====================
This script will help you to run LiteFlowNet for video instead of images. The code is for just research purposes. To run this code first compile LiteFlowNet: https://github.com/twhui/LiteFlowNet Then you need to use the modified deploy.prototxt
Ullah, A., Muhammad, K., Baik, S. W. (2018). Activity Recognition using Temporal Optical Flow Convolutional Features and Multi-Layer LSTM. IEEE Transactions on Industrial Electronics.
Ullah, A., Ahmad, J., Muhammad, K., Sajjad, M., & Baik, S. W. (2018). Action Recognition in Video Sequences using Deep Bi- Directional LSTM With CNN Features. IEEE Access, 6, 1155-1166.
Amin Ullah, Khan Muhammad, Ijaz Ul Haq, and Sung Wook Baik, Action Recognition using Optimized Deep Autoencoder and CNN for Surveillance Data Streams of Non-Stationary Environments, Future Generation Computer Systems, 2018