A Comparative Study for Indoor Planar Surface Segmentation via 3D Laser Point Cloud Data

Eruyar, Eyup Eymen; Yilmaz, Metehan; Yilmaz, Berat; Akbulut, Onur; Turgut, Kaya; Kaleci, Burak

doi:10.34248/bsengineering.735705

Cited by 2 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the basis of the previous formula, programming software is used to design the storage interval of 3D point cloud data as t. Assuming that the moving speed of the translation platform is represented by v, the Y coordinate of each row can be expressed by the following formula [11]:…”

Section: Museum Information Collection Based On 3d Lasermentioning

confidence: 99%

Computational Technologies on Modeling of Museum Interactive Virtual Display Based on User Experience

Zou

2022

Security and Communication Networks

View full text Add to dashboard Cite

In order to solve the problems of the traditional museum interactive virtual display modeling methods such as poor clarity, low user satisfaction, and long interactive response time, a museum interactive virtual display modeling method based on user experience was proposed. The museum information collection system is set up to collect 3D point cloud data of exhibits by using the system, and the 3D point cloud data are denoised by the moving least squares method. The museum building data and denoised 3D point cloud data are integrated, and all point cloud data are registered. According to the registration results, the interactive virtual display model of the museum is preliminarily constructed, and the user experience model is used to adjust the parameters of the display model to realize the interactive virtual display modeling of the museum. The simulation results show that the proposed method has a high definition of the interactive virtual display of a museum, the average user satisfaction is 9.45, and the interactive response time is always below 0.4s, which fully verifies the superiority of the proposed method.

show abstract

Section: Museum Information Collection Based On 3d Lasermentioning

confidence: 99%

Computational Technologies on Modeling of Museum Interactive Virtual Display Based on User Experience

Zou

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…These approaches have been frequently applied for segmentation problems since their implementations are available on Point Cloud Library (PCL) [20]. Besides, Eruyar et al [21] examined the performance of segmentation approaches situated in PCL for structural planar surfaces. However, only region growing and RANSAC approaches were employed to classify walls, ramps, and terrain.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of Point-Based Deep Learning Techniques for Semantic Classification in Search and Rescue Arenas

Turgut

Kaleci

2021

International Journal of Advances in Engineering and Pure Sciences

Self Cite

View full text Add to dashboard Cite

Post-disaster indoor environments, which occur after calamities such as floods, fires, and poisonous material spread, could include serious risks for search and rescue teams. For example, the building's structural integrity could be corrupted, and some harmful substances for humans and animals could exist. Exploiting robots could prevent search and rescue teams from these risks. Nevertheless, robots need to possess advanced techniques to produce high-level information from raw sensor data in these harsh environments. This study aims to explore the positive and negative aspects of point-based deep learning architectures for the semantic classification of ramps in search and rescue test arenas, which are proposed by the National Institute of Standards and Technology (NIST). Also, we take into account walls and terrain since they can provide crucial information for robots. In this study, we opted to utilize point cloud data that is robust against lousy illumination conditions, which is frequently encountered in post-disaster environments. We used the ESOGU RAMPS dataset that contains point cloud data captured from a simulated environment similar to NIST search and rescue arenas. We selected PointNet, PointNet++, Dynamic Graph Convolutional Neural Network (DGCNN), PointCNN, Point2Sequence, PointConv, and Shellnet point-based deep learning architectures to analyze their performance for semantic classification of ramps, walls, and terrain. The test results indicate that accuracy of semantic classification is over 90% for all architectures.

show abstract

A Comparative Study for Indoor Planar Surface Segmentation via 3D Laser Point Cloud Data

Cited by 2 publications

References 32 publications

Computational Technologies on Modeling of Museum Interactive Virtual Display Based on User Experience

Computational Technologies on Modeling of Museum Interactive Virtual Display Based on User Experience

A Comparative Study of Point-Based Deep Learning Techniques for Semantic Classification in Search and Rescue Arenas

Contact Info

Product

Resources

About