基于Mask R-CNN的建筑立面图像门窗语义识别  

Semantic Recognition of Doors and Windows in Architectural Facade Images Based on Mask R-CNN

作　　者：孔文硕 陈达虎 徐照[3] Kong Wenshuo;Chen Dahu;Xu Zhao(College of Software,Southeast University,Suzhou 215028,China;Changzhou Building Research Institute Group Co.,Ltd.,Changzhou 213000,China;College of Civil Engineering,Southeast University,Nanjing 211100,China)

机构地区：[1]东南大学软件学院,苏州215028 [2]常州市建筑科学研究院集团股份有限公司,常州213000 [3]东南大学土木工程学院,南京211100

出　　处：《绿色建造与智能建筑》2024年第12期114-117,共4页Green Construction and Intelligent Building

基　　金：国家重点研发计划基金(2022YFC3803602);国家自然科学基金(72071043)。

摘　　要：建筑立面解析对于城市分析、语义重建、能源需求评估等需要高质量语义数据的任务至关重要,而传统的手动测量及建模方式往往十分耗时。本文探讨了基于迁移学习的Mask R-CNN网络对建筑外立面图像中的门窗进行自动坐标提取的方法。数据集方面选用当前基准数据集中标注图片数量最多的CMP数据集并为适应训练网络对原数据集进行了数据格式转换。结果表明该方法可在较高精准度基础上实现对建筑立面图像中门窗角点坐标的格式化输出。通过这项工作,希望为倾斜摄影等高细节层次的建筑三维建模领域的研究提供解决思路。Parsing building facades is crucial for tasks such as urban analysis,semantic reconstruction,and energy demand assessment,which require high-quality semantic data.However,traditional manual measurement and modeling methods are often time-consuming.This article explores a method based on transfer learning with Mask R-CNN networks for automatic extraction of door and window coordinates in building facade images.The dataset selected for this study is the CMP dataset,which is currently the benchmark dataset with the highest number of annotated images,and it was adapted to train the network by converting the data format.The results demonstrate that this method can achieve formatted output of door and window corner coordinates in building facade images with high precision.Through this work,we aim to provide a solution approach for research in the field of high-detail architectural 3Dmodeling,such as oblique photography.

关 键 词：建筑三维建模 立面解析 语义分割 迁移学习 

分 类 号：TU17[建筑科学—建筑理论]