Embedded real-time stereo estimation via Semi-Global Matching on the GPU

TL;DR

This paper presents a real-time, embedded GPU implementation of the Semi-Global Matching algorithm for stereo disparity estimation, achieving high frame rates on energy-efficient devices suitable for robotics and autonomous vehicles.

Contribution

The work introduces a real-time stereo depth estimation system on embedded GPUs using SGM, optimized for energy efficiency and high frame rates.

Findings

Runs at 42 fps on Tegra X1 for 640x480 images

Achieves reliable disparity estimation in real-time

Demonstrates suitability for robotics and autonomous systems

Abstract

Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems (ADAS) and autonomous vehicles. Semi-Global Matching (SGM) is a widely used algorithm that propagates consistency constraints along several paths across the image. This work presents a real-time system producing reliable disparity estimation results on the new embedded energy-efficient GPU devices. Our design runs on a Tegra X1 at 42 frames per second (fps) for an image size of 640x480, 128 disparity levels, and using 4 path directions for the SGM method.