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
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.
Follow us!