Cargando…

Case Study: Improving the Quality of Dairy Cow Reconstruction with a Deep Learning-Based Framework

Three-dimensional point cloud generation systems from scanning data of a moving camera provide extra information about an object in addition to color. They give access to various prospective study fields for researchers. With applications in animal husbandry, we can analyze the characteristics of th...

Descripción completa

Detalles Bibliográficos
Autores principales: Dang, Changgwon, Choi, Taejeong, Lee, Seungsoo, Lee, Soohyun, Alam, Mahboob, Lee, Sangmin, Han, Seungkyu, Hoang, Duy Tang, Lee, Jaegu, Nguyen, Duc Toan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9736305/
https://www.ncbi.nlm.nih.gov/pubmed/36502026
http://dx.doi.org/10.3390/s22239325
_version_ 1784846992055205888
author Dang, Changgwon
Choi, Taejeong
Lee, Seungsoo
Lee, Soohyun
Alam, Mahboob
Lee, Sangmin
Han, Seungkyu
Hoang, Duy Tang
Lee, Jaegu
Nguyen, Duc Toan
author_facet Dang, Changgwon
Choi, Taejeong
Lee, Seungsoo
Lee, Soohyun
Alam, Mahboob
Lee, Sangmin
Han, Seungkyu
Hoang, Duy Tang
Lee, Jaegu
Nguyen, Duc Toan
author_sort Dang, Changgwon
collection PubMed
description Three-dimensional point cloud generation systems from scanning data of a moving camera provide extra information about an object in addition to color. They give access to various prospective study fields for researchers. With applications in animal husbandry, we can analyze the characteristics of the body parts of a dairy cow to improve its fertility and milk production efficiency. However, in the depth image generation from stereo data, previous solutions using traditional stereo matching algorithms have several drawbacks, such as poor-quality depth images and missing information in overexposed regions. Additionally, the use of one camera to reconstruct a comprehensive 3D point cloud of the dairy cow has several challenges. One of these issues is point cloud misalignment when combining two adjacent point clouds with the small overlapping area between them. In addition, another drawback is the difficulty of point cloud generation from objects which have little motion. Therefore, we proposed an integrated system using two cameras to overcome the above disadvantages. Specifically, our framework includes two main parts: data recording part applies state-of-the-art convolutional neural networks to improve the depth image quality, and dairy cow 3D reconstruction part utilizes the simultaneous localization and calibration framework in order to reduce drift and provide a better-quality reconstruction. The experimental results showed that our approach improved the quality of the generated point cloud to some extent. This work provides the input data for dairy cow characteristics analysis with a deep learning approach.
format Online
Article
Text
id pubmed-9736305
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97363052022-12-11 Case Study: Improving the Quality of Dairy Cow Reconstruction with a Deep Learning-Based Framework Dang, Changgwon Choi, Taejeong Lee, Seungsoo Lee, Soohyun Alam, Mahboob Lee, Sangmin Han, Seungkyu Hoang, Duy Tang Lee, Jaegu Nguyen, Duc Toan Sensors (Basel) Article Three-dimensional point cloud generation systems from scanning data of a moving camera provide extra information about an object in addition to color. They give access to various prospective study fields for researchers. With applications in animal husbandry, we can analyze the characteristics of the body parts of a dairy cow to improve its fertility and milk production efficiency. However, in the depth image generation from stereo data, previous solutions using traditional stereo matching algorithms have several drawbacks, such as poor-quality depth images and missing information in overexposed regions. Additionally, the use of one camera to reconstruct a comprehensive 3D point cloud of the dairy cow has several challenges. One of these issues is point cloud misalignment when combining two adjacent point clouds with the small overlapping area between them. In addition, another drawback is the difficulty of point cloud generation from objects which have little motion. Therefore, we proposed an integrated system using two cameras to overcome the above disadvantages. Specifically, our framework includes two main parts: data recording part applies state-of-the-art convolutional neural networks to improve the depth image quality, and dairy cow 3D reconstruction part utilizes the simultaneous localization and calibration framework in order to reduce drift and provide a better-quality reconstruction. The experimental results showed that our approach improved the quality of the generated point cloud to some extent. This work provides the input data for dairy cow characteristics analysis with a deep learning approach. MDPI 2022-11-30 /pmc/articles/PMC9736305/ /pubmed/36502026 http://dx.doi.org/10.3390/s22239325 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Dang, Changgwon
Choi, Taejeong
Lee, Seungsoo
Lee, Soohyun
Alam, Mahboob
Lee, Sangmin
Han, Seungkyu
Hoang, Duy Tang
Lee, Jaegu
Nguyen, Duc Toan
Case Study: Improving the Quality of Dairy Cow Reconstruction with a Deep Learning-Based Framework
title Case Study: Improving the Quality of Dairy Cow Reconstruction with a Deep Learning-Based Framework
title_full Case Study: Improving the Quality of Dairy Cow Reconstruction with a Deep Learning-Based Framework
title_fullStr Case Study: Improving the Quality of Dairy Cow Reconstruction with a Deep Learning-Based Framework
title_full_unstemmed Case Study: Improving the Quality of Dairy Cow Reconstruction with a Deep Learning-Based Framework
title_short Case Study: Improving the Quality of Dairy Cow Reconstruction with a Deep Learning-Based Framework
title_sort case study: improving the quality of dairy cow reconstruction with a deep learning-based framework
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9736305/
https://www.ncbi.nlm.nih.gov/pubmed/36502026
http://dx.doi.org/10.3390/s22239325
work_keys_str_mv AT dangchanggwon casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework
AT choitaejeong casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework
AT leeseungsoo casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework
AT leesoohyun casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework
AT alammahboob casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework
AT leesangmin casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework
AT hanseungkyu casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework
AT hoangduytang casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework
AT leejaegu casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework
AT nguyenductoan casestudyimprovingthequalityofdairycowreconstructionwithadeeplearningbasedframework