Recurrent Fully Convolutional Networks for Video Segmentation

TL;DR

This paper introduces a recurrent fully convolutional network with a novel convolutional gated recurrent unit for online video segmentation, demonstrating improved accuracy over non-recurrent methods.

Contribution

It presents a new recurrent architecture for video segmentation that preserves spatial information and operates online, unlike previous batch-based methods.

Findings

5.5% improvement in F-measure over plain FCN

1.4% F-measure improvement over baseline FCN 12s

Effective online segmentation with reduced parameters

Abstract

Image segmentation is an important step in most visual tasks. While convolutional neural networks have shown to perform well on single image segmentation, to our knowledge, no study has been been done on leveraging recurrent gated architectures for video segmentation. Accordingly, we propose a novel method for online segmentation of video sequences that incorporates temporal data. The network is built from fully convolutional element and recurrent unit that works on a sliding window over the temporal data. We also introduce a novel convolutional gated recurrent unit that preserves the spatial information and reduces the parameters learned. Our method has the advantage that it can work in an online fashion instead of operating over the whole input batch of video frames. The network is tested on the change detection dataset, and proved to have 5.5\% improvement in F-measure over a plain fully convolutional network for per frame segmentation. It was also shown to have improvement of 1.4\% for the F-measure compared to our baseline network that we call FCN 12s.