:: Volume 5, Issue 1 (6-2017) ::
jgit 2017, 5(1): 89-109 Back to browse issues page
Evaluation of SLIC superpixel and DBSCAN clustering algorithms in segmentation of ultra-high resolution remote sensing imagery over urban areas
Ahmad Hadavand *, Mohamad Saadatseresht, Saeed Homayouni, Zeinab Gharib Bafghi
University of Tehran
Abstract:   (3225 Views)

By increasing the spatial resolution of remote sensing imaging sensors, the image analyzing paradigm is
moving towards the object based image analysis approaches, instead of single pixels. Among the common
segmentation algorithms, super-pixel methods are presenting themselves as the new tools in computer vision.
In this paper, the capabilities of a state-of-the-art super-pixel algorithm, namely called SLIC, is investigated for
creating image segments from ultra-high resolution remote sensing images. In our proposed method, square
and hexagonal super-pixels were formed and then DBSCAN clustering algorithm is employed to build image
segments from these pixels. The results were compared to image segments obtained from FNEA algorithm, a
well-known method for remote sensing image segmentation. Visual and quantitative evaluations demonstrate
the efficiency of proposed method.

Keywords: Super-pixel, Segmentation, Ultra-high resolution Images, Remote Sensing.
Full-Text [PDF 3015 kb]   (1683 Downloads)    
Type of Study: Research | Subject: Aerial Photogrammetry
Received: 2017/06/10 | Accepted: 2017/06/10 | Published: 2017/06/10

XML   Persian Abstract   Print

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 5, Issue 1 (6-2017) Back to browse issues page