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 proceedingChapterpeer-review


    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 languageEnglish
    Title of host publicationAdvances in Intelligent Systems and Computing: Proceedings of the Twenty-Third International Conference on Systems Engineering
    EditorsHenry Selvaraj, Dawid Zydek, Grzegorz Chmaj
    PublisherSpringer Verlag
    ISBN (Print)978-3-319-08421-3
    Publication statusPublished - 2015
    Event23rd International Conference on Systems Engineering - Las Vegas, United States
    Duration: 19 Aug 201421 Aug 2014
    Conference number: 23


    Conference23rd International Conference on Systems Engineering
    Abbreviated titleICSEng2014
    Country/TerritoryUnited States
    CityLas Vegas

    Bibliographical note

    This paper is not available on the repository.


    • colour
    • machine learning
    • semantic segmentation
    • superpixels
    • Terrain classification
    • texture


    Dive into the research topics of 'Superpixel based semantic segmentation for assistance in varying terrain driving conditions'. Together they form a unique fingerprint.

    Cite this