Social sensing in the field: Challenges in detecting social interactions in construction sites

Construction industry is a sector that is renowned for the slow uptake of new technologies. This is usually due to the conservative nature of this sector that relies heavily on tried and tested and successful old business practices. However, there is an eagerness in this industry to adopt Building Information Modelling (BIM) technologies to capture and record accurate information about a building project. But vast amounts of information and knowledge about the construction process is typically hidden within informal social interactions that take place in the work environment. In this paper we present a vision where smartphones and tablet devices carried by construction workers are used to capture the interaction and communication between workers in the field. Informal chats about decisions taken in the field, impromptu formation of teams, identification of key persons for certain tasks, and tracking the flow of information across the project community, are some pieces of information that could be captured by employing social sensing in the field. This information can not only be used during the construction to improve the site processes but it can also be exploited by the end user during maintenance of the building. We highlight the challenges that need to be overcome for this mobile and social sensing system to become a reality. © 2012 ACM.

Sparsity-Inducing Optimization Algorithm for the Extraction of Planar Structures in Noisy Point-Cloud Data

Most of the manual labor needed to create the geometric building information model (BIM) of an existing facility is spent converting raw point cloud data (PCD) to a BIM description. Automating this process would drastically reduce the modeling cost. Surface extraction from PCD is a fundamental step in this process. Compact modeling of redundant points in PCD as a set of planes leads to smaller file size and fast interactive visualization on cheap hardware. Traditional approaches for smooth surface reconstruction do not explicitly model the sparse scene structure or significantly exploit the redundancy. This paper proposes a method based on sparsity-inducing optimization to address the planar surface extraction problem. Through sparse optimization, points in PCD are segmented according to their embedded linear subspaces. Within each segmented part, plane models can be estimated. Experimental results on a typical noisy PCD demonstrate the effectiveness of the algorithm.