Joint Color-Spatial-Directional clustering and Region Merging (JCSD-RM) for unsupervised RGB-D image segmentation

TL;DR

This paper introduces an unsupervised RGB-D image segmentation method that combines color, spatial, and directional clustering with statistical planar region merging, achieving competitive results with reduced computation time.

Contribution

It presents a novel joint clustering and region merging approach for RGB-D segmentation that effectively fuses color and geometry in an unsupervised framework.

Findings

Comparable to state-of-the-art methods in accuracy

Requires less computation time

Effectively fuses color and geometry information

Abstract

Recent advances in depth imaging sensors provide easy access to the synchronized depth with color, called RGB-D image. In this paper, we propose an unsupervised method for indoor RGB-D image segmentation and analysis. We consider a statistical image generation model based on the color and geometry of the scene. Our method consists of a joint color-spatial-directional clustering method followed by a statistical planar region merging method. We evaluate our method on the NYU depth database and compare it with existing unsupervised RGB-D segmentation methods. Results show that, it is comparable with the state of the art methods and it needs less computation time. Moreover, it opens interesting perspectives to fuse color and geometry in an unsupervised manner.