FPGA-based Binocular Image Feature Extraction and Matching System

TL;DR

This paper presents an FPGA-based embedded system that accelerates binocular image feature extraction and matching, achieving high frame rates and robustness for machine vision applications.

Contribution

It introduces a novel FPGA implementation of SURF and BRIEF algorithms for real-time binocular feature matching, combining tracking and stereo matching.

Findings

Processes 640x480 video at 162 fps

Robust to image compression, blurring, and illumination

High frame rate and accuracy in feature matching

Abstract

Image feature extraction and matching is a fundamental but computation intensive task in machine vision. This paper proposes a novel FPGA-based embedded system to accelerate feature extraction and matching. It implements SURF feature point detection and BRIEF feature descriptor construction and matching. For binocular stereo vision, feature matching includes both tracking matching and stereo matching, which simultaneously provide feature point correspondences and parallax information. Our system is evaluated on a ZYNQ XC7Z045 FPGA. The result demonstrates that it can process binocular video data at a high frame rate (640$\times$480 @ 162fps). Moreover, an extensive test proves our system has robustness for image compression, blurring and illumination.