Cargando…

Bayesian-Inference Embedded Spline-Kerneled Chirplet Transform for Spectrum-Aware Motion Magnification

The ability to discern subtle image changes over time is useful in applications such as product quality control, civil engineering structure evaluation, medical video analysis, music entertainment, and so on. However, tiny yet useful variations are often combined with large motions, which severely d...

Descripción completa

Detalles Bibliográficos
Autores principales: Cai, Enjian, Li, Dongsheng, Lin, Jianyuan, Li, Hongnan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9002565/
https://www.ncbi.nlm.nih.gov/pubmed/35408408
http://dx.doi.org/10.3390/s22072794
_version_ 1784685921331838976
author Cai, Enjian
Li, Dongsheng
Lin, Jianyuan
Li, Hongnan
author_facet Cai, Enjian
Li, Dongsheng
Lin, Jianyuan
Li, Hongnan
author_sort Cai, Enjian
collection PubMed
description The ability to discern subtle image changes over time is useful in applications such as product quality control, civil engineering structure evaluation, medical video analysis, music entertainment, and so on. However, tiny yet useful variations are often combined with large motions, which severely distorts current video amplification methods bounded by external constraints. This paper presents a novel use of spectra to make motion magnification robust to large movements. By exploiting spectra, artificial limitations and the magnification of small motions are avoided at similar frequency levels while ignoring large ones at distinct spectral pixels. To achieve this, this paper constructs spline-kerneled chirplet transform (SCT) into an empirical Bayesian paradigm that applies to the entire time series, giving powerful spectral resolution and robust performance to noise in nonstationary nonlinear signal analysis. The important advance reported is Bayesian-rule embedded SCT (BE-SCT); two numerical experiments show its superiority over current approaches. For applying to spectrum-aware motion magnification, an elaborate analytical framework is established that captures global motion, and use of the proposed BE-SCT for dynamic filtering enables a frequency-based motion isolation. Our approach is demonstrated on real-world and synthetic videos. This approach shows superior qualitative and quantitative results with less visual artifacts and more local details over the state-of-the-art methods.
format Online
Article
Text
id pubmed-9002565
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90025652022-04-13 Bayesian-Inference Embedded Spline-Kerneled Chirplet Transform for Spectrum-Aware Motion Magnification Cai, Enjian Li, Dongsheng Lin, Jianyuan Li, Hongnan Sensors (Basel) Article The ability to discern subtle image changes over time is useful in applications such as product quality control, civil engineering structure evaluation, medical video analysis, music entertainment, and so on. However, tiny yet useful variations are often combined with large motions, which severely distorts current video amplification methods bounded by external constraints. This paper presents a novel use of spectra to make motion magnification robust to large movements. By exploiting spectra, artificial limitations and the magnification of small motions are avoided at similar frequency levels while ignoring large ones at distinct spectral pixels. To achieve this, this paper constructs spline-kerneled chirplet transform (SCT) into an empirical Bayesian paradigm that applies to the entire time series, giving powerful spectral resolution and robust performance to noise in nonstationary nonlinear signal analysis. The important advance reported is Bayesian-rule embedded SCT (BE-SCT); two numerical experiments show its superiority over current approaches. For applying to spectrum-aware motion magnification, an elaborate analytical framework is established that captures global motion, and use of the proposed BE-SCT for dynamic filtering enables a frequency-based motion isolation. Our approach is demonstrated on real-world and synthetic videos. This approach shows superior qualitative and quantitative results with less visual artifacts and more local details over the state-of-the-art methods. MDPI 2022-04-06 /pmc/articles/PMC9002565/ /pubmed/35408408 http://dx.doi.org/10.3390/s22072794 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
Cai, Enjian
Li, Dongsheng
Lin, Jianyuan
Li, Hongnan
Bayesian-Inference Embedded Spline-Kerneled Chirplet Transform for Spectrum-Aware Motion Magnification
title Bayesian-Inference Embedded Spline-Kerneled Chirplet Transform for Spectrum-Aware Motion Magnification
title_full Bayesian-Inference Embedded Spline-Kerneled Chirplet Transform for Spectrum-Aware Motion Magnification
title_fullStr Bayesian-Inference Embedded Spline-Kerneled Chirplet Transform for Spectrum-Aware Motion Magnification
title_full_unstemmed Bayesian-Inference Embedded Spline-Kerneled Chirplet Transform for Spectrum-Aware Motion Magnification
title_short Bayesian-Inference Embedded Spline-Kerneled Chirplet Transform for Spectrum-Aware Motion Magnification
title_sort bayesian-inference embedded spline-kerneled chirplet transform for spectrum-aware motion magnification
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9002565/
https://www.ncbi.nlm.nih.gov/pubmed/35408408
http://dx.doi.org/10.3390/s22072794
work_keys_str_mv AT caienjian bayesianinferenceembeddedsplinekerneledchirplettransformforspectrumawaremotionmagnification
AT lidongsheng bayesianinferenceembeddedsplinekerneledchirplettransformforspectrumawaremotionmagnification
AT linjianyuan bayesianinferenceembeddedsplinekerneledchirplettransformforspectrumawaremotionmagnification
AT lihongnan bayesianinferenceembeddedsplinekerneledchirplettransformforspectrumawaremotionmagnification