Robust Performance Comparison of Unstable Videos and their Quality Improvement Implementing Block-Based Frame Matching Technique for Obtaining Digital Video Stabilization
Abhishek Pratap Singh1, Manoj Gupta2

1Mr. Abhishek Pratap Singh, M.Tech, Department of Electronics and Communication Engineering, JECRC University, Jaipur (Rajasthan). India.
2Mr. Manoj Gupta, Associate Professor, Department of Electronics and Communication Engineering, JECRC University, Jaipur (Rajasthan). India.

Manuscript received on 13 August 2016 | Revised Manuscript received on 20 August 2016 | Manuscript Published on 30 August 2016 | PP: 34-41 | Volume-5 Issue-6, August 2016 | Retrieval Number: F4676085616/16©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: In the context of Digital Image stabilization (DIS), based on morphological frame division and comparing, to estimate matching between local and global motion vectors by the means of averaging pixel information of frames; surprisingly proposes an indispensable Digital video stabilization (DVS) technique which can enhance the quality of an input video stream. Videos captured by hand-held devices (e.g. Cell phones, portable camcorders etc.) sometimes appear remarkably shaky hence Digital video stabilization technique can be implemented to refine the video quality by removing unwanted jitters. It’s an important step for several video processing amenities to acquire video stream without intervening jerkiness, eliminating unnecessary camera movements and withdrawing the superfluous inter frame motion between two successive frames. In order to get the stabilized video sequence, first promising step is to check the validity of local motion vector (LMV), and finally global motion vector (GMV) is obtained by averaging to further enhance the reliability. Here low pass filters and moving average filters are used for smoothing estimated motion vectors to get a stabilized sequence. Experiments show that this video stabilization technique is an efficient method to stabilize the input unstable video stream. In this paper we study the digital video stabilization technique with the use of keen motion estimation and finally performance comparison and conclusion of unstabilized and stabilized video sequence with the efficacy of our technique of digital video stabilization.
Keywords: Digital Video Stabilization (DVS), Digital Image Stabilization (DIS), Inter Frame Motion, Local Motion Vector (LMV), Global Motion vector (GV).

Scope of the Article: Network Performance; Protocols; Sensors