mgb45/SignerBodyPose

Stars
2
Language
MATLAB
License
MIT License
Created over 10 years ago
Updated about 10 years ago

mgb45/SignerBodyPose

mgb45

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Upper body joint tracking for the RWTH-Phoenix signer database using a Mixture Kalman filter

ECE4076

Interactive class notebooks for ECE4076 Computer Vision.

Jupyter Notebook

MoGapFill

Low dimensional Kalman smoother that fills gaps in motion capture marker trajectories

ECE3091_resources

A selection of code resources for mobile robot navigation and control.

Jupyter Notebook

facetracking

Opencv face tracking in ROS (Haar wavelets + KF tracking)

OC-notebooks

A series of notebooks for model-based DRL or optimal control. Includes direct trajectory optimisation, CEM policy training and CEM planning.

Jupyter Notebook

action_permutations

Predicting action sequences with visual permutations

Jupyter Notebook

bayes_opt_navigation

Informative path planning for a mobile robot using optimal control and Bayesian optimisation

Jupyter Notebook

NVAE

MWE of Newtonian VAE

Jupyter Notebook

measurementproposals

Measurement proposals for upper body pose estimation

mkfbodytracker_pdaf

Fast upper body pose estimation

neural-data-association

Learning data association without data association (using smoothness assumptions in observations)

Jupyter Notebook

SDN_Pendulum

Switching density network pendulum example https://arxiv.org/abs/1907.04360

Jupyter Notebook

gmm_training

Mixture of random walk motion model training for upper body pose estimation

conf-scheduler

Automatic conference session assignment using latent topic model features

Jupyter Notebook

ilqr_pendulum

ILQR implementation (following Tassa et al - IROS 2012) for gym pendulum environment, using both known model and linear Gaussian dynamic model learning (Levine et al - JMLR 2016).

Jupyter Notebook