Temporal Autoencoder with U-Net Style Skip-Connections for Frame Prediction
arXiv:2011.12661
Abstract
Finding sustainable and novel solutions to predict city-wide mobility behaviour is an ever-growing problem given increased urban complexity and growing populations. This paper seeks to address this by describing a traffic frame prediction approach that uses Convolutional LSTMs to create a Temporal Autoencoder with U-Net style skip-connections that marry together recurrent and traditional computer vision techniques to capture spatio-temporal dependencies at different scales without losing topological details of a given city. Utilisation of Cyclical Learning Rates is also presented, improving training efficiency by achieving lower loss scores in fewer epochs than standard approaches.
arXiv comment7 pages, 3 figures, 3 tables, 4 equations
References in corpus (7)
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- An overview of gradient descent optimization algorithms
- CrevNet: Conditionally Reversible Video Prediction
- Traffic4cast-Traffic Map Movie Forecasting -- Team MIE-Lab
- Traffic map prediction using UNet based deep convolutional neural network
- Spatiotemporal Tile-based Attention-guided LSTMs for Traffic Video Prediction
- Building Effective Large-Scale Traffic State Prediction System: Traffic4cast Challenge Solution