Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Convolutional Gated Recurrent Networks for Video Segmentation

Abstract: 

Semantic segmentation has recently witnessed major progress, but most of the previous work focused on improving single image segmentation. In this paper, we introduce a novel approach to implicitly utilize temporal data in videos for online segmentation. This design receives a sequence of consecutive video frames and outputs the segmentation of the last frame. Convolutional gated recurrent networks are used for the recurrent part to preserve spatial connectivities in the image. This architecture is tested for both binary and semantic video segmentation tasks. Experiments are conducted on the recent benchmarks in SegTrack V2, Davis, Camvid, and Synthia. Using recurrent fully convolutional networks improved the baseline network performance in all of our experiments. Namely, 5% and 3% improvement of F-measure in SegTrack2 and Davis respectively, 5.7% and 1.6% improvement in mean IoU in Synthia and Camvid. Thus, RFCN networks can be seen as a method to improve any baseline segmentation network by embedding them into a recurrent module that utilizes temporal data.

ICIP17.pdf

PDF icon ICIP17.pdf (13 downloads)
up
0 users have voted:

Paper Details

Authors:
Submitted On:
11 September 2017 - 11:14pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Mennatullah Siam
Document Year:
2017
Cite

Document Files

ICIP17.pdf

(13 downloads)

Subscribe

[1] , "Convolutional Gated Recurrent Networks for Video Segmentation", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1924. Accessed: Sep. 19, 2017.
@article{1924-17,
url = {http://sigport.org/1924},
author = { },
publisher = {IEEE SigPort},
title = {Convolutional Gated Recurrent Networks for Video Segmentation},
year = {2017} }
TY - EJOUR
T1 - Convolutional Gated Recurrent Networks for Video Segmentation
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1924
ER -
. (2017). Convolutional Gated Recurrent Networks for Video Segmentation. IEEE SigPort. http://sigport.org/1924
, 2017. Convolutional Gated Recurrent Networks for Video Segmentation. Available at: http://sigport.org/1924.
. (2017). "Convolutional Gated Recurrent Networks for Video Segmentation." Web.
1. . Convolutional Gated Recurrent Networks for Video Segmentation [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1924