Moving object segmentation for jittery videos, by clustering of stabilized latent trajectories
作者：
Highlights：
• Closed-form solution based optimization to stabilize jerky videos, using OTDM feature matrix
• Accurate tracking using pLSA for matrix factorization
• Ground truth for 16 real-world jerky videos as a new benchmark, for performance evaluation
• Jitter model using homography matrix, to corrupt stable videos with desired levels of jitter
• Superior performance of stabilized tracking on real-world and synthetic jitter patterns
摘要
•Closed-form solution based optimization to stabilize jerky videos, using OTDM feature matrix•Accurate tracking using pLSA for matrix factorization•Ground truth for 16 real-world jerky videos as a new benchmark, for performance evaluation•Jitter model using homography matrix, to corrupt stable videos with desired levels of jitter•Superior performance of stabilized tracking on real-world and synthetic jitter patterns
论文关键词：Video Stabilization,pLSA,Trajectory Clustering,GraphCut,Jitter Synthesis
论文评审过程：Received 9 March 2016, Revised 12 February 2017, Accepted 13 May 2017, Available online 21 May 2017, Version of Record 9 June 2017.
论文官网地址：https://doi.org/10.1016/j.imavis.2017.05.002
