Superpixel based semantic segmentation for assistance in varying terrain driving conditions

Ionut Gheorghe; Weidong Li; Thomas Popham; Keith J. Burnham

doi:10.1007/978-3-319-08422-0_98

Superpixel based semantic segmentation for assistance in varying terrain driving conditions

Ionut Gheorghe, Weidong Li, Thomas Popham, Keith J. Burnham

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Vehicle drivability and maneuverability can be improved by increasing the environment awareness via sensory inputs. In particular, off-road capable vehicles possess subsystems which are configurable to the driving conditions. In this work, a vision solution is explored as a precursor to autonomous toggling between different operating modes. The emphasis is on selecting an appropriate response to transitions from one terrain type to another. Given a forward facing camera, images are partitioned into pixel subsets known as superpixels in order to be classified. The quality of this semantic segmentation is considered for classes such as {grass, tree, sky, tarmac, dirt, gravel, shrubs}. Colour and texture are combined together to form visual cues and address this image recognition problem with good segmentation results

Original language	English
Title of host publication	Advances in Intelligent Systems and Computing: Proceedings of the Twenty-Third International Conference on Systems Engineering
Editors	Henry Selvaraj, Dawid Zydek, Grzegorz Chmaj
Publisher	Springer Verlag
Pages	691-698
Volume	1089
ISBN (Print)	978-3-319-08421-3
DOIs	https://doi.org/10.1007/978-3-319-08422-0_98
Publication status	Published - 2015
Event	23rd International Conference on Systems Engineering - Las Vegas, United States Duration: 19 Aug 2014 → 21 Aug 2014 Conference number: 23

Conference

Conference	23rd International Conference on Systems Engineering
Abbreviated title	ICSEng2014
Country/Territory	United States
City	Las Vegas
Period	19/08/14 → 21/08/14

Bibliographical note

This paper is not available on the repository.

Keywords

colour
machine learning
semantic segmentation
superpixels
Terrain classification
texture

Access to Document

10.1007/978-3-319-08422-0_98

Cite this

Gheorghe, I., Li, W., Popham, T., & Burnham, K. J. (2015). Superpixel based semantic segmentation for assistance in varying terrain driving conditions. In H. Selvaraj, D. Zydek, & G. Chmaj (Eds.), Advances in Intelligent Systems and Computing: Proceedings of the Twenty-Third International Conference on Systems Engineering (Vol. 1089, pp. 691-698). Springer Verlag. https://doi.org/10.1007/978-3-319-08422-0_98

Superpixel based semantic segmentation for assistance in varying terrain driving conditions. / Gheorghe, Ionut; Li, Weidong; Popham, Thomas et al.
Advances in Intelligent Systems and Computing: Proceedings of the Twenty-Third International Conference on Systems Engineering. ed. / Henry Selvaraj; Dawid Zydek; Grzegorz Chmaj. Vol. 1089 Springer Verlag, 2015. p. 691-698.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Gheorghe, I, Li, W, Popham, T & Burnham, KJ 2015, Superpixel based semantic segmentation for assistance in varying terrain driving conditions. in H Selvaraj, D Zydek & G Chmaj (eds), Advances in Intelligent Systems and Computing: Proceedings of the Twenty-Third International Conference on Systems Engineering. vol. 1089, Springer Verlag, pp. 691-698, 23rd International Conference on Systems Engineering, Las Vegas, Nevada, United States, 19/08/14. https://doi.org/10.1007/978-3-319-08422-0_98

Gheorghe I, Li W, Popham T, Burnham KJ. Superpixel based semantic segmentation for assistance in varying terrain driving conditions. In Selvaraj H, Zydek D, Chmaj G, editors, Advances in Intelligent Systems and Computing: Proceedings of the Twenty-Third International Conference on Systems Engineering. Vol. 1089. Springer Verlag. 2015. p. 691-698 doi: 10.1007/978-3-319-08422-0_98

Gheorghe, Ionut ; Li, Weidong ; Popham, Thomas et al. / Superpixel based semantic segmentation for assistance in varying terrain driving conditions. Advances in Intelligent Systems and Computing: Proceedings of the Twenty-Third International Conference on Systems Engineering. editor / Henry Selvaraj ; Dawid Zydek ; Grzegorz Chmaj. Vol. 1089 Springer Verlag, 2015. pp. 691-698

@inbook{8bad932ec16b43e6b1e5c00af52be151,

title = "Superpixel based semantic segmentation for assistance in varying terrain driving conditions",

abstract = "Vehicle drivability and maneuverability can be improved by increasing the environment awareness via sensory inputs. In particular, off-road capable vehicles possess subsystems which are configurable to the driving conditions. In this work, a vision solution is explored as a precursor to autonomous toggling between different operating modes. The emphasis is on selecting an appropriate response to transitions from one terrain type to another. Given a forward facing camera, images are partitioned into pixel subsets known as superpixels in order to be classified. The quality of this semantic segmentation is considered for classes such as {grass, tree, sky, tarmac, dirt, gravel, shrubs}. Colour and texture are combined together to form visual cues and address this image recognition problem with good segmentation results",

keywords = "colour, machine learning, semantic segmentation, superpixels, Terrain classification, texture",

author = "Ionut Gheorghe and Weidong Li and Thomas Popham and Burnham, {Keith J.}",

note = "This paper is not available on the repository. ; 23rd International Conference on Systems Engineering, ICSEng2014 ; Conference date: 19-08-2014 Through 21-08-2014",

year = "2015",

doi = "10.1007/978-3-319-08422-0_98",

language = "English",

isbn = "978-3-319-08421-3",

volume = "1089",

pages = "691--698",

editor = "Henry Selvaraj and Dawid Zydek and Grzegorz Chmaj",

booktitle = "Advances in Intelligent Systems and Computing: Proceedings of the Twenty-Third International Conference on Systems Engineering",

publisher = "Springer Verlag",

address = "Austria",

}

TY - CHAP

T1 - Superpixel based semantic segmentation for assistance in varying terrain driving conditions

AU - Gheorghe, Ionut

AU - Li, Weidong

AU - Popham, Thomas

AU - Burnham, Keith J.

N1 - Conference code: 23

PY - 2015

Y1 - 2015

N2 - Vehicle drivability and maneuverability can be improved by increasing the environment awareness via sensory inputs. In particular, off-road capable vehicles possess subsystems which are configurable to the driving conditions. In this work, a vision solution is explored as a precursor to autonomous toggling between different operating modes. The emphasis is on selecting an appropriate response to transitions from one terrain type to another. Given a forward facing camera, images are partitioned into pixel subsets known as superpixels in order to be classified. The quality of this semantic segmentation is considered for classes such as {grass, tree, sky, tarmac, dirt, gravel, shrubs}. Colour and texture are combined together to form visual cues and address this image recognition problem with good segmentation results

AB - Vehicle drivability and maneuverability can be improved by increasing the environment awareness via sensory inputs. In particular, off-road capable vehicles possess subsystems which are configurable to the driving conditions. In this work, a vision solution is explored as a precursor to autonomous toggling between different operating modes. The emphasis is on selecting an appropriate response to transitions from one terrain type to another. Given a forward facing camera, images are partitioned into pixel subsets known as superpixels in order to be classified. The quality of this semantic segmentation is considered for classes such as {grass, tree, sky, tarmac, dirt, gravel, shrubs}. Colour and texture are combined together to form visual cues and address this image recognition problem with good segmentation results

KW - colour

KW - machine learning

KW - semantic segmentation

KW - superpixels

KW - Terrain classification

KW - texture

U2 - 10.1007/978-3-319-08422-0_98

DO - 10.1007/978-3-319-08422-0_98

M3 - Chapter

SN - 978-3-319-08421-3

VL - 1089

SP - 691

EP - 698

BT - Advances in Intelligent Systems and Computing: Proceedings of the Twenty-Third International Conference on Systems Engineering

A2 - Selvaraj, Henry

A2 - Zydek, Dawid

A2 - Chmaj, Grzegorz

PB - Springer Verlag

T2 - 23rd International Conference on Systems Engineering

Y2 - 19 August 2014 through 21 August 2014

ER -

Superpixel based semantic segmentation for assistance in varying terrain driving conditions

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this