Salient Obstacle Avoidance for Robotic Systems

Research output: Contribution to conferencePaper

Abstract

Salient object detection is a very active area of interest, based on human selective attention which shifts our focus across prominent areas in a scene. Many models have been created and achieved impressive accuracies, however, this often comes at a high computational efficiency cost making them less attractive for real-time robotic systems. We develop a novel salient object detection algorithm and investigate the trade-off between accuracy and computation time by comparing pixel-based and region-based processing. Salient object detection has been used in a variety of applications, however, this work is focused on developing an algorithm considering obstacle avoidance for a robot operating in a cluttered and dynamic environment. The strategy is evaluated on the publicly available MSRA10K salient object dataset, against three current state-of-the-art methods.
LanguageEnglish
Pages57
Number of pages64
Publication statusPublished - 29 Jul 2018
EventIrish Machine Vision and Image Processing Conference - Belfast, United Kingdom
Duration: 29 Aug 201831 Aug 2018

Conference

ConferenceIrish Machine Vision and Image Processing Conference
Abbreviated titleIMVIP
CountryUnited Kingdom
Period29/08/1831/08/18

Fingerprint

Collision avoidance
Robotics
Computational efficiency
Pixels
Robots
Processing
Object detection
Costs

Keywords

  • Saliency
  • SLIC
  • Obstacle Avoidance

Cite this

Cooley, C., Coleman, S., Gardiner, B., & Scotney, B. (2018). Salient Obstacle Avoidance for Robotic Systems. 57. Paper presented at Irish Machine Vision and Image Processing Conference, United Kingdom.
Cooley, Christopher ; Coleman, Sonya ; Gardiner, Bryan ; Scotney, Bryan. / Salient Obstacle Avoidance for Robotic Systems. Paper presented at Irish Machine Vision and Image Processing Conference, United Kingdom.64 p.
@conference{08e86f168f2c49899a9be2894f468559,
title = "Salient Obstacle Avoidance for Robotic Systems",
abstract = "Salient object detection is a very active area of interest, based on human selective attention which shifts our focus across prominent areas in a scene. Many models have been created and achieved impressive accuracies, however, this often comes at a high computational efficiency cost making them less attractive for real-time robotic systems. We develop a novel salient object detection algorithm and investigate the trade-off between accuracy and computation time by comparing pixel-based and region-based processing. Salient object detection has been used in a variety of applications, however, this work is focused on developing an algorithm considering obstacle avoidance for a robot operating in a cluttered and dynamic environment. The strategy is evaluated on the publicly available MSRA10K salient object dataset, against three current state-of-the-art methods.",
keywords = "Saliency, SLIC, Obstacle Avoidance",
author = "Christopher Cooley and Sonya Coleman and Bryan Gardiner and Bryan Scotney",
year = "2018",
month = "7",
day = "29",
language = "English",
pages = "57",
note = "Irish Machine Vision and Image Processing Conference, IMVIP ; Conference date: 29-08-2018 Through 31-08-2018",

}

Cooley, C, Coleman, S, Gardiner, B & Scotney, B 2018, 'Salient Obstacle Avoidance for Robotic Systems' Paper presented at Irish Machine Vision and Image Processing Conference, United Kingdom, 29/08/18 - 31/08/18, pp. 57.

Salient Obstacle Avoidance for Robotic Systems. / Cooley, Christopher; Coleman, Sonya; Gardiner, Bryan; Scotney, Bryan.

2018. 57 Paper presented at Irish Machine Vision and Image Processing Conference, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Salient Obstacle Avoidance for Robotic Systems

AU - Cooley, Christopher

AU - Coleman, Sonya

AU - Gardiner, Bryan

AU - Scotney, Bryan

PY - 2018/7/29

Y1 - 2018/7/29

N2 - Salient object detection is a very active area of interest, based on human selective attention which shifts our focus across prominent areas in a scene. Many models have been created and achieved impressive accuracies, however, this often comes at a high computational efficiency cost making them less attractive for real-time robotic systems. We develop a novel salient object detection algorithm and investigate the trade-off between accuracy and computation time by comparing pixel-based and region-based processing. Salient object detection has been used in a variety of applications, however, this work is focused on developing an algorithm considering obstacle avoidance for a robot operating in a cluttered and dynamic environment. The strategy is evaluated on the publicly available MSRA10K salient object dataset, against three current state-of-the-art methods.

AB - Salient object detection is a very active area of interest, based on human selective attention which shifts our focus across prominent areas in a scene. Many models have been created and achieved impressive accuracies, however, this often comes at a high computational efficiency cost making them less attractive for real-time robotic systems. We develop a novel salient object detection algorithm and investigate the trade-off between accuracy and computation time by comparing pixel-based and region-based processing. Salient object detection has been used in a variety of applications, however, this work is focused on developing an algorithm considering obstacle avoidance for a robot operating in a cluttered and dynamic environment. The strategy is evaluated on the publicly available MSRA10K salient object dataset, against three current state-of-the-art methods.

KW - Saliency

KW - SLIC

KW - Obstacle Avoidance

M3 - Paper

SP - 57

ER -

Cooley C, Coleman S, Gardiner B, Scotney B. Salient Obstacle Avoidance for Robotic Systems. 2018. Paper presented at Irish Machine Vision and Image Processing Conference, United Kingdom.