arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.00482cs.CV
收藏

实时的视频对象分割的状态感知跟踪器

State-Aware Tracker for Real-Time Video Object Segmentation

Zhejiang University(浙江大学);Megvii Inc.(旷视科技有限公司)

Xi Chen, Zuoxin Li, Ye Yuan, Gang Yu, Jianxin Shen, Donglian Qi

摘要:

在这项工作中,我们解决了半监督视频对象分割(VOS)的任务,并探讨如何有效地利用视频属性来应对半监督的挑战。我们提出了一种新的管道称为状态感知跟踪器(SAT),它可以产生准确的分割结果与实时的【形】速度。为了提高效率,SAT利用帧间一致性,并处理每个目标对象作为一个轨迹。为了在视频序列上获得更稳定和鲁棒的性能,SAT可以感知每个状态,并通过两个反馈回路进行自适应。一个循环帮助SAT生成更稳定的轨迹。另一个循环有助于构建更健壮和更全面的目标表示。SAT在DAVIS 2017-Val数据集上实现了72.3%J &F平均值和39 FPS的令人满意的结果,这表明效率和准确性之间的折衷。代码将在github.com/MegviiDetection/video_analyst上发布。

英文摘要:

In this work, we address the task of semi-supervised video object segmentation(VOS) and explore how to make efficient use of video property to tackle the challenge of semi-supervision. We propose a novel pipeline called State-Aware Tracker(SAT), which can produce accurate segmentation results with real-time speed. For higher efficiency, SAT takes advantage of the inter-frame consistency and deals with each target object as a tracklet. For more stable and robust performance over video sequences, SAT gets awareness for each state and makes self-adaptation via two feedback loops. One loop assists SAT in generating more stable tracklets. The other loop helps to construct a more robust and holistic target representation. SAT achieves a promising result of 72.3% J&F mean with 39 FPS on DAVIS2017-Val dataset, which shows a decent trade-off between efficiency and accuracy. Code will be released at github.com/MegviiDetection/video_analyst.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑