《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (5): 1605-1612.DOI: 10.11772/j.issn.1001-9081.2023050687

• 多媒体计算与计算机仿真 • 上一篇    

面向复杂施工环境的实时目标检测算法

宋霄罡1,2(), 张冬冬1, 张鹏飞1, 梁莉1, 黑新宏1,2   

  1. 1.西安理工大学 计算机科学与工程学院,西安 710048
    2.人机共融智能机器人陕西省高校工程研究中心,西安 710048
  • 收稿日期:2023-05-30 修回日期:2023-09-12 接受日期:2023-09-14 发布日期:2023-09-19 出版日期:2024-05-10
  • 通讯作者: 宋霄罡
  • 作者简介:张冬冬(1998—),男,湖南郴州人,硕士研究生,主要研究方向:目标检测、视频行为识别
    张鹏飞(1998—),男,河南三门峡人,硕士研究生,主要研究方向:目标检测、伪装物体检测
    梁莉(1964—),女,陕西西安人,副教授,硕士,主要研究方向:深度学习、机器视觉
    黑新宏(1976—),男,陕西西安人,教授,博士生导师,博士,CCF杰出会员,主要研究方向:人工智能、智能建造。
    第一联系人:宋霄罡(1987—),男,河南漯河人,副教授,博士,主要研究方向:计算机视觉、无人系统自主导航
  • 基金资助:
    国家重点研发计划项目(2022YFB2602203)

Real-time object detection algorithm for complex construction environments

Xiaogang SONG1,2(), Dongdong ZHANG1, Pengfei ZHANG1, Li LIANG1, Xinhong HEI1,2   

  1. 1.Faculty of Computer Science and Engineering,Xi’an University of Technology,Xi’an Shaanxi 710048,China
    2.Human Machine Integration Intelligent Robot Shaanxi Provincial University Engineering Research Center,Xi’an Shaanxi 710048,China
  • Received:2023-05-30 Revised:2023-09-12 Accepted:2023-09-14 Online:2023-09-19 Published:2024-05-10
  • Contact: Xiaogang SONG
  • About author:ZHANG Dongdong, born in 1998, M. S. candidate. His research interests include object detection, video action recognition.
    ZHANG Pengfei, born in 1998, M. S. candidate. His research interests include object detection, camouflage object detection.
    LIANG Li, born in 1964, M. S., associate professor. Her research interests include deep learning, machine vision.
    HEI Xinhong, born in 1976, Ph. D., professor. His research interests include artificial intelligence, intelligent construction.
  • Supported by:
    National Key R&D Program of China(2022YFB2602203)

摘要:

针对施工环境下普遍存在的环境杂乱、目标被遮挡、目标尺度范围大、正负样本不平衡、现有检测算法实时性不足等问题,提出一种面向复杂施工环境的实时目标检测算法YOLO-C。将提取到的低层特征与高层特征相融合,增强网络全局感知能力;设计小目标检测层,提高算法对不同尺度目标的检测精度;设计通道-空间注意力(CSA)模块,增强目标特征,抑制背景特征;在损失函数部分,采用VariFocal Loss计算分类损失,解决正负样本不平衡问题;GhostConv作为基本卷积块构建GCSP(Ghost Cross Stage Partial)结构,降低参数量和计算量;针对复杂施工环境,构建混凝土施工现场目标检测数据集,在构建的数据集上与多个算法进行对比分析实验。实验结果表明,YOLO-C算法的检测精度更高,参数量更小,更适合复杂施工环境下的目标检测任务。

关键词: 实时目标检测, YOLOv5s, 混凝土施工现场, 注意力机制, 轻量化

Abstract:

A real-time object detection algorithm YOLO-C for complex construction environment was proposed for the problems of cluttered environment, obscured objects, large object scale range, unbalanced positive and negative samples, and insufficient real-time of existing detection algorithms, which commonly exist in construction environment. The extracted low-level features were fused with the high-level features to enhance the global sensing capability of the network, and a small object detection layer was designed to improve the detection accuracy of the algorithm for objects of different scales. A Channel-Spatial Attention (CSA) module was designed to enhance the object features and suppress the background features. In the loss function part, VariFocal Loss was used to calculate the classification loss to solve the problem of positive and negative sample imbalance. GhostConv was used as the basic convolutional block to construct the GCSP (Ghost Cross Stage Partial) structure to reduce the number of parameters and the amount of computation. For complex construction environments, a concrete construction site object detection dataset was constructed, and comparison experiments for various algorithms were conducted on the constructed dataset. Experimental results demonstrate that the YOLO?C has higher detection accuracy and smaller parameters, making it more suitable for object detection tasks in complex construction environments.

Key words: real-time object detection, YOLOv5s, concrete construction site, attention mechanism, lightweight

中图分类号: