KIT | KIT-Bibliothek | Impressum | Datenschutz

Assistance system for an automated log-quality and assortment estimation based on data-driven approaches using hydraulic signals of forestry machines

Geiger, Chris; Maier, Niklas; Kalinke, Florian; Geimer, Marcus


The correct classification of a logs assortment is crucial for the economic output within a fully mechanized timber harvest. This task is especially for unexperienced but also for professional machine operators mentally demanding. This paper presents a method towards an assistance system for machine operators for an automated log quality and assortment estimation. Therefore, machine vision methods for object detection are combined with machine learning approaches for estimating the logs weight based on a Convolutional Neural Network (CNN). Based on the dimensions oft he object ´log, a first categorisation into a specific assortment is done. By comparing the theoretical weight of a healthy log of such dimensions to the real weight estimated by the CNN-based crane scale, quality reducing properties such as beetle infestation or red rod can be detected. In such cases, the assistance system displays a visual warning to the operator to check the loaded log.

Preprint §
DOI: 10.5445/IR/1000129234
Veröffentlicht am 02.02.2021
DOI: 10.25368/2020.97
Zitationen: 2
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Fahrzeugsystemtechnik (FAST)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2020
Sprache Englisch
Identifikator KITopen-ID: 1000129234
Erschienen in Fluid Power Future Technology! Vol. 3
Veranstaltung 12th International Fluid Power Conference (IFK 2020), Dresden, Deutschland, 12.10.2020 – 14.10.2020
Verlag Technische Universität Dresden (TU Dresden)
Seiten 83–92
Vorab online veröffentlicht am 26.06.2020
Schlagwörter Assistance System, Log Assortment, Crane Scale, Machine Learning, Machine Vision,, Forwarder, Convolutional Neural Network
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page