Scene analysis of unstable video flows - using multiple retina channels and attentional methods

Anna Lázár, Karl Pauwels, Marc Van Hulle, T. Roska

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

The present work describes a bio-inspired approach designed to solve some tasks raised in the 'Bionic Eyeglass Project' [1], which aims to help the everyday life of blind or visually impaired people. The purpose of this approach is to provide a specific kind of information or to determine the region of interest ("ROI") in a low-resolution and unstable video flow recorded with a mobile phone by the visually impaired person. In the present paper we introduce a new stabilization method and three different tasks are resolved: Firstly, locating LED (light-emitting diode) indicators, secondly, locating traffic signs, and thirdly, deciding whether there is any switched-on lamp in a room. The test database has been made out of real-life scenes. We provide detailed evaluation results referring to the execution of those tasks. Our descriptive context refers to the recently modeled mammalian retina channel decomposition [2]. Using it we can avoid - at least partially - the classical difficulty that image processing algorithms nowadays face, namely that the intensity or color values of the same object largely depend on the actual lighting conditions. A further difficulty referring to the lamp-detection is that the solution has to be completely independent of the input's actual brightness. The method we introduce relies only on a single retina channel and achieves a very high accuracy: The ratio of the correct answers is around 99%. The other two tasks are to carry out an approximately real-time ROI-detection algorithm based solely on image information from an unstable low-resolution video-flow containing complex real-life scenes with unconstrained lighting conditions. The accuracy of the introduced methods is around 80%. We also make use of a stabilization algorithm designed especially for this project. In order to yield the desired information, we process channel-data as well as saliency maps. The presented method can be useful in a variety of other application areas.

Original languageEnglish
Title of host publicationIntegrated Circuits, Photodiodes and Organic Field Effect Transistors
PublisherNova Science Publishers, Inc.
Pages95-113
Number of pages19
ISBN (Electronic)9781617618680
ISBN (Print)9781606926604
Publication statusPublished - Jan 1 2009

Fingerprint

Electric lamps
Stabilization
Lighting
Eyeglasses
Traffic signs
Bionics
Mobile phones
Light emitting diodes
Luminance
Image processing
Color
Decomposition

Keywords

  • Cellular wave computing
  • CNN
  • Region of interest
  • Retina channel
  • Saliency map
  • Video flow stabilization

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Lázár, A., Pauwels, K., Van Hulle, M., & Roska, T. (2009). Scene analysis of unstable video flows - using multiple retina channels and attentional methods. In Integrated Circuits, Photodiodes and Organic Field Effect Transistors (pp. 95-113). Nova Science Publishers, Inc..

Scene analysis of unstable video flows - using multiple retina channels and attentional methods. / Lázár, Anna; Pauwels, Karl; Van Hulle, Marc; Roska, T.

Integrated Circuits, Photodiodes and Organic Field Effect Transistors. Nova Science Publishers, Inc., 2009. p. 95-113.

Research output: Chapter in Book/Report/Conference proceedingChapter

Lázár, A, Pauwels, K, Van Hulle, M & Roska, T 2009, Scene analysis of unstable video flows - using multiple retina channels and attentional methods. in Integrated Circuits, Photodiodes and Organic Field Effect Transistors. Nova Science Publishers, Inc., pp. 95-113.
Lázár A, Pauwels K, Van Hulle M, Roska T. Scene analysis of unstable video flows - using multiple retina channels and attentional methods. In Integrated Circuits, Photodiodes and Organic Field Effect Transistors. Nova Science Publishers, Inc. 2009. p. 95-113
Lázár, Anna ; Pauwels, Karl ; Van Hulle, Marc ; Roska, T. / Scene analysis of unstable video flows - using multiple retina channels and attentional methods. Integrated Circuits, Photodiodes and Organic Field Effect Transistors. Nova Science Publishers, Inc., 2009. pp. 95-113
@inbook{0d1692ab7f34452dad76982029424b27,
title = "Scene analysis of unstable video flows - using multiple retina channels and attentional methods",
abstract = "The present work describes a bio-inspired approach designed to solve some tasks raised in the 'Bionic Eyeglass Project' [1], which aims to help the everyday life of blind or visually impaired people. The purpose of this approach is to provide a specific kind of information or to determine the region of interest ({"}ROI{"}) in a low-resolution and unstable video flow recorded with a mobile phone by the visually impaired person. In the present paper we introduce a new stabilization method and three different tasks are resolved: Firstly, locating LED (light-emitting diode) indicators, secondly, locating traffic signs, and thirdly, deciding whether there is any switched-on lamp in a room. The test database has been made out of real-life scenes. We provide detailed evaluation results referring to the execution of those tasks. Our descriptive context refers to the recently modeled mammalian retina channel decomposition [2]. Using it we can avoid - at least partially - the classical difficulty that image processing algorithms nowadays face, namely that the intensity or color values of the same object largely depend on the actual lighting conditions. A further difficulty referring to the lamp-detection is that the solution has to be completely independent of the input's actual brightness. The method we introduce relies only on a single retina channel and achieves a very high accuracy: The ratio of the correct answers is around 99{\%}. The other two tasks are to carry out an approximately real-time ROI-detection algorithm based solely on image information from an unstable low-resolution video-flow containing complex real-life scenes with unconstrained lighting conditions. The accuracy of the introduced methods is around 80{\%}. We also make use of a stabilization algorithm designed especially for this project. In order to yield the desired information, we process channel-data as well as saliency maps. The presented method can be useful in a variety of other application areas.",
keywords = "Cellular wave computing, CNN, Region of interest, Retina channel, Saliency map, Video flow stabilization",
author = "Anna L{\'a}z{\'a}r and Karl Pauwels and {Van Hulle}, Marc and T. Roska",
year = "2009",
month = "1",
day = "1",
language = "English",
isbn = "9781606926604",
pages = "95--113",
booktitle = "Integrated Circuits, Photodiodes and Organic Field Effect Transistors",
publisher = "Nova Science Publishers, Inc.",

}

TY - CHAP

T1 - Scene analysis of unstable video flows - using multiple retina channels and attentional methods

AU - Lázár, Anna

AU - Pauwels, Karl

AU - Van Hulle, Marc

AU - Roska, T.

PY - 2009/1/1

Y1 - 2009/1/1

N2 - The present work describes a bio-inspired approach designed to solve some tasks raised in the 'Bionic Eyeglass Project' [1], which aims to help the everyday life of blind or visually impaired people. The purpose of this approach is to provide a specific kind of information or to determine the region of interest ("ROI") in a low-resolution and unstable video flow recorded with a mobile phone by the visually impaired person. In the present paper we introduce a new stabilization method and three different tasks are resolved: Firstly, locating LED (light-emitting diode) indicators, secondly, locating traffic signs, and thirdly, deciding whether there is any switched-on lamp in a room. The test database has been made out of real-life scenes. We provide detailed evaluation results referring to the execution of those tasks. Our descriptive context refers to the recently modeled mammalian retina channel decomposition [2]. Using it we can avoid - at least partially - the classical difficulty that image processing algorithms nowadays face, namely that the intensity or color values of the same object largely depend on the actual lighting conditions. A further difficulty referring to the lamp-detection is that the solution has to be completely independent of the input's actual brightness. The method we introduce relies only on a single retina channel and achieves a very high accuracy: The ratio of the correct answers is around 99%. The other two tasks are to carry out an approximately real-time ROI-detection algorithm based solely on image information from an unstable low-resolution video-flow containing complex real-life scenes with unconstrained lighting conditions. The accuracy of the introduced methods is around 80%. We also make use of a stabilization algorithm designed especially for this project. In order to yield the desired information, we process channel-data as well as saliency maps. The presented method can be useful in a variety of other application areas.

AB - The present work describes a bio-inspired approach designed to solve some tasks raised in the 'Bionic Eyeglass Project' [1], which aims to help the everyday life of blind or visually impaired people. The purpose of this approach is to provide a specific kind of information or to determine the region of interest ("ROI") in a low-resolution and unstable video flow recorded with a mobile phone by the visually impaired person. In the present paper we introduce a new stabilization method and three different tasks are resolved: Firstly, locating LED (light-emitting diode) indicators, secondly, locating traffic signs, and thirdly, deciding whether there is any switched-on lamp in a room. The test database has been made out of real-life scenes. We provide detailed evaluation results referring to the execution of those tasks. Our descriptive context refers to the recently modeled mammalian retina channel decomposition [2]. Using it we can avoid - at least partially - the classical difficulty that image processing algorithms nowadays face, namely that the intensity or color values of the same object largely depend on the actual lighting conditions. A further difficulty referring to the lamp-detection is that the solution has to be completely independent of the input's actual brightness. The method we introduce relies only on a single retina channel and achieves a very high accuracy: The ratio of the correct answers is around 99%. The other two tasks are to carry out an approximately real-time ROI-detection algorithm based solely on image information from an unstable low-resolution video-flow containing complex real-life scenes with unconstrained lighting conditions. The accuracy of the introduced methods is around 80%. We also make use of a stabilization algorithm designed especially for this project. In order to yield the desired information, we process channel-data as well as saliency maps. The presented method can be useful in a variety of other application areas.

KW - Cellular wave computing

KW - CNN

KW - Region of interest

KW - Retina channel

KW - Saliency map

KW - Video flow stabilization

UR - http://www.scopus.com/inward/record.url?scp=85049543328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049543328&partnerID=8YFLogxK

M3 - Chapter

SN - 9781606926604

SP - 95

EP - 113

BT - Integrated Circuits, Photodiodes and Organic Field Effect Transistors

PB - Nova Science Publishers, Inc.

ER -