We propose a compressed domain video object segmentation method for MPEG or MPEG-like encoded videos. Computational superiority is the main advantage of the compressed domain proc...
Fatih Murat Porikli, Faisal I. Bashir, Huifang Sun
In this paper we propose a high-S/N imaging method involving combining many images captured with small blur using a video camera capable of high-frame-rate image capturing at 1000...
We propose measures to evaluate the performance of video object segmentation and tracking methods quantitatively without ground-truth segmentation maps. The proposed measures are ...
A novel video object segmentation method is proposed which aims at combining color and motion information. The model has a multilayer structure: Each feature has its own layer, cal...
Non-linear interactive access to video is very important in video information management. The term non-linear refers to that there are more than one video streams delivering to us...