ConstructAide

Abstract

Figure 1: Our system aligns sets of photographs with 4D building models (a) to allow for new modes of construction-site interaction and visualization (using the ConstructAide GUI, b), such as architectural renderings (c), 4D navigation (d), and performance monitoring (e). AbstractWe describe a set of tools for analyzing, visualizing, and assessing architectural/construction progress with unordered photo collections and 3D building models. With our interface, a user guides the registration of the model in one of the images, and our system automatically computes the alignment for the rest of the photos using a novel Structure-from-Motion (SfM) technique; images with nearby viewpoints are also brought into alignment with each other. After aligning the photo(s) and model(s), our system allows a user, such as a project manager or facility owner, to explore the construction site seamlessly in time, monitor the progress of construction, assess errors and deviations, and create photorealistic architectural visualizations. These interactions are facilitated by automatic reasoning performed by our system: static and dynamic occlusions are removed automatically, rendering information is collected, and semantic selection tools help guide user input. We also demonstrate that our user-assisted SfM method outperforms existing techniques on both real-world construction data and established multiview datasets.

Automatic concrete defect detection and reconstruction by aligning aerial images onto semantic‐rich building information model

“…Even though learning-based semantic segmentation can automatically extract the SOI, they need to be trained with massive amounts of data and thus are not suggested. Inspired by the model-assisted SfM proposed by Karsch et al (2014), we proposed a BIM-assisted SfM pipeline to generate an as-is point cloud as "pure" as possible. First, pixels belonging to the SOI are extracted from a collection of aerial photographs.…”

“…Inspired by the model‐assisted SfM proposed by Karsch et al. (2014), we proposed a BIM‐assisted SfM pipeline to generate an as‐is point cloud as “pure” as possible. First, pixels belonging to the SOI are extracted from a collection of aerial photographs.…”

A Review of Augmented Reality Applications in Civil Infrastructure During the 4th Industrial Revolution

“…Later, D4AR was updated to the HD4AR system (Bae et al, 2013), enabling the application of available camera-equipped mobile devices. In 2014, bottomed on the D4AR system, manual occlusion management, and "X-ray" metaphors (Zollmann et al, 2012;Karsch et al (2014) combined a set of AR tools to build a valuable platform, ConstructAide, to monitor project progress. ConstructAide combined unordered photo collections and 3D models to obtain construction progress.…”

An Analysis of Potential Uses, Limitations and Barriers to Implementation of 3D Scan Data for Construction Management-Related Use—Are the Industry and the Technical Solutions Mature Enough for Adoption?

“…For a photogrammetric 3D point cloud to be usable, images need to have adequate quality in terms of resolution and blurriness and need to have at least 50-60% overlap in order to enable the execution of reality recreation using photogrammetry as a technique. If all conditions are met, photogrammetry can be used for progress monitoring [26][27][28][29][30], quality control [31][32][33] and 3D model generation [7,30,34] Videogrammetry is similar to photogrammetry. The difference is that 3D data are extracted from sequential frames of a video, which, in essence, is a string of at least 24 photographs taken in one second.…”