Segmentation of Kinect Captured Images using Grid based 3D Connected Component Labeling

Aniruddha Sinha, T. Chattopadhyay, Apurbaa Mallik

2013

Abstract

In this paper authors have presented a grid based 3-Dimensional (3D) connected component labeling method to segment the video frames captured using Kinect RGB-D sensor. The Kinect captures the RGB value of the object as well as its depth using two different cameras/sensors. A calibration between these two sensors enables us to generate the point cloud (a 6 tuple entry containing the RGB values as well as its position along x, y and z directions with respect to the camera) for each pixel in the depth image. In the proposed method we initially construct the point clouds for all the pixels in the depth image. Then the space comprising the cloud points is divided into 3D grids and then label the components using the same index which are connected in the 3D space. The proposed method can segment the images even where the projection of two spatially different objects overlaps in the projected plane. We have tested the segmentation method against the HARL dataset with different grid size and obtained an overall segmentation accuracy of 83.8% for the optimum grid size.

Paper Citation

in Harvard Style

Sinha A., Chattopadhyay T. and Mallik A. (2013). Segmentation of Kinect Captured Images using Grid based 3D Connected Component Labeling . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 327-332. DOI: 10.5220/0004289303270332

in Bibtex Style

@conference{visapp13,
author={Aniruddha Sinha and T. Chattopadhyay and Apurbaa Mallik},
title={Segmentation of Kinect Captured Images using Grid based 3D Connected Component Labeling},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={327-332},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004289303270332},
isbn={978-989-8565-47-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - Segmentation of Kinect Captured Images using Grid based 3D Connected Component Labeling
SN - 978-989-8565-47-1
AU - Sinha A.
AU - Chattopadhyay T.
AU - Mallik A.
PY - 2013
SP - 327
EP - 332
DO - 10.5220/0004289303270332