Cargando…

A Novel Central Camera Calibration Method Recording Point-to-Point Distortion for Vision-Based Human Activity Recognition

The camera is the main sensor of vison-based human activity recognition, and its high-precision calibration of distortion is an important prerequisite of the task. Current studies have shown that multi-parameter model methods achieve higher accuracy than traditional methods in the process of camera...

Descripción completa

Detalles Bibliográficos
Autores principales: Jin, Ziyi, Li, Zhixue, Gan, Tianyuan, Fu, Zuoming, Zhang, Chongan, He, Zhongyu, Zhang, Hong, Wang, Peng, Liu, Jiquan, Ye, Xuesong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9105339/
https://www.ncbi.nlm.nih.gov/pubmed/35591215
http://dx.doi.org/10.3390/s22093524
_version_ 1784708016408363008
author Jin, Ziyi
Li, Zhixue
Gan, Tianyuan
Fu, Zuoming
Zhang, Chongan
He, Zhongyu
Zhang, Hong
Wang, Peng
Liu, Jiquan
Ye, Xuesong
author_facet Jin, Ziyi
Li, Zhixue
Gan, Tianyuan
Fu, Zuoming
Zhang, Chongan
He, Zhongyu
Zhang, Hong
Wang, Peng
Liu, Jiquan
Ye, Xuesong
author_sort Jin, Ziyi
collection PubMed
description The camera is the main sensor of vison-based human activity recognition, and its high-precision calibration of distortion is an important prerequisite of the task. Current studies have shown that multi-parameter model methods achieve higher accuracy than traditional methods in the process of camera calibration. However, these methods need hundreds or even thousands of images to optimize the camera model, which limits their practical use. Here, we propose a novel point-to-point camera distortion calibration method that requires only dozens of images to get a dense distortion rectification map. We have designed an objective function based on deformation between the original images and the projection of reference images, which can eliminate the effect of distortion when optimizing camera parameters. Dense features between the original images and the projection of the reference images are calculated by digital image correlation (DIC). Experiments indicate that our method obtains a comparable result with the multi-parameter model method using a large number of pictures, and contributes a 28.5% improvement to the reprojection error over the polynomial distortion model.
format Online
Article
Text
id pubmed-9105339
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91053392022-05-14 A Novel Central Camera Calibration Method Recording Point-to-Point Distortion for Vision-Based Human Activity Recognition Jin, Ziyi Li, Zhixue Gan, Tianyuan Fu, Zuoming Zhang, Chongan He, Zhongyu Zhang, Hong Wang, Peng Liu, Jiquan Ye, Xuesong Sensors (Basel) Article The camera is the main sensor of vison-based human activity recognition, and its high-precision calibration of distortion is an important prerequisite of the task. Current studies have shown that multi-parameter model methods achieve higher accuracy than traditional methods in the process of camera calibration. However, these methods need hundreds or even thousands of images to optimize the camera model, which limits their practical use. Here, we propose a novel point-to-point camera distortion calibration method that requires only dozens of images to get a dense distortion rectification map. We have designed an objective function based on deformation between the original images and the projection of reference images, which can eliminate the effect of distortion when optimizing camera parameters. Dense features between the original images and the projection of the reference images are calculated by digital image correlation (DIC). Experiments indicate that our method obtains a comparable result with the multi-parameter model method using a large number of pictures, and contributes a 28.5% improvement to the reprojection error over the polynomial distortion model. MDPI 2022-05-05 /pmc/articles/PMC9105339/ /pubmed/35591215 http://dx.doi.org/10.3390/s22093524 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
Jin, Ziyi
Li, Zhixue
Gan, Tianyuan
Fu, Zuoming
Zhang, Chongan
He, Zhongyu
Zhang, Hong
Wang, Peng
Liu, Jiquan
Ye, Xuesong
A Novel Central Camera Calibration Method Recording Point-to-Point Distortion for Vision-Based Human Activity Recognition
title A Novel Central Camera Calibration Method Recording Point-to-Point Distortion for Vision-Based Human Activity Recognition
title_full A Novel Central Camera Calibration Method Recording Point-to-Point Distortion for Vision-Based Human Activity Recognition
title_fullStr A Novel Central Camera Calibration Method Recording Point-to-Point Distortion for Vision-Based Human Activity Recognition
title_full_unstemmed A Novel Central Camera Calibration Method Recording Point-to-Point Distortion for Vision-Based Human Activity Recognition
title_short A Novel Central Camera Calibration Method Recording Point-to-Point Distortion for Vision-Based Human Activity Recognition
title_sort novel central camera calibration method recording point-to-point distortion for vision-based human activity recognition
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9105339/
https://www.ncbi.nlm.nih.gov/pubmed/35591215
http://dx.doi.org/10.3390/s22093524
work_keys_str_mv AT jinziyi anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT lizhixue anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT gantianyuan anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT fuzuoming anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT zhangchongan anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT hezhongyu anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT zhanghong anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT wangpeng anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT liujiquan anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT yexuesong anovelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT jinziyi novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT lizhixue novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT gantianyuan novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT fuzuoming novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT zhangchongan novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT hezhongyu novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT zhanghong novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT wangpeng novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT liujiquan novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition
AT yexuesong novelcentralcameracalibrationmethodrecordingpointtopointdistortionforvisionbasedhumanactivityrecognition