Background estimation for object segmentation using coarse level tracking

摘要

Embodiments described herein provide an apparatus comprising a processor configured to: receive an input video, convert the input video into one or more image sequences based at least in part on an analysis of movement of one or more objects in the input video, receive an indicator an object of interest in a first frame to be followed through multiple frames in the input video; and using a convolutional neural network to track the object of interest through the multiple frames in the input video. Other embodiments can be described and claimed.