A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Development of Point Cloud Data-Denoising Technology for Earthwork Sites Using Encoder-Decoder Network
https://orcid.org/http://orcid.org/0000-0003-0105-6578
https://orcid.org/http://orcid.org/0000-0003-0196-6037
https://orcid.org/http://orcid.org/0000-0003-1539-5714
Recently, the construction industry has acquired geographic information on-site and used it in various fields for effective project management. However, a point cloud containing geographic information can be corrupted with noise because of several factors, such as sensor performance limitations, which degrade data quality and make them difficult to use in the future. Numerous algorithms for filtering point clouds have been developed; however, they still have several shortcomings. In this study, a denoising model suitable for an earthwork site with good performance was developed using a deep-learning-based approach. The approach involved selecting the encoder—decoder network as the training network, and training and evaluation were performed using actual earthwork site data. The results show that the developed denoising model precisely maintains the geographical shape without loss of information and deep learning can overcome the limitations of conventional denoising methods.
Development of Point Cloud Data-Denoising Technology for Earthwork Sites Using Encoder-Decoder Network
https://orcid.org/http://orcid.org/0000-0003-0105-6578
https://orcid.org/http://orcid.org/0000-0003-0196-6037
https://orcid.org/http://orcid.org/0000-0003-1539-5714
Recently, the construction industry has acquired geographic information on-site and used it in various fields for effective project management. However, a point cloud containing geographic information can be corrupted with noise because of several factors, such as sensor performance limitations, which degrade data quality and make them difficult to use in the future. Numerous algorithms for filtering point clouds have been developed; however, they still have several shortcomings. In this study, a denoising model suitable for an earthwork site with good performance was developed using a deep-learning-based approach. The approach involved selecting the encoder—decoder network as the training network, and training and evaluation were performed using actual earthwork site data. The results show that the developed denoising model precisely maintains the geographical shape without loss of information and deep learning can overcome the limitations of conventional denoising methods.
Development of Point Cloud Data-Denoising Technology for Earthwork Sites Using Encoder-Decoder Network
https://orcid.org/http://orcid.org/0000-0003-0105-6578
https://orcid.org/http://orcid.org/0000-0003-0196-6037
https://orcid.org/http://orcid.org/0000-0003-1539-5714
Recently, the construction industry has acquired geographic information on-site and used it in various fields for effective project management. However, a point cloud containing geographic information can be corrupted with noise because of several factors, such as sensor performance limitations, which degrade data quality and make them difficult to use in the future. Numerous algorithms for filtering point clouds have been developed; however, they still have several shortcomings. In this study, a denoising model suitable for an earthwork site with good performance was developed using a deep-learning-based approach. The approach involved selecting the encoder—decoder network as the training network, and training and evaluation were performed using actual earthwork site data. The results show that the developed denoising model precisely maintains the geographical shape without loss of information and deep learning can overcome the limitations of conventional denoising methods.
Development of Point Cloud Data-Denoising Technology for Earthwork Sites Using Encoder-Decoder Network
KSCE J Civ Eng
Choi, Yeongjun (author) / Park, Suyeul (author) / Kim, Seok (author)
KSCE Journal of Civil Engineering ; 26 ; 4380-4389
2022-11-01
10 pages
Article (Journal)
Electronic Resource
English
| British Library Online Contents | 2013