Evolutionary active vision system: from 2D to 3D

Olalekan Lanihun, Bernie Tiddeman, Patricia Shaw, Elio Tuci

Research output: Contribution to journalArticle

Abstract

Biological vision incorporates intelligent cooperation between the sensory and the motor systems, which is facilitated by the development of motor skills that help to shape visual information that is relevant to a specific vision task. In this article, we seek to explore an approach to active vision inspired by biological systems, which uses limited constraints for motor strategies through progressive adaptation via an evolutionary method. This type of approach gives freedom to artificial systems in the discovery of eye-movement strategies that may be useful to solve a given vision task but are not known to us. In the experiment sections of this article, we use this type of evolutionary active vision system for more complex natural images in both two-dimensional (2D) and three-dimensional (3D) environments. To further improve the results, we experiment with the use of pre-processing the visual input with both the uniform local binary patterns (ULBP) and the histogram of oriented gradients (HOG) for classification tasks in the 2D and 3D environments. The 3D experiments include application of the active vision system to object categorisation and indoor versus outdoor environment classification. Our experiments are conducted on the iCub humanoid robot simulator platform.

Original languageEnglish
JournalAdaptive Behavior
DOIs
Publication statusPublished - 3 Oct 2019

Fingerprint

Motor Skills
Eye Movements

Keywords

  • Active vision system
  • evolutionary robotics
  • histogram of oriented gradients
  • humanoid robot
  • neural network
  • uniform local binary patterns

Cite this

Lanihun, Olalekan ; Tiddeman, Bernie ; Shaw, Patricia ; Tuci, Elio. / Evolutionary active vision system : from 2D to 3D. In: Adaptive Behavior. 2019.
@article{f50f562264124b5a94f6d792e93d11cb,
title = "Evolutionary active vision system: from 2D to 3D",
abstract = "Biological vision incorporates intelligent cooperation between the sensory and the motor systems, which is facilitated by the development of motor skills that help to shape visual information that is relevant to a specific vision task. In this article, we seek to explore an approach to active vision inspired by biological systems, which uses limited constraints for motor strategies through progressive adaptation via an evolutionary method. This type of approach gives freedom to artificial systems in the discovery of eye-movement strategies that may be useful to solve a given vision task but are not known to us. In the experiment sections of this article, we use this type of evolutionary active vision system for more complex natural images in both two-dimensional (2D) and three-dimensional (3D) environments. To further improve the results, we experiment with the use of pre-processing the visual input with both the uniform local binary patterns (ULBP) and the histogram of oriented gradients (HOG) for classification tasks in the 2D and 3D environments. The 3D experiments include application of the active vision system to object categorisation and indoor versus outdoor environment classification. Our experiments are conducted on the iCub humanoid robot simulator platform.",
keywords = "Active vision system, evolutionary robotics, histogram of oriented gradients, humanoid robot, neural network, uniform local binary patterns",
author = "Olalekan Lanihun and Bernie Tiddeman and Patricia Shaw and Elio Tuci",
year = "2019",
month = "10",
day = "3",
doi = "10.1177/1059712319874475",
language = "English",
journal = "Adaptive Behavior",
issn = "1059-7123",
publisher = "SAGE Publications Ltd",

}

Evolutionary active vision system : from 2D to 3D. / Lanihun, Olalekan; Tiddeman, Bernie; Shaw, Patricia; Tuci, Elio.

In: Adaptive Behavior, 03.10.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evolutionary active vision system

T2 - from 2D to 3D

AU - Lanihun, Olalekan

AU - Tiddeman, Bernie

AU - Shaw, Patricia

AU - Tuci, Elio

PY - 2019/10/3

Y1 - 2019/10/3

N2 - Biological vision incorporates intelligent cooperation between the sensory and the motor systems, which is facilitated by the development of motor skills that help to shape visual information that is relevant to a specific vision task. In this article, we seek to explore an approach to active vision inspired by biological systems, which uses limited constraints for motor strategies through progressive adaptation via an evolutionary method. This type of approach gives freedom to artificial systems in the discovery of eye-movement strategies that may be useful to solve a given vision task but are not known to us. In the experiment sections of this article, we use this type of evolutionary active vision system for more complex natural images in both two-dimensional (2D) and three-dimensional (3D) environments. To further improve the results, we experiment with the use of pre-processing the visual input with both the uniform local binary patterns (ULBP) and the histogram of oriented gradients (HOG) for classification tasks in the 2D and 3D environments. The 3D experiments include application of the active vision system to object categorisation and indoor versus outdoor environment classification. Our experiments are conducted on the iCub humanoid robot simulator platform.

AB - Biological vision incorporates intelligent cooperation between the sensory and the motor systems, which is facilitated by the development of motor skills that help to shape visual information that is relevant to a specific vision task. In this article, we seek to explore an approach to active vision inspired by biological systems, which uses limited constraints for motor strategies through progressive adaptation via an evolutionary method. This type of approach gives freedom to artificial systems in the discovery of eye-movement strategies that may be useful to solve a given vision task but are not known to us. In the experiment sections of this article, we use this type of evolutionary active vision system for more complex natural images in both two-dimensional (2D) and three-dimensional (3D) environments. To further improve the results, we experiment with the use of pre-processing the visual input with both the uniform local binary patterns (ULBP) and the histogram of oriented gradients (HOG) for classification tasks in the 2D and 3D environments. The 3D experiments include application of the active vision system to object categorisation and indoor versus outdoor environment classification. Our experiments are conducted on the iCub humanoid robot simulator platform.

KW - Active vision system

KW - evolutionary robotics

KW - histogram of oriented gradients

KW - humanoid robot

KW - neural network

KW - uniform local binary patterns

UR - http://www.scopus.com/inward/record.url?scp=85074017419&partnerID=8YFLogxK

U2 - 10.1177/1059712319874475

DO - 10.1177/1059712319874475

M3 - Article

AN - SCOPUS:85074017419

JO - Adaptive Behavior

JF - Adaptive Behavior

SN - 1059-7123

ER -