mDBSCAN: Real Time Superpixel Segmentation by DBSCAN Clustering based on Boundary Term

Hasan Almassri, Tim Dackermann, Norbert Haala

Abstract

mDBSCAN is an improved version of DBSCAN (Density Based Spatial Clustering of Applications with Noise) superpixel segmentation. Unlike DBSCAN algorithm, the proposed algorithm has an automatic threshold based on the colour and gradient information. The proposed algorithm performs under different colour space such as RGB, Lab and grey images using a novel distance measurement. The experimental results demonstrate that the proposed algorithm outperforms the state of the art algorithms in terms of boundary adherence and segmentation accuracy with low computational cost (30 frames/s).

Download


Paper Citation


in Harvard Style

Almassri H., Dackermann T. and Haala N. (2019). mDBSCAN: Real Time Superpixel Segmentation by DBSCAN Clustering based on Boundary Term.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 283-291. DOI: 10.5220/0007249302830291


in Bibtex Style

@conference{icpram19,
author={Hasan Almassri and Tim Dackermann and Norbert Haala},
title={mDBSCAN: Real Time Superpixel Segmentation by DBSCAN Clustering based on Boundary Term},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={283-291},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007249302830291},
isbn={978-989-758-351-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - mDBSCAN: Real Time Superpixel Segmentation by DBSCAN Clustering based on Boundary Term
SN - 978-989-758-351-3
AU - Almassri H.
AU - Dackermann T.
AU - Haala N.
PY - 2019
SP - 283
EP - 291
DO - 10.5220/0007249302830291