Performance Tests for Automatic 3D Geometric Data Registration Technique for Progressive As-Built Construction Site Modeling

Wang, C.; Cho, Y. K.; Park, J.

doi:10.1061/9780784413616.131

Cited by 7 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cost function in the original presentation included not only the distances between corresponding points, but also the error between unit vectors representing the direction of edges or the normal to faces of the model. This formulation was even later extended to deal with scale factors in [37].…”

Section: Using Screw Parametersmentioning

confidence: 99%

Approximating Displacements in ${\mathbb {R}}^3$ by Rotations in ${\mathbb {R}}^4$ and Its Application to Pointcloud Registration

Sarabandi

Thomas

2022

IEEE Trans. Robot.

View full text Add to dashboard Cite

No proper norm exists to measure the distance between two object poses essentially because a general pose is defined by a rotation and a translation, and thus it involves magnitudes with different units. As a means to solve this dimensionalinhomogeneity problem, the concept of characteristic length has been put forward in the area of kinematics. The idea consists in scaling translations according to this characteristic length and then approximating the corresponding displacement defining the object pose in R 3 by a rotation in R 4 , for which a norm exists. This paper sheds new light on this kind of approximations which permits simplifying optimization problem whose cost functions involve translations and rotations simultaneously. A good example of this kind of problems is the pointcloud registration problem in which the optimal rotation and translation between two sets of corresponding 3D point data, so that they are aligned/registered, have to be found. As a result, a simple closed-form formula for solving this problem is presented which is shown to be an attractive alternative to the previous approaches.

show abstract

Section: Using Screw Parametersmentioning

confidence: 99%

Approximating Displacements in ${\mathbb {R}}^3$ by Rotations in ${\mathbb {R}}^4$ and Its Application to Pointcloud Registration

Sarabandi

Thomas

2022

IEEE Trans. Robot.

View full text Add to dashboard Cite

show abstract

“…In order to provide proper safety measures, construction researchers have taken into account recent technological advances such as information and sensing technology as well as associated computational techniques. Using vision technology, researchers accomplished accurate real-time detection of workers [ 2 , 3 , 4 , 5 ], tracking of equipment and resources [ 6 , 7 , 8 ], productivity analysis [ 9 ], and a construction hazard avoidance system [ 10 ]. Wireless signal-based sensors have been explored for solutions towards labor tracking [ 11 , 12 , 13 ] and safety tracking [ 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

An Embedded Sensory System for Worker Safety: Prototype Development and Evaluation

Cho

Park

2018

Sensors

View full text Add to dashboard Cite

At a construction site, workers mainly rely on two senses, which are sight and sound, in order to perceive their physical surroundings. However, they are often hindered by the nature of most construction sites, which are usually dynamic, loud, and complicated. To overcome these challenges, this research explored a method using an embedded sensory system that might offer construction workers an artificial sensing ability to better perceive their surroundings. This study identified three parameters (i.e., intensity, signal length, and delay between consecutive pulses) needed for tactile-based signals for the construction workers to communicate quickly. We developed a prototype system based on these parameters, conducted experimental studies to quantify and validate the sensitivity of the parameters for quick communication, and analyzed test data to reveal what was added by this method in order to perceive information from the tactile signals. The findings disclosed that the parameters of tactile-based signals and their distinguishable ranges could be perceived in a short amount of time (i.e., a fraction of a second). Further experimentation demonstrated the capability of the identified unit signals combined with a signal mapping technique to effectively deliver simple information to individuals and offer an additional sense of awareness to the surroundings. The findings of this study could serve as a basis for future research in exploring advanced tactile-based messages to overcome challenges in environments for which communication is a struggle.

show abstract

“…However, ICP-based registration methods still incur problems with calculation time due to the heavy computation load involved in the ICP algorithm. Also, the performance may not be reliable depending on the overlapping area and the initial starting points [6].…”

Section: Iterative Closest Point (Icp) Basedmentioning

confidence: 99%

Target-Free Automatic Registration of Point Clouds

Kim¹,

Cho²,

Chen³

2016

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

-The aim of this paper is to introduce a novel method that automatically registers colored 3D point cloud sets without using targets or any other manual alignment processes. For fully automated point cloud registration without targets or landmarks, our approach utilizes feature detection algorithms used in computer vision. A digital camera and a laser scanner is utilized and the sensor data is merged based on a kinematic solution. The proposed approach is to detect and extract common features not directly from a 3D point cloud but from digital images corresponding to the point clouds. The initial alignment is achieved by matching common SURF features from corresponding digital images. Further alignment is obtained using plane segmentation and matching from the 3D point clouds. The test outcomes show promising results in terms of registration accuracy and processing time.

show abstract

Performance Tests for Automatic 3D Geometric Data Registration Technique for Progressive As-Built Construction Site Modeling

Cited by 7 publications

References 13 publications

Approximating Displacements in ${\mathbb {R}}^3$ by Rotations in ${\mathbb {R}}^4$ and Its Application to Pointcloud Registration

Approximating Displacements in ${\mathbb {R}}^3$ by Rotations in ${\mathbb {R}}^4$ and Its Application to Pointcloud Registration

An Embedded Sensory System for Worker Safety: Prototype Development and Evaluation

Target-Free Automatic Registration of Point Clouds

Contact Info

Product

Resources

About