Cargando…

Deep Learned Quantization-Based Codec for 3D Airborne LiDAR Point Cloud Images

This paper introduces a novel deep learned quantization-based coding for 3D Airborne LiDAR (Light detection and ranging) point cloud (pcd) image (DLQCPCD). The raw pcd signals are sampled and transformed by applying the Nyquist signal sampling and Min-max signal transformation techniques, respective...

Descripción completa

Detalles Bibliográficos
Autores principales: Tamilmathi, A. Christoper, Chithra, P. L.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8155491/
https://www.ncbi.nlm.nih.gov/pubmed/34055900
http://dx.doi.org/10.3389/frobt.2021.606770
_version_ 1783699215861415936
author Tamilmathi, A. Christoper
Chithra, P. L.
author_facet Tamilmathi, A. Christoper
Chithra, P. L.
author_sort Tamilmathi, A. Christoper
collection PubMed
description This paper introduces a novel deep learned quantization-based coding for 3D Airborne LiDAR (Light detection and ranging) point cloud (pcd) image (DLQCPCD). The raw pcd signals are sampled and transformed by applying the Nyquist signal sampling and Min-max signal transformation techniques, respectively for improving the efficiency of the training process. Then, the transformed signals are feed into the deep learned quantization module for compressing the data. To the best of our knowledge, this proposed DLQCPCD is the first deep learning-based model for 3D airborne LiDAR pcd compression. The functions of Mean Squared Error and Stochastic Gradient Descent optimization function enhance the quality of the decompressed image by 67.01 percent on average, compared to other functions. The model’s efficiency has been validated with established well-known compression techniques such as the 7-Zip, WinRAR, and tensor tucker decomposition algorithm on the three inconsistent airborne datasets. The experimental results show that the proposed model compresses every pcd image into constant 16 Number of Neurons of data and decompresses the image with approximately 160 dB of PSNR value, 174.46 s execution time with 0.6 s execution speed per instruction, and proved that it outperforms the other existing algorithms regarding space and time.
format Online
Article
Text
id pubmed-8155491
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-81554912021-05-28 Deep Learned Quantization-Based Codec for 3D Airborne LiDAR Point Cloud Images Tamilmathi, A. Christoper Chithra, P. L. Front Robot AI Robotics and AI This paper introduces a novel deep learned quantization-based coding for 3D Airborne LiDAR (Light detection and ranging) point cloud (pcd) image (DLQCPCD). The raw pcd signals are sampled and transformed by applying the Nyquist signal sampling and Min-max signal transformation techniques, respectively for improving the efficiency of the training process. Then, the transformed signals are feed into the deep learned quantization module for compressing the data. To the best of our knowledge, this proposed DLQCPCD is the first deep learning-based model for 3D airborne LiDAR pcd compression. The functions of Mean Squared Error and Stochastic Gradient Descent optimization function enhance the quality of the decompressed image by 67.01 percent on average, compared to other functions. The model’s efficiency has been validated with established well-known compression techniques such as the 7-Zip, WinRAR, and tensor tucker decomposition algorithm on the three inconsistent airborne datasets. The experimental results show that the proposed model compresses every pcd image into constant 16 Number of Neurons of data and decompresses the image with approximately 160 dB of PSNR value, 174.46 s execution time with 0.6 s execution speed per instruction, and proved that it outperforms the other existing algorithms regarding space and time. Frontiers Media S.A. 2021-05-13 /pmc/articles/PMC8155491/ /pubmed/34055900 http://dx.doi.org/10.3389/frobt.2021.606770 Text en Copyright © 2021 Tamilmathi and Chithra. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Robotics and AI
Tamilmathi, A. Christoper
Chithra, P. L.
Deep Learned Quantization-Based Codec for 3D Airborne LiDAR Point Cloud Images
title Deep Learned Quantization-Based Codec for 3D Airborne LiDAR Point Cloud Images
title_full Deep Learned Quantization-Based Codec for 3D Airborne LiDAR Point Cloud Images
title_fullStr Deep Learned Quantization-Based Codec for 3D Airborne LiDAR Point Cloud Images
title_full_unstemmed Deep Learned Quantization-Based Codec for 3D Airborne LiDAR Point Cloud Images
title_short Deep Learned Quantization-Based Codec for 3D Airborne LiDAR Point Cloud Images
title_sort deep learned quantization-based codec for 3d airborne lidar point cloud images
topic Robotics and AI
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8155491/
https://www.ncbi.nlm.nih.gov/pubmed/34055900
http://dx.doi.org/10.3389/frobt.2021.606770
work_keys_str_mv AT tamilmathiachristoper deeplearnedquantizationbasedcodecfor3dairbornelidarpointcloudimages
AT chithrapl deeplearnedquantizationbasedcodecfor3dairbornelidarpointcloudimages