Ground segmentation and free space estimation in off-road terrain

Simple item page
dc.contributor.authorHamandi, Mahmoud
dc.contributor.authorAsmar, Daniel C.
dc.contributor.authorShammas, Elie A.
dc.contributor.departmentDepartment of Mechanical Engineering
dc.contributor.facultyMaroun Semaan Faculty of Engineering and Architecture (MSFEA)
dc.contributor.institutionAmerican University of Beirut
dc.date.accessioned2025-01-24T11:32:21Z
dc.date.available2025-01-24T11:32:21Z
dc.date.issued2018
dc.description.abstractIn this paper, we propose a novel approach for ground segmentation and free space estimation of outdoor environments. The system is completely self-supervised and relies on two modules: the first module is built around a Fully Convolutional Network (FCN), and is used for ground segmentation after the system is initiated. The second module relies on depth information paired with interactive graphs cuts, and is used to train the FCN at startup, and anytime the FCN's performance degrades during runtime. This usually happens when the camera observes a new type of outdoor scene, which is foreign to the FCN. Experiments were conducted on three datasets of different ruggedness to highlight the advantages of the proposed method. © 2018
dc.identifier.doihttps://doi.org/10.1016/j.patrec.2018.02.019
dc.identifier.eid2-s2.0-85042694918
dc.identifier.urihttp://hdl.handle.net/10938/27777
dc.language.isoen
dc.publisherElsevier B.V.
dc.relation.ispartofPattern Recognition Letters
dc.sourceScopus
dc.subjectSoftware engineering
dc.subjectConvolutional networks
dc.subjectDepth information
dc.subjectFree spaces
dc.subjectOutdoor environment
dc.subjectOutdoor scenes
dc.subjectRuntimes
dc.subjectPattern recognition
dc.titleGround segmentation and free space estimation in off-road terrain
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
2018-8145.pdf
Size:
1.2 MB
Format:
Adobe Portable Document Format
Download

Collections

Department of Mechanical Engineering