Increase construction productivity using 3D computer vision & BIM to automate project progress and quality reporting.

使用 3D 计算机视觉提高施工效率

• 批准号: 104783
• 金额: $ 47.19万
• 依托单位: CONTILIO LIMITED
• 依托单位国家: 英国
• 项目类别: Collaborative R&D
• 财政年份: 2019
• 资助国家: 英国
• 起止时间: 2019 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=104783
• 关键词: Increase; construction; productivity; using; 3D

"The $12Tn construction industry contributes to 15% global GDP, but is one of the least productive and digitized sectors. This makes billion-dollar cost overruns and delays the industry norm and results in trillions getting wasted every year. One of the key drivers is the broken progress and quality reporting process. Currently, it takes 4 to 8 weeks for critical information to reach key stakeholders. This results in major rework and low productivity, adding significantly to project schedule, cost and scope risks.This project aims to develop an AI-enabled solution to measure construction progress for large property and infrastructure projects. Based on high-quality 3D Reality Capture data and using advanced machine learning techniques, the prototype will give real-time insights on project performance as well on productivity and risks. This will enable project owners, contractors and investors to improve short term planning and make timely and accurate decisions, transforming productivity, schedule and cost performance. Automated & reliable reporting will also establish ""one source of truth"" for all project stakeholders, enabling a range of other applications.This project is conducted by Contilio, a London-based deeptech startup, the Department of Civil, Environmental and Geomatic Engineering, University College London together with industry partners. It is aligned with the objectives of the UK Government Construction Strategy and ties into the overall BIM process."

“建筑业的产值为12万亿美元，占全球GDP的15%，但却是生产力和数字化程度最低的行业之一。这导致数十亿美元的成本超支，推迟了行业规范，并导致每年数万亿美元的浪费。其中一个关键驱动因素是进度和质量报告流程的不完整。目前，关键信息需要4至8周才能送达关键利益攸关方。该项目旨在开发一种支持AI的解决方案，以衡量大型房地产和基础设施项目的施工进度。该原型基于高质量的3D Reality Capture数据，并使用先进的机器学习技术，可以实时了解项目绩效以及生产力和风险。这将使项目所有者、承包商和投资者能够改进短期规划，并做出及时准确的决策，从而提高生产力、进度和成本效益。自动化和可靠的报告还将为所有项目利益相关者建立“一个真实的来源”，从而实现一系列其他应用。该项目由总部位于伦敦的深度科技初创公司Contilio、伦敦大学学院土木、环境和地质工程系以及行业合作伙伴共同实施。它与英国政府建设战略的目标保持一致，并与整个BIM流程相联系。"