Video Stabilization Using Modified Blurriness Index Employing De-Blurring with Temporal Derivatives Using Motion Smoothing

Sábháilte in:
Sonraí bibleagrafaíochta
Foilsithe in:Traitement du Signal vol. 42, no. 3 (Jun 2025), p. 1457-1480
Príomhchruthaitheoir: Pandey, Sourabh
Rannpháirtithe: Jain, Prashant Kumar, Patel, Prabhat
Foilsithe / Cruthaithe:
International Information and Engineering Technology Association (IIETA)
Ábhair:
Rochtain ar líne:Citation/Abstract
Full Text - PDF
Clibeanna: Cuir clib leis
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!

MARC

LEADER 00000nab a2200000uu 4500
001 3231508462
003 UK-CbPIL
022 |a 0765-0019 
022 |a 1958-5608 
024 7 |a 10.18280/ts.420320  |2 doi 
035 |a 3231508462 
045 2 |b d20250601  |b d20250630 
100 1 |a Pandey, Sourabh 
245 1 |a Video Stabilization Using Modified Blurriness Index Employing De-Blurring with Temporal Derivatives Using Motion Smoothing 
260 |b International Information and Engineering Technology Association (IIETA)  |c Jun 2025 
513 |a Journal Article 
520 3 |a In low-cost portable cameras and camcorders, simple and fixed lens configurations are used. Items outside of the depth range appear fuzzy due to the short depth of focus of these cameras. Furthermore, videos taken with a hand-held camera include severe handshakes with jitters. As a result, it is critical to stabilize camera motions to increase video quality. Previous video stabilization (VS) solutions included de-blurring at the post-processing stage, resulting in erroneous measurement of motion parameters. To eliminate these estimation errors, this research suggests including de-blurring before implementing motion estimation (ME). The brightness of each pixel is convolved with the square of orthogonal temporal derivatives as a newly modified proposed blurriness index, which represents magnified objects and background motions. The proposed VS method to smooth the accidental motions and jitters in the movie has utilized an adaptive FIR filter. The simplified edge completion approach is designed to produce full-frame stabilized video sequences. The suggested method may accurately identify blurry frames at a cheap computational cost. Results present the performance comparison of the proposed blurriness index with the two most commonly used blurriness indexes. De-blurring the video before motion estimation improves the video stabilization quality. 
653 |a Computing costs 
653 |a Depth of field 
653 |a Cameras 
653 |a Methods 
653 |a Algorithms 
653 |a Blurring 
653 |a Video recordings 
653 |a Stabilization 
653 |a FIR filters 
653 |a Motion simulation 
700 1 |a Jain, Prashant Kumar 
700 1 |a Patel, Prabhat 
773 0 |t Traitement du Signal  |g vol. 42, no. 3 (Jun 2025), p. 1457-1480 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3231508462/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3231508462/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch