Moving Object Proposals with Deep Learned Optical Flow for Video Object Segmentation

arXiv:2402.08882v1 Announce Type: cross
Abstract: Dynamic scene understanding is one of the most conspicuous field of interest among computer vision community. In order to enhance dynamic scene understanding, pixel-wise segmentation with neural networks is widely accepted. The latest researches on pixel-wise segmentation combined semantic and motion information and produced good performance. In this work, we propose a state of art architecture of neural networks to accurately and efficiently get the moving object proposals (MOP). We first train an unsupervised convolutional …

abstract arxiv community computer computer vision cs.cv cs.lg dynamic flow information moving networks neural networks optical optical flow pixel proposals segmentation semantic type understanding video vision wise