Automated As-Is Modeling with Visual and Spatial Data Fusion

本提案的目的是评估申请人提出的框架是否可以将建筑物内部重建为面向对象的模型。根据所提出的框架，建筑物内部首先调查与便携式视觉和空间传感系统，它提供了一个流的视频帧沿着与每像素的深度值。基于视频帧中的建筑物元素的视觉图案来识别它们。占用像素被标记有语义标签，诸如“列”或“墙”。同时，通过匹配它们的联合视觉特征的位置并评估特征的深度值来提取任意两个视频帧之间的逐点3D对应关系。基于这些3D对应关系，估计帧之间的成对相对变换。这样，帧中的像素可以对齐以形成3D点的“云”。根据先前分配给像素的标签，云中的点可以被划分为多个部分并进行参数化建模。这种面向对象的参数化模型代表了感知的建筑内部，并可用于建筑内部的施工和改造。 这项研究背后的动机在于目前的手工和耗时的建模过程。原样模型记录建筑物的现有条件，这是有用的许多评估和管理任务，如翻新/改造规划，维护调度，项目质量控制等，但是，目前的原样建模过程需要大量的手动编辑和校正工作，这可能会占用超过三分之二的整体建模工作。大量的手工工作增加了建模成本，并限制了在绝大多数建筑和改造项目中使用原样模型。因此，由于设计和施工变更而导致的返工经常发生，其成本高达合同价值的10.29%。任何自动化建模过程的努力都将增加土木项目中原样模型的潜在用途，并减少不必要的返工。考虑到2010年加拿大的建筑业是一项价值738亿美元的业务，减少1%的返工将节省7590万美元。

The objective of this proposal is to evaluate whether a framework proposed by the applicant can reconstruct building interiors into an object-oriented model. According to the proposed framework, building interiors are first surveyed with a portable visual and spatial sensing system, which provides a stream of video frames along with per-pixel depth values. Building elements in the video frames are recognized based on their visual patterns. The occupying pixels are tagged with semantic labels, such as "column" or "wall". Meanwhile, a set of point-wise 3D correspondences between any two video frames are extracted by matching the locations of their joint visual features and evaluating the features' depth values. Based on these 3D correspondences, the pair-wise relative transformation between the frames is estimated. This way, the pixels in the frames can be aligned to form a "cloud" of 3D points. According to the labels previously assigned to the pixels, the points in the cloud can be divided into multiple parts and modeled parametrically. This object-oriented parametric model represents the perceived building interiors, and can be used for building interior construction and retrofit. The motivation behind this research lies in the manual and time-consuming nature of the current as-is modeling process. As-is models record building's existing conditions, which are useful for many assessment and management tasks, such as renovation/retrofit planning, maintenance scheduling, project quality control, etc. However, the current as-is modeling process requires a lot of manual editing and correction work, which could take up over two thirds of the overall modeling effort. The large volume of manual work increases modeling cost, and limits the use of as-is models in the vast majority of construction and retrofit projects. As a result, rework due to design and construction changes always happens, which costs up to 10.29% of the contract values. Any efforts towards automating this modeling process will increase the potential use of as-is models in civil projects and reduce unnecessary rework. Considering that construction was a $73.8 billion business in Canada in 2010, 1% of rework reduction would lead up to $75.9 million savings.