Progressive 3D reconstruction of infrastructure with videogrammetry

A number of methods are commonly used today to collect infrastructure's spatial data (time-of-flight, visual triangulation, etc.). However, current practice lacks a solution that is accurate, automatic, and cost-efficient at the same time. This paper presents a videogrammetric framework for acquiring spatial data of infrastructure which holds the promise to address this limitation. It uses a calibrated set of low-cost high resolution video cameras that is progressively traversed around the scene and aims to produce a dense 3D point cloud which is updated in each frame. It allows for progressive reconstruction as opposed to point-and-shoot followed by point cloud stitching. The feasibility of the framework is studied in this paper. Required steps through this process are presented and the unique challenges of each step are identified. Results specific to each step are also presented.

Research Highlights
► This paper evaluates the capability of a videogrammetric remote sensing method.
► The method is automatic, accurate, and cost efficient at the same time.
► A novel window matching algorithm automatically matches non-feature points.
► A Euclidean point cloud of infrastructure is progressively reconstructed.
► Point cloud-based measurements are compatible with tape measurements.