中国机械工程 ›› 2026, Vol. 37 ›› Issue (1): 201-208.DOI: 10.3969/j.issn.1004-132X.2026.01.021

• 智能制造 • 上一篇    

基于轻量化高分辨率网络的双目视觉定位与测量

任加琪(), 许四祥(), 董宾卉, 汤澳, 宋昱宸   

  1. 安徽工业大学机械工程学院, 马鞍山, 243032
  • 收稿日期:2024-04-24 出版日期:2026-01-25 发布日期:2026-02-05
  • 通讯作者: 许四祥
  • 作者简介:任加琪,女,2000年生,硕士研究生。研究方向为机器视觉。E-mail: 1837433005@qq.com
    许四祥*(通信作者),男,1974年生,教授、硕士研究生导师。研究方向为机器人、机器视觉。发表论文70余篇。E-mail: xsxhust@ahut.edu.cn
  • 基金资助:
    国家自然科学基金(51374007);安徽高校自然科学研究重点项目(KJ2020A0259)

Binocular Vision Localization and Measurement Based on Lightweight HRNet

REN Jiaqi(), XU Sixiang(), DONG Binhui, TANG Ao, SONG Yuchen   

  1. School of Mechanical Engineering,Anhui University of Technology,Ma'anshan,Anhui,243032
  • Received:2024-04-24 Online:2026-01-25 Published:2026-02-05
  • Contact: XU Sixiang

摘要:

针对基于特征点检测的双目视觉测量效率低、神经网络计算复杂度高等问题,提出了基于轻量化高分辨率网络(HRNet)的双目视觉定位与测量方法。轻量化HRNet以HRNet为基准,先替换卷积模块、缩减参数量,再引入Transformer提取全局图像特征,最后使用多级上采样融合策略捕获多尺度特征信息。与原HRNet模型相比,轻量化HRNet模型参数减少95.40%,计算量、归一化平均误差分别减小94.27%和6.25%;三维测量上,轻量化HRNet与双目视觉结合方法的相对误差达到0.256%,能在低算力硬件上实现高精度检测。

关键词: 双目视觉, 高分辨率网络, 轻量化, 关键点检测, 尺寸测量

Abstract:

Aiming at the problems of low efficiency in binocular vision measurements based on feature point detection and high computational complexity of neural networks, a binocular vision localization and measurement method was proposed based on a lightweight HRNet. The lightweight HRNet was built upon the original HRNet by replacing the convolutional modules to reduce the number of parameters, introducing Transformer to extract global image features, and employing a multi-level upsampling fusion strategy to capture the multi-scale feature information. Compared with the original HRNet model, the lightweight HRNet reduces model parameters by 95.40%, while computational loads and normalized mean errors are decreased by 94.27% and 6.25% respectively. In terms of 3D measurement, the relative errors of the method combining lightweight HRNet with binocular vision reache 0.256%, enabling high-precision detection on hardware with low computational power.

Key words: binocular vision, high resolution net (HRNet), lightweight, landmark detection, measurement

中图分类号: