Fast Object Extraction from Bayesian Occupancy Grids using Self Organizing Networks

Vasquez, Dizan; Romanelli, Fabrizio; Fraichard, Thierry; Laugier, Christian

doi:10.1109/icarcv.2006.345364

Cited by 6 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Standard data clustering techniques may be used on either point clouds or evidence grids [7]. There are also studies particular to segmentation in point clouds [5] and in evidence grids [12]. However, while useful for finding certain foreground features, these methods do not directly address the problem of background subtraction and accessibility.…”

Section: A Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

Background subtraction and accessibility analysis in evidence grids

Anderson-Sprecher

Simmons

Huber

2011

2011 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-Evidence grids are a popular representation for fused data from multiple sensors. Previous attempts at background subtraction within evidence grids either do so prior to sensor fusion or do so naively, simply ignoring any cells with a high background occupancy probability. A key weakness of these approaches is that they cannot reason about interiors of objects or other unobserved regions. Recognizing and removing solid object interiors is important for any application that must be able to differentiate between occupied and unknown space after background subtraction.In this paper, we propose accessibility analysis as a method for the removal of interior regions. We then present and compare two approaches for performing background subtraction with accessibility analysis in evidence grids. Performance is measured using a 3D evidence grid in a test bed for a sensing system designed for use in safety monitoring of an automated assembly workcell. Within the parameters of the present study, both techniques allow for precise detection of foreground objects while fully removing background objects. Subtraction runs in near real-time, even for large grids.

show abstract

Section: A Prior Workmentioning

confidence: 99%

“…Now we can define our configuration space grid G E R based on the background probability grid G B , using (12). Also, from here on we choose to work in the negative log space for computational stability.…”

Section: A Configuration Space Probabilitiesmentioning

confidence: 99%

Background subtraction and accessibility analysis in evidence grids

Anderson-Sprecher

Simmons

Huber

2011

2011 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…Mohamed et al [3] and Chiu et al [4] integrated the CC algorithm to search bounding boxes for tracking foreground objects. Dizan et al [5] developed a fast object extraction algorithm using the CC algorithm for relabeling nodes. Liu et al [6] performed object detection and tracking in real time by combining the CC algorithm for containing all connected regions.…”

Section: Introductionmentioning

confidence: 99%

Directional Connected Components Algorithm Based on Gradient Information

Chang

Chiu

2014

2014 International Symposium on Computer, Consumer and Control

View full text Add to dashboard Cite

This paper presents a directional connected components algorithm that overcomes the problem of overlapping components by gradient information. The proposed algorithm replaces the binary matrix with the directional matrix that contains the gradient information. The directional matrix contains both the gradient magnitude and angle and provides the merge decisions of neighboring pixels for solving the problem of overlapping edges. The proposed algorithm improves the performance of the connected components algorithm in the classification of features and candidates using edge information. Experimental results demonstrate that the proposed algorithm can resolve the problem of overlapping components, and prevent false connections between components and background under various circumstances.

show abstract

“…After that, object extraction is done by means of a clustering algorithm based on Self Organizing Networks (SON) which, in previous works, has been applied to images [13] and occupancy grids [14], showing that it is able to produce good results in real time. This paper improves the clustering algorithm by enabling it to process continuous input pixel values while maintaining a linear complexity with respect to the size of the input image.…”

Section: Introductionmentioning

confidence: 99%

A novel approach for object extraction from video sequences based on continuous background/foreground classification

Bellardi

Ríos-Martínez

Vasquez

et al. 2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

In many computer vision related applications it is necessary to distinguish between the background of an image and the objects that are contained in it. This is a difficult problem because of the constraints imposed by the available time and the computational cost of robust object extraction algorithms.This report describes a new method that benefits from state of the art background/foreground classification combined with the strong theoretical foundations of clustering. The pixels on the scene background are modeled as Mixtures of Gaussians and the output of the classification process are continuous values representing the likelihood that each pixel belongs to the foreground. The clustering is based on a Self Organizing Network (SON) which has a robust initialization schema and is able to find the number of objects in an image or grid. The algorithm's complexity is linear with respect to the number of pixels or cells.

show abstract

Fast Object Extraction from Bayesian Occupancy Grids using Self Organizing Networks

Cited by 6 publications

References 16 publications

Background subtraction and accessibility analysis in evidence grids

Background subtraction and accessibility analysis in evidence grids

Directional Connected Components Algorithm Based on Gradient Information

A novel approach for object extraction from video sequences based on continuous background/foreground classification

Contact Info

Product

Resources

About