Original scientific paper

https://doi.org/10.21278/TOF.453024420

Vision-Based Inspection of Tyre Tread Depth

Emina Petrović orcid.org/0000-0002-4230-2416 ; University of Niš, Faculty of Mechanical Engineering, Niš, Serbia
Danijela Ristić Durrant ; Institute of Automation, University of Bremen, Bremen, Germany
Miloš Simonović orcid.org/0000-0003-1364-7746 ; University of Niš, Faculty of Mechanical Engineering, Niš, Serbia
Žarko Ćojbašić ; University of Niš, Faculty of Mechanical Engineering, Niš, Serbia
Vlastimir Nikolić ; University of Niš, Faculty of Mechanical Engineering, Niš, Serbia

Abstract

In this paper, an approach for visual, non-contact automatic inspection of tyre tread depth based on existing image processing techniques is presented. Histograms of oriented gradient are used for feature extraction from images. In order to analyse which set of features gives the best classification results, a linear support-vector machine classifier was trained and tested using different numbers of pixels and numbers of cells per block. The obtained processing and experimental results are presented in this paper.

Keywords

Histogram of oriented gradient; Support vector machine; Tyre tread depth inspection; Optimal descriptor configuration; Classification

Hrčak ID:

265648

URI

https://hrcak.srce.hr/265648

Publication date:

1.12.2021.

Visits: 1.278 *