Future Semantic Segmentation with Convolutional LSTM
This work addresses real-time decision-making needs in applications like autonomous driving by improving future semantic segmentation prediction.
The paper tackles the problem of predicting semantic segmentation maps for future video frames using observed frames, proposing a model with convolutional LSTM (ConvLSTM) and bidirectional ConvLSTM to encode spatiotemporal information, which outperforms state-of-the-art methods on a benchmark dataset.
We consider the problem of predicting semantic segmentation of future frames in a video. Given several observed frames in a video, our goal is to predict the semantic segmentation map of future frames that are not yet observed. A reliable solution to this problem is useful in many applications that require real-time decision making, such as autonomous driving. We propose a novel model that uses convolutional LSTM (ConvLSTM) to encode the spatiotemporal information of observed frames for future prediction. We also extend our model to use bidirectional ConvLSTM to capture temporal information in both directions. Our proposed approach outperforms other state-of-the-art methods on the benchmark dataset.