Biologically Inspired Intensity and Depth Image Edge Extraction

Research output: Contribution to journalArticle

Abstract

In recent years artificial vision research has moved from focusing on the use of only intensity images to include using depth images, or RGB-D combinations due to the recent development of low cost depth cameras. However, depth images require a lot of storage and processing requirements. In addition, it is challenging to extract relevant features from depth images in real-time. Researchers have sought inspiration from biology in order to overcome these challenges resulting in biologically inspired feature extraction methods. By taking inspiration from nature it may be possible to reduce redundancy, extract relevant features, and process an image efficiently by emulating biological visual processes. In this paper, we present a depth and intensity image feature extraction approach that has been inspired by biological vision systems. Through the use of biologically inspired spiking neural networks we emulate functional computational aspects of biological visual systems. Results demonstrate that the proposed bio-inspired artificial vision system has increased performance over existing computer vision feature extraction approaches.
LanguageEnglish
Pages5356-5365
Number of pages9
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume29
Issue number11
Early online date20 Feb 2018
DOIs
Publication statusE-pub ahead of print - 20 Feb 2018

Fingerprint

Computer vision
Feature extraction
Redundancy
Cameras
Neural networks
Processing
Costs

Keywords

  • depth image
  • spiking neural network
  • bio-inspired imaging

Cite this

@article{5517e13d14024e78a1f5af9bd91f1c7f,
title = "Biologically Inspired Intensity and Depth Image Edge Extraction",
abstract = "In recent years artificial vision research has moved from focusing on the use of only intensity images to include using depth images, or RGB-D combinations due to the recent development of low cost depth cameras. However, depth images require a lot of storage and processing requirements. In addition, it is challenging to extract relevant features from depth images in real-time. Researchers have sought inspiration from biology in order to overcome these challenges resulting in biologically inspired feature extraction methods. By taking inspiration from nature it may be possible to reduce redundancy, extract relevant features, and process an image efficiently by emulating biological visual processes. In this paper, we present a depth and intensity image feature extraction approach that has been inspired by biological vision systems. Through the use of biologically inspired spiking neural networks we emulate functional computational aspects of biological visual systems. Results demonstrate that the proposed bio-inspired artificial vision system has increased performance over existing computer vision feature extraction approaches.",
keywords = "depth image, spiking neural network, bio-inspired imaging",
author = "Dermot Kerr and SA Coleman and TM McGinnity",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/TNNLS.2018.2797994",
language = "English",
volume = "29",
pages = "5356--5365",
number = "11",

}

Biologically Inspired Intensity and Depth Image Edge Extraction. / Kerr, Dermot; Coleman, SA; McGinnity, TM.

Vol. 29, No. 11, 20.02.2018, p. 5356-5365.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Biologically Inspired Intensity and Depth Image Edge Extraction

AU - Kerr, Dermot

AU - Coleman, SA

AU - McGinnity, TM

PY - 2018/2/20

Y1 - 2018/2/20

N2 - In recent years artificial vision research has moved from focusing on the use of only intensity images to include using depth images, or RGB-D combinations due to the recent development of low cost depth cameras. However, depth images require a lot of storage and processing requirements. In addition, it is challenging to extract relevant features from depth images in real-time. Researchers have sought inspiration from biology in order to overcome these challenges resulting in biologically inspired feature extraction methods. By taking inspiration from nature it may be possible to reduce redundancy, extract relevant features, and process an image efficiently by emulating biological visual processes. In this paper, we present a depth and intensity image feature extraction approach that has been inspired by biological vision systems. Through the use of biologically inspired spiking neural networks we emulate functional computational aspects of biological visual systems. Results demonstrate that the proposed bio-inspired artificial vision system has increased performance over existing computer vision feature extraction approaches.

AB - In recent years artificial vision research has moved from focusing on the use of only intensity images to include using depth images, or RGB-D combinations due to the recent development of low cost depth cameras. However, depth images require a lot of storage and processing requirements. In addition, it is challenging to extract relevant features from depth images in real-time. Researchers have sought inspiration from biology in order to overcome these challenges resulting in biologically inspired feature extraction methods. By taking inspiration from nature it may be possible to reduce redundancy, extract relevant features, and process an image efficiently by emulating biological visual processes. In this paper, we present a depth and intensity image feature extraction approach that has been inspired by biological vision systems. Through the use of biologically inspired spiking neural networks we emulate functional computational aspects of biological visual systems. Results demonstrate that the proposed bio-inspired artificial vision system has increased performance over existing computer vision feature extraction approaches.

KW - depth image

KW - spiking neural network

KW - bio-inspired imaging

U2 - 10.1109/TNNLS.2018.2797994

DO - 10.1109/TNNLS.2018.2797994

M3 - Article

VL - 29

SP - 5356

EP - 5365

IS - 11

ER -