测绘通报 ›› 2025, Vol. 0 ›› Issue (3): 161-167.doi: 10.13474/j.cnki.11-2246.2025.0328

• 技术交流 • 上一篇    

一种基于改进U-Net算法的建筑垃圾堆放检测与识别方法

邹伟林1,2, 周文1,2, 张永利1,2, 高思岩1,2,3, 王普亮1,2   

  1. 1. 正元地理信息集团股份有限公司, 北京 101300;
    2. 北京市智慧管网安全评价及运营监管工程技术研究中心, 北京 101300;
    3. 北京建筑大学测绘与城市空间信息学院, 北京 102616
  • 收稿日期:2024-06-18 发布日期:2025-04-03
  • 通讯作者: 高思岩。E-mail:gsy@geniuses.com.cn
  • 作者简介:邹伟林(1989—),男,工程师,研究方向为智能遥感解译。E-mail:1315882510@qq.com
  • 基金资助:
    福建省科学技术厅区域发展项目(2023Y3001);中国冶金地质总局科研项目(CMGBKY202307)

A construction waste pile detection and identification method based on improved U-Net algorithm

ZOU Weilin1,2, ZHOU Wen1,2, ZHANG Yongli1,2, GAO Siyan1,2,3, WANG Puliang1,2   

  1. 1. Zhengyuan Geographic Information Group Co., Ltd., Beijing 101300, China;
    2. Beijing Engineering Research Center of Intelligent Pipe Network Assessment and Operating Regulation, Beijing 101300, China;
    3. School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 102616, China
  • Received:2024-06-18 Published:2025-04-03

摘要: 当前我国在实际生产建设中产生的建筑垃圾体量大且成分复杂,若未经妥善处理,部分成分会与周围环境发生反应造成健康隐患,导致的后果难以估量。此外,在“无废城市”建设政策的要求下,建筑垃圾成为当前解决环境问题的重要议题。本文在自主采集的建筑垃圾数据集的基础上,提出了一种U-Net算法改进模型。该模型依托于原始U-Net网络,将主干网络引入ResNet残差网络、小波变换和注意力机制模块,不但有效解决了原始模型出现的梯度消失、边缘特征模糊等问题,还在mIoU、mPA、F1分数等性能指标上,与其他模型相比有较大的提升,且模型的整体性能较平稳,可成功且高效地完成建筑垃圾堆放识别与检测任务。以河南省平顶山市卫东区下辖街道作为试验区域进行应用验证,结果表明,该识别检测模型可有效识别检测出建筑垃圾的覆盖范围,且精度达到实际应用要求,可为实现建筑垃圾管理与处置提供重要的决策支持。

关键词: 建筑垃圾, U-Net算法, 模型优化, 识别检测, 建筑垃圾管理

Abstract: At present, China's actual production and construction of large volumes of construction waste and complex composition, if not properly handled, some of the components will react with the surrounding environment to form a health hazard, resulting in immeasurable consequences. In addition, under the policy of “waste-free city”, construction waste has become an important issue in solving environmental problems. This paper proposes an improved model of U-Net algorithm based on the construction waste dataset collected independently. Relying on the original U-Net network, the model introduces ResNet residual network, wavelet transform and attention mechanism module into the backbone network, which not only effectively solves the problems of gradient disappearance and blurring of edge features of the original model, but also improves the performance indexes such as mIOU, mPA,F1 score, etc., compared with some other models, and the overall performance of the model is smoother, so that the model can successfully and efficiently accomplish the construction waste stacking and disposal. The overall performance of the model is smooth, which can successfully and efficiently accomplish the task of recognizing and detecting the construction waste dumping.Finally, the streets under the jurisdiction of Weidong district, Pingdingshan city, Henan province, are used as the experimental area for the application of the results to verify the results. The experimental results show that the identification and detection model can effectively identify and detect the coverage of construction waste, and the accuracy of identification and detection meets the requirements of practical application, which can provide important decision support for the realization of construction waste management and disposal.

Key words: construction waste, U-Net algorithm, model optimization, recognition detection, construction waste management

中图分类号: