Application Of Segmentation Of Object Video In Robot

DOI

10.2991/iiicec-15.2015.313How to use a DOI?

Keywords

near duplicated video detection; segmentation of object image; video key frames

Abstract

In order to eliminate the redundancy of the video on visual information and improve the matching speed of video sub-sequence, an efficient solution is to extract a set key frame which is far less than an entire video frame to represent the video content. The common practice of extracting the video key frames is to split the video camera, and then extract the key frames in visual content which is most representative of the lens from each lens. The method based on shot segmentation has limitations in the two aspects. There is redundant visual information on the lens with similar content; When the query video is very short (less than 5s), the granularity of key frame extraction is difficult to ensure the accuracy of detection.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Heng Gong
PY  - 2015/03
DA  - 2015/03
TI  - Application Of Segmentation Of Object Video In Robot
BT  - Proceedings of the 2015 International Industrial Informatics and Computer Engineering Conference
PB  - Atlantis Press
SP  - 1411
EP  - 1414
SN  - 2352-538X
UR  - https://doi.org/10.2991/iiicec-15.2015.313
DO  - 10.2991/iiicec-15.2015.313
ID  - Gong2015/03
ER  -