Real-time FPGA implementation of the Semi-Global Matching stereo vision algorithm for a 4K/UHD video stream

TL;DR

This paper presents a real-time FPGA implementation of the Semi-Global Matching stereo vision algorithm capable of processing 4K video streams at 30 fps, with modifications to support high-resolution and high-speed processing.

Contribution

The paper introduces a modified SGM algorithm implementation optimized for FPGA that supports 4K video at real-time frame rates, maintaining accuracy while meeting strict timing constraints.

Findings

Supports 4K/Ultra HD video at 30 fps

Achieves real-time processing with a 64-pixel disparity range

Provides results comparable to the original SGM implementation

Abstract

In this paper, we propose a real-time FPGA implementation of the Semi-Global Matching (SGM) stereo vision algorithm. The designed module supports a 4K/Ultra HD (3840 x 2160 pixels @ 30 frames per second) video stream in a 4 pixel per clock (ppc) format and a 64-pixel disparity range. The baseline SGM implementation had to be modified to process pixels in the 4ppc format and meet the timing constrains, however, our version provides results comparable to the original design. The solution has been positively evaluated on the Xilinx VC707 development board with a Virtex-7 FPGA device.