Enhancing boundary for video object segmentation

Qi Zhang, Xiaoqiang Lu, Yuan Yuan

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Video object segmentation aims to separate objects from background in successive video sequence accurately. It is a challenging task as the huge variance in object regions and similarity between object and background. Among previous methods, inner region of an object can be easily separated from background while the region around object boundary is often classified improperly. To address this problem, a novel video object segmentation method is proposed to enhance the object boundary by integrating video supervoxel into Convolutional Neural Network (CNN) model. Supervoxel is exploited in our method for its ability of preserving spatial details. The proposed method can be divided into four steps: 1) convolutional feature of video is extracted with CNN model; 2) supervoxel feature is constructed through averaging the convolutional features within each supervoxel to preserve spatial details of video; 3) the supervoxel feature and original convolutional feature are fused to construct video representation; 4) a softmax classifier is trained based on video representation to classify each pixel in video. The proposed method is evaluated both on DAVIS and Youtube-Objects datasets. Experimental results show that by considering supervoxel with spatial details, the proposed method can achieve impressive performance for video object segmentation through enhancing object boundary.

源语言英语
主期刊名Proceedings of the 2nd International Conference on Vision, Image and Signal Processing, ICVISP 2018
出版商Association for Computing Machinery
ISBN(电子版)9781450365291
DOI
出版状态已出版 - 27 8月 2018
已对外发布
活动2nd International Conference on Vision, Image and Signal Processing, ICVISP 2018 - Las Vegas, 美国
期限: 27 8月 201829 8月 2018

出版系列

姓名ACM International Conference Proceeding Series

会议

会议2nd International Conference on Vision, Image and Signal Processing, ICVISP 2018
国家/地区美国
Las Vegas
时期27/08/1829/08/18

指纹

探究 'Enhancing boundary for video object segmentation' 的科研主题。它们共同构成独一无二的指纹。

引用此