Generating Absolute-Scale Point Cloud Data of Built Infrastructure Scenes Using a Monocular Camera Setting

Abstract

The global scale of Point Cloud Data (PCD) generated through monocular photo/videogrammetry is unknown, and can be calculated using at least one known dimension of the scene. Measuring one or more dimensions for this purpose induces a manual step in the 3D reconstruction process; this increases the effort and reduces the speed of reconstructing scenes, and induces substantial human error in the process due to the high level of measurement accuracy needed. Other ways of measuring such dimensions are based on acquiring additional information by either using extra sensors or specific classes of objects existing in the scene; we found that these solutions are not simple, cost effective or general enough to be considered practical for reconstructing both indoor and outdoor built infrastructure scenes. To address the issue, in this paper, we propose a novel method for automatically calculating the absolute scale of built infrastructure PCD. We use a premeasured cube for outdoor scenes and a sheet of paper for indoor environments as the calibration patterns. Assuming that the dimensions of these objects are known, the proposed method extracts the objects' corner points in 2D video frames using a novel algorithm. The

Automated as-built 3D reconstruction of civil infrastructure using computer vision: Achievements, opportunities, and challenges

“…The standard practice for estimating the scale factor is to manually measure the distance between two points in the scene and use this reference measurement to scale the reconstruction accordingly. The automation of this process has been studied in several papers such as [123][124][125] by considering a known motion or an object with known dimensions. The use of additional sensor data such as laser readings, GPS, inertial measurement units, gyroscope and accelerometer, etc.…”

Automated assembly discrepancy feedback using 3D imaging and forward kinematics

“…These promising approaches include laser scanning [15,18], image-based techniques [16,[19][20][21], videogrammetry [22,23], and range imaging [17,24]. Automated and accurate as-built status acquisition results in a reliable and robust assessment of the built status of civil infrastructure [14,25,26].…”

Automatically Determining Scale Within Unstructured Point Clouds

“…This method is semi-automatic as a particular object needs to be identified within each scene but it only needs to be measured once. An example of this is illustrated in the work by Rashidi et al (2014) where a pre-measured cube is placed within a scene that is captured using a monocular camera setup. Using Structure from Motion (SfM) the distance between subsequent frames of a video feed or collection of images can be recovered and used to propagate an arbitrary scale throughout the resulting point cloud.…”