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

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.

References in corpus (1)

• Computing the Stereo Matching Cost with a Convolutional Neural Network

Cited by in corpus (13)

• Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices
• R${}^3$SGM: Real-time Raster-Respecting Semi-Global Matching for Power-Constrained Systems
• Real-Time Highly Accurate Dense Depth on a Power Budget using an FPGA-CPU Hybrid SoC
• ReS2tAC -- UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices
• Displacement-Invariant Cost Computation for Efficient Stereo Matching
• Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching
• An evaluation of Deep Learning based stereo dense matching dataset shift from aerial images and a large scale stereo dataset
• Stereo-LiDAR Fusion by Semi-Global Matching With Discrete Disparity-Matching Cost and Semidensification
• FP-Stereo: Hardware-Efficient Stereo Vision for Embedded Applications
• A Survey of FPGA-Based Robotic Computing
• Robust Full-FoV Depth Estimation in Tele-wide Camera System
• FaSS-MVS -- Fast Multi-View Stereo with Surface-Aware Semi-Global Matching from UAV-borne Monocular Imagery
• Fast and Differentiable Message Passing on Pairwise Markov Random Fields