Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Feb 10;17(2):344.
doi: 10.3390/s17020344.

A Review of the Bayesian Occupancy Filter

Marcelo Saval-Calvo  1 , Luis Medina-Valdés  1 , José María Castillo-Secilla  2 , Sergio Cuenca-Asensi  1 , Antonio Martínezlvarez  3 , Jorge Villagrá  4
Affiliations

A Review of the Bayesian Occupancy Filter

Marcelo Saval-Calvo et al. Sensors (Basel). .

Abstract

Autonomous vehicle systems are currently the object of intense research within scientific and industrial communities; however, many problems remain to be solved. One of the most critical aspects addressed in both autonomous driving and robotics is environment perception, since it consists of the ability to understand the surroundings of the vehicle to estimate risks and make decisions on future movements. In recent years, the Bayesian Occupancy Filter (BOF) method has been developed to evaluate occupancy by tessellation of the environment. A review of the BOF and its variants is presented in this paper. Moreover, we propose a detailed taxonomy where the BOF is decomposed into five progressive layers, from the level closest to the sensor to the highest abstractlevelofriskassessment. Inaddition,wepresentastudyofimplementedusecasestoprovide a practical understanding on the main uses of the BOF and its taxonomy.

Keywords: ADAS; Bayesian Occupancy Filter (BOF); uncertainty management.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Relationship among Bayesian Occupancy Filter (BOF) techniques, institutions, authors, and publication dates. 1 University of Alcalá de Henares; 2 University of Edinburgh; 3 University of Cluj-Napoca.
Figure 2
Figure 2
Taxonomy of Bayesian Occupancy Filter.
Figure 3
Figure 3
Diagram of prediction and estimation paradigm with the observation input [15]. Reproduced with permission from reference [15]. Copyright 2008 International Journal of Vehicle Autonomous Systems.
Figure 4
Figure 4
BOF representation from [13]: A two-dimensional grid where each cell has an occupancy value and a histogram of possible velocities. Reproduced with permission from reference [13]. Copyright 2014 IEEE.
Figure 5
Figure 5
Aliasing problem: the area of an object counted in occupied cell number is not constant for each position of the object in the grid. Reproduced with permission from reference [30]. Copytight 2006 Inria.
Figure 6
Figure 6
Comparison of prediction results for different filtering techniques after several timesteps proposed by Gindele et al. [16] (Bayesian Occupancy Filter Using prior Map knowledge (BOFUM)). Reproduced with permission from reference [16]. Copyright 2009 IEEE. The image (a) shows the knowledge of the environment, (b) presents the initial occupancy and (c) the prediction without uncertainties. In the second row (e) represents the simple BOF prediction using only uncertainties. The BOFUM application is depicted in (f) without knowledge and in (g) and incorporating the knowledge. The legend shows the occupation probability normalized between 0 and 1.
Figure 7
Figure 7
Proposed representation in Hybrid Sampling Bayesian Occupancy Filter (HSBOF) [13]: a two-dimensional grid, to each cell we assigned an occupancy value, a static coefficient P(V=0) and a set of particles drawn along P(V=v|V≠0). Reproduced with permission from reference [13]. Copyright 2014 IEEE.
Figure 8
Figure 8
Fast Clustering-Tracking algorithm scheme extracted from Meckhnacha et al. [32]. Reproduced with permission from reference [32]. Copyright 2008 Springer.
See this image and copyright information in PMC

References

    1. Moravec H.P. Sensor Fusion in Certainty Grids for Mobile Robots. AI Mag. 1988;9:61–74.
    1. Elfes A. Using occupancy grids for mobile robot perception and navigation. Computer. 1989;22:46–57. doi: 10.1109/2.30720. - DOI
    1. Azorín-López J., Saval-Calvo M., Fuster-Guilló A., García-Rodríguez J. Human Behaviour Recognition based on Trajectory Analysis using Neural Networks; Proceedings of the 2013 International Joint Conference on Neural Networks (IJCNN); Dallas, TX, USA. 4–9 August 2013; pp. 99–105.
    1. Coue C., Fraichard T., Bessiere P., Mazer E. Using Bayesian Programming for multi-sensor multi-target tracking in automotive applications; Proceedings of the 2003 IEEE International Conference on Robotics and Automation (Cat. No. 03CH37422); Taipei, Taiwan. 14–19 September 2003; pp. 2104–2109.
    1. Kurdej M., Moras J., Cherfaoui V., Bonnifait P. Map-Aided Fusion Using Evidential Grids for Mobile Perception in Urban Environment. Springer; Berlin/Heidelberg, Germany: 2012. pp. 343–350.