Real-Time High-Quality Stereo Matching System on a GPU

TL;DR

This paper presents a GPU-based stereo vision system capable of real-time processing of high-resolution images with low error rates, achieving 40 fps at 1436x992 resolution, surpassing existing systems in accuracy and speed.

Contribution

The authors develop a GPU implementation of stereo matching that balances high resolution processing with low error rates, which was not achieved in prior real-time systems.

Findings

Achieves 40 fps processing speed for high-resolution images.

Maintains the lowest error rate among fast GPU stereo systems.

Successfully implements cost aggregation, cross-checking, and median filtering on GPU.

Abstract

In this paper, we propose a low error rate and real-time stereo vision system on GPU. Many stereo vision systems on GPU have been proposed to date. In those systems, the error rates and the processing speed are in trade-off relationship. We propose a real-time stereo vision system on GPU for the high resolution images. This system also maintains a low error rate compared to other fast systems. In our approach, we have implemented the cost aggregation (CA), cross-checking and median filter on GPU in order to realize the real-time processing. Its processing speed is 40 fps for 1436x992 pixels images when the maximum disparity is 145, and its error rate is the lowest among the GPU systems which are faster than 30 fps.