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

facebooktwittermailshare

Semantic Segmentation in Compressed Videos

Abstract: 

Existing approaches for semantic segmentation in
videos usually extract each frame as an RGB image, then apply
standard image-based semantic segmentation models on each
frame. This is time-consuming. In this paper, we tackle this
problem by exploring the nature of video compression techniques.
A compressed video contains three types of frames, I-frames,
P-frames, and B-frames. I-frames are represented as regular
images, P-frames are represented as motion vectors and residual
errors, and B-frames are bidirectionally frames that can be
regarded as a special case of a P frame. We propose a method
that directly operates on I-frames (as RGB images) and P-frames
(motion vectors and residual errors) in a video. Our
proposed model uses a ConvLSTM model to capture the temporal
information in the video required for producing the semantic
segmentation on P-frames. Our experimental results show that
our method performs much faster than other alternatives while
achieving similar performance in terms of accuracies.

up
0 users have voted:

Paper Details

Authors:
Ang Li, Yang Wang
Submitted On:
23 September 2019 - 9:26pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Yiwei Lu
Document Year:
2019
Cite

Document Files

Semantic Segmentation in Compressed Videos .pdf

(31)

Subscribe

[1] Ang Li, Yang Wang, "Semantic Segmentation in Compressed Videos", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4825. Accessed: Nov. 15, 2019.
@article{4825-19,
url = {http://sigport.org/4825},
author = {Ang Li; Yang Wang },
publisher = {IEEE SigPort},
title = {Semantic Segmentation in Compressed Videos},
year = {2019} }
TY - EJOUR
T1 - Semantic Segmentation in Compressed Videos
AU - Ang Li; Yang Wang
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4825
ER -
Ang Li, Yang Wang. (2019). Semantic Segmentation in Compressed Videos. IEEE SigPort. http://sigport.org/4825
Ang Li, Yang Wang, 2019. Semantic Segmentation in Compressed Videos. Available at: http://sigport.org/4825.
Ang Li, Yang Wang. (2019). "Semantic Segmentation in Compressed Videos." Web.
1. Ang Li, Yang Wang. Semantic Segmentation in Compressed Videos [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4825