Image to Decision AI for Real Estate Valuation (Imatod)
Image to Decision AI for Real Estate Valuation (Imatod)
批准号:
105772
负责人:
金额:
$89.06万
依托单位:
依托单位国家:
英国
项目类别:
Study
财政年份:
2020
资助国家:
英国
项目状态:
已结题
起止时间:
2020 至 --
中文摘要
Imatod将利用虚拟视图App现有的生态系统来提取360°图像中包含的大量非结构化数据,以增强对AVM数据的信心水平,并消除对低至中等风险物业进行抵押贷款估值的物理检查的需要。现有的生态系统包括Vieweet360和Smart view,它们分别由低成本的可扩展360°图像技术和用于360°虚拟物业之旅的开放协议平台组成。Imatod将通过开发创新的计算机视觉(360°图像的认知分析)和应用复杂的机器学习(辅之以观众和摄影师的输入)来利用这些数据来评估物业内部的状态并验证捕获图像的日期/位置。因此,Imatod将通过提供室内信息(商业上可用的AVM目前对此视而不见),全面实现物业评估过程的数字化,并提高对AVM数据的置信度,并改进向监管机构的报告。Imatod还将使申请者获得抵押贷款的成本更低、速度更快,因为它不需要经常需要2-3周的实物检查,每个任务平均需要500 GB。Imatod AVM将允许抵押贷款机构提供即时抵押贷款,为所有利益相关者带来好处。
英文摘要
Imatod will leverage Virtual View App's existing eco-system to extract the vast amount of unstructured data comprised in the 360° imagery to enhance confidence levels in AVM's data and eliminate the need of physical inspection for low-to-medium risk properties for mortgage valuation. The existing eco-system consists of Vieweet360 and Smart Viewing, these are made of a low cost scalable 360° imagery technology and an open protocol platform for 360° virtual tour of properties respectively. Imatod will leverage these data through the development of an innovative computer vision (Cognitive analysis of 360° imagery) and the application of complex machine learning (supplemented by input from viewers and photographers) to evaluate the state of properties' interior and authenticate the date/location of captured imagery.As a result, Imatod will fully digitise the property valuation process and enhance confidence level in AVMs' data by providing information on interiors, which commercially available AVMs are currently blind to, and improve reporting to the regulators. Imatod will also make it cheaper and faster for applicants to access mortgage loans by eliminating the need for physical inspections which often require 2-3 weeks and an average of £500 per mandate. Imatod AVM will allow mortgage lenders to provide instant mortgage offering, bringing benefits to all stakeholders.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
国内基金
海外基金
Scalable Learning and Optimization: High-dimensional Models and Online Decision-Making Strategies for Big Data Analysis
-
批准号:--
-
项目类别:合作创新研究团队
-
资助金额:--
-
批准年份:2024
-
负责人:姚韬
-
依托单位: