Accurate vector extraction from design drawings is required first to automatically create 3D models from pixel-level engineering design drawings. However, this task faces the challenges of complicated design shapes as...Accurate vector extraction from design drawings is required first to automatically create 3D models from pixel-level engineering design drawings. However, this task faces the challenges of complicated design shapes as well as cumbersome and cluttered annotations on drawings, which interfere with the vector extraction heavily. In this article, the transmission tower containing the most complex structure is taken as the research object, and a semantic segmentation network is constructed to first segment the shape masks from the pixel-level drawings. Preprocessing and postprocessing are also proposed to ensure the stability and accuracy of the shape mask segmentation. Then, based on the obtained shape masks, a vector extraction network guided by heatmaps is designed to extract structural vectors by fusing the features from node heatmap and skeleton heatmap, respectively. Compared with the state-of-the-art methods, experiment results illustrate that the proposed semantic segmentation method can effectively eliminate the interference of many elements on drawings to segment the shape masks effectively, meanwhile, the model trained by the proposed vector extraction network can accurately extract the vectors such as nodes and line connections, avoiding redundant vector detection. The proposed method lays a solid foundation for automatic 3D model reconstruction and contributes to technological advancements in relevant fields.展开更多
Energy conservation and emissions reduction in the construction industry are important steps in achieving China’s goals of peak carbon emissions by 2030 and carbon neutrality by 2060.The premise for building carbon e...Energy conservation and emissions reduction in the construction industry are important steps in achieving China’s goals of peak carbon emissions by 2030 and carbon neutrality by 2060.The premise for building carbon emission(CE)reduction is to produce accurate CE calculations.Existing calculation methods for building CEs have many problems,such as complicated calculations,large data demands,time-consuming and laborious processes,weak design orientation of results,and poor feedback on emission reduction.At the same time,the calculation of CEs during the process of architectural design faces obstacles such as uncertainty of information,incomplete data,and difficulty in obtaining a bill of quantities based on design information.To resolve these obstacles,this study,based on a designer’s vocabulary and thinking mode,describes the construction of a“design-oriented”calculation methods for building-embodied carbon emissions(ECEs).The prediction and assessment of the impact on the building environment during the architectural design process were helpful for identifying the key areas for carbon reduction,exploring potential emission reduction hotspots,and providing timely feedback for design optimization,which can have important theoretical value and practical significance in promoting the construction of low-carbon buildings.展开更多
Applying the visual simulation technology to highway engineering, an expressway visual simulation system for the analysis of landscape design proposals is built during the construction of Xiaoxiang expressway. Its fun...Applying the visual simulation technology to highway engineering, an expressway visual simulation system for the analysis of landscape design proposals is built during the construction of Xiaoxiang expressway. Its functional requirements and overall architecture are presented. The 3D model of expressway is created with AutoCAD DWG files as source data and the dynamic design method of expressway landscape elements is introduced. A data analysis interface dedicated to the landscape evaluation is developed. The system offers an effective tool to facilitate the analysis and evaluation of the road landscape proposals.展开更多
基金funded by the Chinese State Grid Jiangsu Electric Power Co.,Ltd.Science and Technology Project Funding,Grant Number J2023031.
文摘Accurate vector extraction from design drawings is required first to automatically create 3D models from pixel-level engineering design drawings. However, this task faces the challenges of complicated design shapes as well as cumbersome and cluttered annotations on drawings, which interfere with the vector extraction heavily. In this article, the transmission tower containing the most complex structure is taken as the research object, and a semantic segmentation network is constructed to first segment the shape masks from the pixel-level drawings. Preprocessing and postprocessing are also proposed to ensure the stability and accuracy of the shape mask segmentation. Then, based on the obtained shape masks, a vector extraction network guided by heatmaps is designed to extract structural vectors by fusing the features from node heatmap and skeleton heatmap, respectively. Compared with the state-of-the-art methods, experiment results illustrate that the proposed semantic segmentation method can effectively eliminate the interference of many elements on drawings to segment the shape masks effectively, meanwhile, the model trained by the proposed vector extraction network can accurately extract the vectors such as nodes and line connections, avoiding redundant vector detection. The proposed method lays a solid foundation for automatic 3D model reconstruction and contributes to technological advancements in relevant fields.
基金supported by the National Key Research and Development Program of China(2022YFC3802701)the Key Research and Development Program of Shaanxi Province of China(2023-ZDLSF-66).
文摘Energy conservation and emissions reduction in the construction industry are important steps in achieving China’s goals of peak carbon emissions by 2030 and carbon neutrality by 2060.The premise for building carbon emission(CE)reduction is to produce accurate CE calculations.Existing calculation methods for building CEs have many problems,such as complicated calculations,large data demands,time-consuming and laborious processes,weak design orientation of results,and poor feedback on emission reduction.At the same time,the calculation of CEs during the process of architectural design faces obstacles such as uncertainty of information,incomplete data,and difficulty in obtaining a bill of quantities based on design information.To resolve these obstacles,this study,based on a designer’s vocabulary and thinking mode,describes the construction of a“design-oriented”calculation methods for building-embodied carbon emissions(ECEs).The prediction and assessment of the impact on the building environment during the architectural design process were helpful for identifying the key areas for carbon reduction,exploring potential emission reduction hotspots,and providing timely feedback for design optimization,which can have important theoretical value and practical significance in promoting the construction of low-carbon buildings.
基金Supported by the Communication Science and Technology Fund Item of Hubei Province(2003)
文摘Applying the visual simulation technology to highway engineering, an expressway visual simulation system for the analysis of landscape design proposals is built during the construction of Xiaoxiang expressway. Its functional requirements and overall architecture are presented. The 3D model of expressway is created with AutoCAD DWG files as source data and the dynamic design method of expressway landscape elements is introduced. A data analysis interface dedicated to the landscape evaluation is developed. The system offers an effective tool to facilitate the analysis and evaluation of the road landscape proposals.
