SciTePress - Affiliation Profile

Aalborg University, Denmark

Context (please use complete words only)

Field

Sort by

4 Papers

A THREE-LEVEL ARCHITECTURE FOR MODEL–FREE DETECTION AND TRACKING OF INDEPENDENTLY MOVING OBJECTS

Topics: Image-Based Modeling and 3D Reconstruction; Motion and Tracking; Stereo Vision and Structure from Motion; Detecting 3D Objects Using Patterns of Motion and Appearance

Authors: Nicolas Pugeault ¹ , Karl Pauwels ² , Mark M. Van Hulle ² , Florian Pilz ³ and Norbert Krüger ⁴

Affiliations: ¹ University of Surrey, United Kingdom , ² Katholieke Universiteit Leuven, Belgium , ³ Aalborg Universitet Copenhagen, Denmark , ⁴ University of Southern Denmark, Denmark

Digital Object Identifier: 10.5220/0002838002370244

Proceedings of VISAPP 2010/VISIGRAPP, ISBN: 978-989-674-028-3

Quick Abstract

We present a three–level architecture for detection and tracking of independently moving objects (IMOs) in sequences recorded from a moving vehicle. At the first stage, image pixels with an optical flow that is not entirely induced by the car’s motion are detected by combining dense optical flow, egomotion extracted from this optical flow, and dense stereo. These pixels are segmented and an attention mechanism is used to process them at finer resolution at the second level making use of sparse 2D and 3D edge descriptors. Based on the rich and precise information on the second level, the full rigid motion for the environment and for each IMO is computed. This motion information is then used for tracking, filtering and the building of a 3D model of the street structure as well as the IMO. This multi-level architecture allows us to combine the strength of both dense and sparse processing methods in terms of precision and computational complexity, and to dedicate more processing capacity to the important parts of the scene (the IMOs).

Related Ontology Subjects/Areas/Topics (13)

Applications	Image-Based Modeling	Pattern Recognition
Computer Vision, Visualization and Computer Graphics	Methodologies and Methods	Physiological Computing Systems
Detecting 3D Objects Using Patterns of Motion and Appearance	Motion and Tracking	Software Engineering
Geometry and Modeling	Motion, Tracking and Stereo Vision	Stereo Vision and Structure from Motion
Human-Computer Interaction

ROAD INTERPRETATION FOR DRIVER ASSISTANCE BASED ON AN EARLY COGNITIVE VISION SYSTEM

Topics: Image-Based Modeling and 3D Reconstruction; Statistical Approach; Early Vision and Image Representation; Visual Navigation; Cognitive & Biologically Inspired Vision; 2D and 3D Scene Understanding

Authors: Emre Başeski ¹ , Lars Baunegaard With Jensen ¹ , Nicolas Pugeault ¹ , Florian Pilz ² , Karl Pauwels ³ , Marc M. Van Hulle ³ , Florentin Wörgötter ⁴ and Norbert Krüger ¹

Affiliations: ¹ The Mærsk Mc-Kinney Møller Institute, Univeristy of Southern Denmark, Denmark , ² Department for Media Technology, Aalborg University Copenhagen, Denmark , ³ Laboratorium voor Neuro- en Psychofysiologie, Belgium , ⁴ Bernstein Center for Computational Neuroscience, University of Göttingen, Germany

Digital Object Identifier: 10.5220/0001796104960505

Proceedings of VISAPP 2009/VISIGRAPP, ISBN: 978-989-8111-69-2

Quick Abstract

In this work, we address the problem of road interpretation for driver assistance based on an early cognitive vision system. The structure of a road and the relevant traffic are interpreted in terms of ego-motion estimation of the car, independently moving objects on the road, lane markers and large scale maps of the road. We make use of temporal and spatial disambiguation mechanisms to increase the reliability of visually extracted 2D and 3D information. This information is then used to interpret the layout of the road by using lane markers that are detected via Bayesian reasoning. We also estimate the ego-motion of the car which is used to create large scale maps of the road and also to detect independently moving objects. Sample results for the presented algorithms are shown on a stereo image sequence, that has been collected from a structured road.

Related Ontology Subjects/Areas/Topics (11)

Applications	Image and Video Analysis	Software Engineering
Computer Vision, Visualization and Computer Graphics	Image-Based Modeling	Statistical Approach
Early Vision and Image Representation	Motion, Tracking and Stereo Vision	Visual Navigation
Geometry and Modeling	Pattern Recognition

A SIGNAL-SYMBOL LOOP MECHANISM FOR ENHANCED EDGE EXTRACTION

Topic: Cognitive & Biologically Inspired Vision

Authors: Sinan Kalkan ¹ , Florentin Wörgötter ¹ , Shi Yan ² , Volker Krüger ² and Norbert Krüger ³

Affiliations: ¹ Bernstein Center for Computational Neuroscience, Univ. of Göttingen, Germany , ² Medialogy Lab, Aalborg Univ., Denmark , ³ Cognitive Vision Lab, Univ. of Southern Denmark, Denmark

Digital Object Identifier: 10.5220/0001077602140221

Proceedings of VISAPP 2008/VISIGRAPP, ISBN: 978-989-8111-21-0

Quick Abstract

The transition to symbolic information from images involves in general the loss or misclassification of information. One way to deal with this missing or wrong information is to get feedback from concrete hypotheses derived at a symbolic level to the sub-symbolic (signal) stage to amplify weak information or correct misclassifications. This paper proposes such a feedback mechanism between the symbolic level and the signal level, which we call signal symbol loop. We apply this framework for the detection of low contrast edges making use of predictions based on Rigid Body Motion. Once the Rigid Body Motion is known, the location and the properties of edges at a later frame can be predicted. We use these predictions as feedback to the signal level at a later frame to improve the detection of low contrast edges. We demonstrate our mechanism on a real example, and evaluate the results using an artificial scene, where the ground truth data is available.

IMPROVING JUNCTION DETECTION BY SEMANTIC INTERPRETATION

Topics: Feature Extraction; Early Vision and Image Representation

Authors: Sinan Kalkan ¹ , Shi Yan ² , Florian Pilz ² and Norbert Krüger ³

Affiliations: ¹ Bernstein Centre for Computational Neuroscience, Univ. of Göttingen, Germany , ² Medialogy Lab, Aalborg Univ. Copenhagen, Denmark , ³ Cognitive Vision Group, Univ. of Southern Denmark, Denmark

Digital Object Identifier: 10.5220/0002044302640271

Proceedings of VISAPP 2007/VISIGRAPP, ISBN: 978-972-8865-73-3

Quick Abstract

Every junction detector has a set of thresholds to make decisions about the junctionness of image points. Low-contrast junctions may pass such thresholds and may not be detected. Lowering the thresholds to find such junctions will lead to spurious junction detections at other image points. In this paper, we implement a junction-regularity measure to improve localization of junctions, and we develop a method to create semantic interpretations of arbitrary junction configurations at improved junction positions. We propose to utilize such a semantic interpretation as a feedback mechanism to filter false-positive junctions. We show results of our proposals on natural images using Harris and SUSAN operators as well as a continuous concept of intrinsic dimensionality.

Related Ontology Subjects/Areas/Topics (7)

Computer Vision, Visualization and Computer Graphics	Features Extraction	Informatics in Control, Automation and Robotics
Early Vision and Image Representation	Image and Video Analysis	Signal Processing, Sensors, Systems Modeling and Control
Feature Extraction

Topic(s):

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject:

Affiliation

Filter listed results, by