Recurrent Fully Convolutional Networks for Video Segmentation
This work addresses the problem of video segmentation for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles video segmentation by proposing a recurrent fully convolutional network that incorporates temporal data for online processing, achieving a 5.5% improvement in F-measure over a plain fully convolutional network and a 1.4% improvement over a baseline FCN 12s on a change detection dataset.
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.