An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos
Identifying <italic>k</italic> ey frames is the first and necessary step before solving the variety of other <italic>B</italic> haratanatyam problems. The paper aims to partition the momentarily stationary frames (<italic>key frame</italic> s) from this dance vide...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9429237/ |
| _version_ | 1818950041341001728 |
|---|---|
| author | Himadri Bhuyan Partha Pratim Das Jatindra Kumar Dash Jagadeesh Killi |
| author_facet | Himadri Bhuyan Partha Pratim Das Jatindra Kumar Dash Jagadeesh Killi |
| author_sort | Himadri Bhuyan |
| collection | DOAJ |
| description | Identifying <italic>k</italic> ey frames is the first and necessary step before solving the variety of other <italic>B</italic> haratanatyam problems. The paper aims to partition the momentarily stationary frames (<italic>key frame</italic> s) from this dance video’s motion frames. The proposed <italic>key frame</italic> s (KFs) localization is novel, simple, and effective compared to the existing dance video analysis methods. It is distinctive from standard KFs detection algorithms as used in other human motion videos. In the dance’s basic structure, the occurrence of KFs during performances is often not completely stationary and varies with the dance form and the performer. Hence, it is not easy to decide a global threshold (on the quantum of motion) to work across dancers and performances. The earlier approaches try to compute the threshold iteratively. However, the novelty of the paper is: (a) formulating an adaptive threshold, (b) adopting Machine Learning (ML) approach and, (c) generating the effective feature by combining three frame differencing and bit-plane technique for the KF detection. In ML, we use Support Vector Machine (SVM) and Convolutional Neural Network (CNN) as the classifiers. The proposed approaches are also compared and analyzed with the earlier approaches. Finally, the proposed ML techniques emerge as a winner with around 90% accuracy. |
| first_indexed | 2024-12-20T09:12:17Z |
| format | Article |
| id | doaj.art-103ca028d7c34904a134a581193d328e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T09:12:17Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-103ca028d7c34904a134a581193d328e2022-12-21T19:45:30ZengIEEEIEEE Access2169-35362021-01-019726707268010.1109/ACCESS.2021.30793979429237An Automated Method for Identification of Key frames in Bharatanatyam Dance VideosHimadri Bhuyan0https://orcid.org/0000-0002-5105-9390Partha Pratim Das1Jatindra Kumar Dash2https://orcid.org/0000-0001-9067-8517Jagadeesh Killi3https://orcid.org/0000-0001-5230-0097Indian Institute of Technology Kharagpur, Kharagpur, IndiaIndian Institute of Technology Kharagpur, Kharagpur, IndiaDepartment of Computer Science and Engineering, SRM University AP, Amaravati, IndiaIndian Institute of Technology Kharagpur, Kharagpur, IndiaIdentifying <italic>k</italic> ey frames is the first and necessary step before solving the variety of other <italic>B</italic> haratanatyam problems. The paper aims to partition the momentarily stationary frames (<italic>key frame</italic> s) from this dance video’s motion frames. The proposed <italic>key frame</italic> s (KFs) localization is novel, simple, and effective compared to the existing dance video analysis methods. It is distinctive from standard KFs detection algorithms as used in other human motion videos. In the dance’s basic structure, the occurrence of KFs during performances is often not completely stationary and varies with the dance form and the performer. Hence, it is not easy to decide a global threshold (on the quantum of motion) to work across dancers and performances. The earlier approaches try to compute the threshold iteratively. However, the novelty of the paper is: (a) formulating an adaptive threshold, (b) adopting Machine Learning (ML) approach and, (c) generating the effective feature by combining three frame differencing and bit-plane technique for the KF detection. In ML, we use Support Vector Machine (SVM) and Convolutional Neural Network (CNN) as the classifiers. The proposed approaches are also compared and analyzed with the earlier approaches. Finally, the proposed ML techniques emerge as a winner with around 90% accuracy.https://ieeexplore.ieee.org/document/9429237/<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">K</italic>ey frame<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">A</italic>davuthree frame differencebit-plane extractionadaptive thresholdmachine learning |
| spellingShingle | Himadri Bhuyan Partha Pratim Das Jatindra Kumar Dash Jagadeesh Killi An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos IEEE Access <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">K</italic>ey frame <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">A</italic>davu three frame difference bit-plane extraction adaptive threshold machine learning |
| title | An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos |
| title_full | An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos |
| title_fullStr | An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos |
| title_full_unstemmed | An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos |
| title_short | An Automated Method for Identification of Key frames in Bharatanatyam Dance Videos |
| title_sort | automated method for identification of key frames in bharatanatyam dance videos |
| topic | <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">K</italic>ey frame <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">A</italic>davu three frame difference bit-plane extraction adaptive threshold machine learning |
| url | https://ieeexplore.ieee.org/document/9429237/ |
| work_keys_str_mv | AT himadribhuyan anautomatedmethodforidentificationofkeyframesinbharatanatyamdancevideos AT parthapratimdas anautomatedmethodforidentificationofkeyframesinbharatanatyamdancevideos AT jatindrakumardash anautomatedmethodforidentificationofkeyframesinbharatanatyamdancevideos AT jagadeeshkilli anautomatedmethodforidentificationofkeyframesinbharatanatyamdancevideos AT himadribhuyan automatedmethodforidentificationofkeyframesinbharatanatyamdancevideos AT parthapratimdas automatedmethodforidentificationofkeyframesinbharatanatyamdancevideos AT jatindrakumardash automatedmethodforidentificationofkeyframesinbharatanatyamdancevideos AT jagadeeshkilli automatedmethodforidentificationofkeyframesinbharatanatyamdancevideos |