DeepAI AI Chat
Log In Sign Up

Semantic Segmentation of Video Sequences with Convolutional LSTMs

05/03/2019
by   Andreas Pfeuffer, et al.
0

Most of the semantic segmentation approaches have been developed for single image segmentation, and hence, video sequences are currently segmented by processing each frame of the video sequence separately. The disadvantage of this is that temporal image information is not considered, which improves the performance of the segmentation approach. One possibility to include temporal information is to use recurrent neural networks. However, there are only a few approaches using recurrent networks for video segmentation so far. These approaches extend the encoder-decoder network architecture of well-known segmentation approaches and place convolutional LSTM layers between encoder and decoder. However, in this paper it is shown that this position is not optimal, and that other positions in the network exhibit better performance. Nowadays, state-of-the-art segmentation approaches rarely use the classical encoder-decoder structure, but use multi-branch architectures. These architectures are more complex, and hence, it is more difficult to place the recurrent units at a proper position. In this work, the multi-branch architectures are extended by convolutional LSTM layers at different positions and evaluated on two different datasets in order to find the best one. It turned out that the proposed approach outperforms the pure CNN-based approach for up to 1.6 percent.

READ FULL TEXT

page 1

page 6

07/16/2019

Separable Convolutional LSTMs for Faster Video Segmentation

Semantic Segmentation is an important module for autonomous robots such ...
01/08/2019

Multi-stream CNN based Video Semantic Segmentation for Automated Driving

Majority of semantic segmentation algorithms operate on a single frame e...
11/29/2020

UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by Embedding Temporal Information

Semantic segmentation of aerial videos has been extensively used for dec...
05/22/2017

TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation

Action segmentation as a milestone towards building automatic systems to...
07/01/2020

Robust Semantic Segmentation in Adverse Weather Conditions by means of Fast Video-Sequence Segmentation

Computer vision tasks such as semantic segmentation perform very well in...
11/27/2018

Beyond One Glance: Gated Recurrent Architecture for Hand Segmentation

As mixed reality is gaining increased momentum, the development of effec...