic environments is a complex task but is crucial in the field of intelligent vehicle. A traditional way of addressing these issues is the modeling of moving objects, through Detection And Tracking of Moving Objects (DATMO) methods. An alternative to a classic object model framework is the occupancy grid filtering domain. Instead of segmenting the scene into objects and track them, the environment is represented as a regular grid of occupancy, in which each cell is tracked … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
66
0

Year Published

2015
2015
2021
2021

Publication Types

Select...
4
3
1

Relationship

2
6

Authors

Journals

citations
Cited by 61 publications
(67 citation statements)
references
References 13 publications
1
66
0
Order By: Relevance
“…Real-time MSF computation with a growing number of cells and sensors is also challenging. To accelerate MSF, parallel implementations in GPUs [15,16] or manycore platforms [17] have been proposed but they still use floating-point representation for probability estimation and fusion. Unfortunately, requiring floating-point support hinders the integration of OG-based MSF on highly constrained embedded platforms.…”
Section: B Sensor Data Fusion and Occupancy Grid Calculationmentioning
confidence: 99%
“…Real-time MSF computation with a growing number of cells and sensors is also challenging. To accelerate MSF, parallel implementations in GPUs [15,16] or manycore platforms [17] have been proposed but they still use floating-point representation for probability estimation and fusion. Unfortunately, requiring floating-point support hinders the integration of OG-based MSF on highly constrained embedded platforms.…”
Section: B Sensor Data Fusion and Occupancy Grid Calculationmentioning
confidence: 99%
“…Another alternative to the object-based approaches are the grid-based approaches, like the Bayesian Occupancy Filter [6], or its extension HybridSampling Bayesian Occupancy Filter (HSBOF) [7], which represents the environment as a probabilistic occupancy grid. This framework allows to model both the static and the dynamic environment, by estimating velocity probability distributions for each cell in the grid.…”
Section: Related Workmentioning
confidence: 99%
“…The Hybrid Sampling Bayesian Occupancy Filter (HSBOF) [7] is a Bayesian filtering perception technique which models the environment at a sub-object level, in term of spatial occupancy and dynamics. The surrounding of the subject is divided into cells, to which are associated random variables, symbolizing their occupancies and velocities.…”
Section: Hsbof Presentationmentioning
confidence: 99%
“…Real-time MSF computation with a growing number of cells and sensors is challenging. To accelerate MSF, parallel implementation in GPUs [4], [5] or many-core platforms [6] have been proposed. All these attempts use floating-point representation for probability estimation and fusion.…”
Section: Introductionmentioning
confidence: 99%