STFCN: Spatio-Temporal FCN for Semantic Video Segmentation

TL;DR

This paper introduces a spatio-temporal fully convolutional network (STFCN) that combines CNNs and LSTM to improve semantic video segmentation by capturing both spatial and temporal features in an end-to-end architecture.

Contribution

The paper proposes a novel end-to-end spatio-temporal CNN architecture integrating LSTM for temporal features, enhancing semantic video segmentation performance.

Findings

Achieved state-of-the-art results on Camvid dataset.

Demonstrated effectiveness of combining CNN and LSTM for video segmentation.

Extended existing CNN architectures with spatio-temporal modules.

Abstract

This paper presents a novel method to involve both spatial and temporal features for semantic video segmentation. Current work on convolutional neural networks(CNNs) has shown that CNNs provide advanced spatial features supporting a very good performance of solutions for both image and video analysis, especially for the semantic segmentation task. We investigate how involving temporal features also has a good effect on segmenting video data. We propose a module based on a long short-term memory (LSTM) architecture of a recurrent neural network for interpreting the temporal characteristics of video frames over time. Our system takes as input frames of a video and produces a correspondingly-sized output; for segmenting the video our method combines the use of three components: First, the regional spatial features of frames are extracted using a CNN; then, using LSTM the temporal features are added; finally, by deconvolving the spatio-temporal features we produce pixel-wise predictions. Our key insight is to build spatio-temporal convolutional networks (spatio-temporal CNNs) that have an end-to-end architecture for semantic video segmentation. We adapted fully some known convolutional network architectures (such as FCN-AlexNet and FCN-VGG16), and dilated convolution into our spatio-temporal CNNs. Our spatio-temporal CNNs achieve state-of-the-art semantic segmentation, as demonstrated for the Camvid and NYUDv2 datasets.