Convolutional Gated Recurrent Networks for Video Segmentation

TL;DR

This paper introduces a convolutional gated recurrent network architecture that leverages temporal information in videos to enhance semantic segmentation accuracy in online and batch settings, showing consistent improvements across multiple benchmarks.

Contribution

The novel convolutional gated recurrent network architecture effectively incorporates temporal video data into segmentation, improving performance over baseline models.

Findings

Improved F-measure by 5% on SegTrack V2

Enhanced mean IoU by 5.7% on Synthia

Achieved 3.5% higher categorical mean IoU on CityScapes

Abstract

Semantic segmentation has recently witnessed major progress, where fully convolutional neural networks have shown to perform well. However, most of the previous work focused on improving single image segmentation. To our knowledge, no prior work has made use of temporal video information in a recurrent network. In this paper, we introduce a novel approach to implicitly utilize temporal data in videos for online semantic segmentation. The method relies on a fully convolutional network that is embedded into a gated recurrent architecture. 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. Our proposed method can be applied in both online and batch segmentation. This architecture is tested for both binary and semantic video segmentation tasks. Experiments are conducted on the recent benchmarks in SegTrack V2, Davis, CityScapes, 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% improvement in mean IoU in Synthia and 3.5% improvement in categorical mean IoU in CityScapes. The performance of the RFCN network depends on its baseline fully convolutional network. Thus RFCN architecture can be seen as a method to improve its baseline segmentation network by exploiting spatiotemporal information in videos.