Bio-LSTM: A Biomechanically Inspired Recurrent Neural Network for 3-D Pedestrian Pose and Gait Prediction.
Xiaoxiao DuRam VasudevanMatthew Johnson-RobersonPublished in: IEEE Robotics Autom. Lett. (2019)
Keyphrases
- recurrent neural networks
- long short term memory
- chaotic time series
- neural network
- feed forward
- prediction accuracy
- echo state networks
- complex valued
- recurrent networks
- artificial neural networks
- hidden layer
- pose estimation
- neural model
- gait recognition
- prediction model
- gait analysis
- pedestrian detection
- feedforward neural networks
- human identification
- reservoir computing
- d objects
- position and orientation
- object detection
- nonlinear dynamic systems
- joint angles
- action recognition