Terrain classification using ToF sensors for the enhancement of agricultural machinery traversability

dc.contributor.authorYandun, Francisco J.
dc.contributor.authorGregorio López, Eduard
dc.contributor.authorEscolà i Agustí, Alexandre
dc.contributor.authorRosell Polo, Joan Ramon
dc.contributor.authorTorres-Torriti, Miguel
dc.contributor.authorAuat Cheein, Fernando A.
dc.date.accessioned2017-11-21T12:34:14Z
dc.date.available2019-11-18T23:31:09Z
dc.date.issued2017-11-14
dc.date.updated2017-11-21T12:34:14Z
dc.description.abstractGround properties influence various aspects of mobile machinery navigation including localization, mobility status or task execution. Excessive slipping, skidding or trapping situations can compromise the vehicle itself or other elements in the workspace. Thus, detecting the soil surface characteristics is an important issue for performing different activities in an efficient, safe and satisfactory manner. In agricultural applications, this point is specially important since activities such as seeding, fertilizing, or ploughing are carried on within off-road landscapes which contain a diversity of terrains that modify the navigation behaviour of the vehicle. Thus, the machinery requires a cognitive capability to understand the surrounding terrain type or its characteristics in order to take the proper guidance or control actions. This work is focused on the soil surface classification by implementing a visual system capable to distinguish between five usual types of off-road terrains. Computer vision and machine learning techniques are applied to characterize the texture and color of images acquired with a Microsoft Kinect V2 sensor. In a first stage, development tests showed that only infra-red and RGB streams are useful to obtain satisfactory accuracy rates (above 90%). The second stage included field trials with the sensor mounted on a mobile robot driving through various agricultural landscapes. These scenarios did not present illumination restrictions nor ideal driving roads; hence, conditions can resemble real agricultural operations. In such circumstances, the proposed approach showed robustness and reliability, obtaining an average of 85.20% of successful classifications when tested along 17 trials within agricultural landscapes.
dc.description.sponsorshipThis work was supported by the National Commission for Scientific and Technological Research of Chile under grant CONICYT-PCHA/Doctorado Nacional/2015-21150694, grant FONDECYT – Chile 1171431, FB0008, DGIIP-UTFSM Chile and University of Lleida, Spain.
dc.format.mimetypeapplication/pdf
dc.identifier.doihttps://doi.org/10.1016/j.jterra.2017.10.005
dc.identifier.idgrec026196
dc.identifier.issn0022-4898
dc.identifier.urihttp://hdl.handle.net/10459.1/60523
dc.language.isoeng
dc.relation.isformatofVersió postprint del document publicat a: https://doi.org/10.1016/j.jterra.2017.10.005
dc.relation.ispartofJournal of Terramechanics, 2017, vol. 76 (2018), p. 1-13
dc.rightscc-by-nc-nd, (c) Elsevier, 2017
dc.rights(c) International Society for Terrain-Vehicle Systems, 2017
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectAgricultural robotics
dc.subjectTerrain Classification
dc.subjectPattern recognition
dc.subjectToF sensors
dc.subjectKinect
dc.titleTerrain classification using ToF sensors for the enhancement of agricultural machinery traversability
dc.typeinfo:eu-repo/semantics/article
dc.type.versioninfo:eu-repo/semantics/acceptedVersion
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
026196.pdf
Size:
17.94 MB
Format:
Adobe Portable Document Format
Description:
Postprint
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: