Automatic aircraft extraction using video matting and frame registration. Issue 8 (15th May 2020)

• Record Type: Journal Article
• Authors: Amin, Benish; Mohsin Riaz, Muhammad; Ghafoor, Abdul
• Is Part Of: IET image processing. Volume 14:Issue 8(2020)
• Page Start: 1628
• Page End: 1635
• Publication Date: 2020-05-15
• Subjects: feature extraction -- image sequences -- object detection -- image colour analysis -- image segmentation -- medical image processing -- image processing -- object tracking -- video signal processing -- image registration; automatic aircraft extraction -- video matting -- video sequence -- object tracking algorithm -- computational complexity -- given ROI -- nonrigid image registration -- alpha mattes -- KNN matting algorithm -- static region -- final alpha matte -- different videos -- high quality alpha maps; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0067
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : This study presents a technique to automatically extract the aircraft from video sequences. The technique incorporates object tracking algorithm to separate the region of interest (ROI), i.e. movement of aircraft, from video sequence, to reduce the computational complexity. Trimaps are generated automatically for given ROI using non‐rigid image registration to obtain the prior information of the object and alpha mattes are estimated for each frame using KNN matting algorithm. However, the alpha matte of static region is estimated only once, that is combined with the alpha matte of moving region to generate final alpha matte. Simulations performed on different videos show that the proposed technique not only reduces the computational complexity, but also gives competitive results by generating high quality alpha maps.