Video stabilization performance enhancement for low-texture videos
- PDF / 4,157,434 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 104 Downloads / 171 Views
ORIGINAL RESEARCH PAPER
Video stabilization performance enhancement for low‑texture videos Supriya Unnikrishnan1 · G. Sreelekha1 Received: 12 March 2018 / Accepted: 27 February 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract Digital video stabilization (DVS) aims to remove irregular global motion effects from an image sequence. This work aims at developing a real-time video stabilization algorithm for rectifying high-frequency jitter in marine surveillance applications. A DVS system consists of a global motion estimation system and motion correction system. The development of global motion estimation system resistant to failures in low texture videos is the primary goal. Due to the computational advantage and inherent properties, the phase correlation method is adopted as the basic global motion estimation algorithm. The basic algorithm is then modified to adapt to the varying texture content of the video sequences under consideration. An adaptive phase correlation-based global motion estimation is suggested and verified on the videos of varying textures. Keywords Video stabilization · Motion estimation · Phase correlation
1 Introduction Video processing can be broadly classified as (1) processing for quality enhancement; (2) processing for effective communication or storage and (3) processing for analysis. Since most of the video captured in real-life situations undergo quality degradations, the first stage of processing for quality enhancement comes as one of the most important and well-investigated stages in any video related application. The effectiveness of this stage is the key factor in deciding the efficiency of further stages such as video coding, analysis and overall improvement of visual experience. Though there are immense applications where these types of processing can be fitted into in general, in this work the focus is on the videos captured by surveillance systems operating in an outdoor environment, specifically marine surveillance. The major factors that hinder sustained quality in surveillance videos owe to haze, turbulence, shaky motion due to vibrations and low light. The sensor noise inherent in all capturing devices also affects them. Moreover, video surveillance applications rely on videos operating across the different spectrum for extracting useful information and further analysis. Infrared images captured during the night or low light * Supriya Unnikrishnan [email protected] 1
Department of Electronics and Communication, National Institute of Technology, Calicut, Kerala 673601, India
conditions is a typical example of this nature. Multi-spectral videos thus obtained will have some inherent defects such as poor resolution, low texture, and high noise. Hence an effective enhancement stage is mandatory in any video monitoring system operating in an outdoor environment. Processing of video data for quality enhancement in the general scenario involves various stages such as noise removal, brightness correction, and contrast improvement. But for a surv
Data Loading...
