Publication

Real-time image segmentation on a GPU

Conference Article

Conference

Conference for Young Scientists on Facing the Multicore Challenge (MULTICORE CHALLENGE)

Edition

2010

Pages

1-13

Doc link

http://www.multicore-challenge.org/

File

Download the digital copy of the doc pdf document

Authors

Projects associated

Abstract

Efficient segmentation of color images is important for many applications in computer vision. Non-parametric solutions are required in situations where little or no prior knowledge about the data is available. In this paper, we present a novel parallel image segmentation algorithm which segments images in real-time in a non-parametric way. The algorithm finds the equilibrium states of a Potts model in the superparamagnetic phase of the system. Our method maps perfectly onto the Graphics



Processing Unit (GPU) architecture and has been implemented using the framework NVIDIA Compute Unified Device Architecture (CUDA). For images of 256 × 320 pixels we obtained a frame rate of 30 Hz that demonstrates the applicability of the algorithm to video-processing tasks in real-time.

Categories

pattern recognition.

Scientific reference

A. Alexey, T. Kulvicius, F. Wörgötter and B. Dellen. Real-time image segmentation on a GPU, 2010 Conference for Young Scientists on Facing the Multicore Challenge, 2010, , pp. 1-13.