Analyze your gait for health disorders at the comfort of your home in your own personal computer.
Gait abnormalities can be attributed to various musculoskeletal and neurological conditions and so gait analysis is being used as an important diagnostic tool by doctors.
Automated gait analysis requires expensive motion capture or multiple-camera systems. But with Gait Analyzer one can analyze their gait in comfort and privacy of their home on their computer.
Gait Analyzer implements the algorithm published in the paper titled Automated Gait Analysis Based on a Marker-Free Pose Estimation Model.
This algorithm for gait analysis is shown to be as reliable as a motion capture system for most scenarios.
Gait Analyzer further uses Llama2 large language model to interpret the gait data to the end user in simple terms.
Clicking the above image will open the video on YouTube.
- Do gait analysis on videos locally on your computer.
- Annotated video with pose-estimation.
- Distances, Peaks and Minima plotted for each leg.
- Displaying Gait data.
- Download of gait data as .csv file.
- Gait pattern explanation using Large Language Model.
Use Gait Analyzer to analyze your gait on your computer using Docker.
Run the LLM model on CPU
mkdir gaitanalyzer && cd gaitanalyzer
sh -c "$(curl -fsSL https://raw.githubusercontent.com/abishekmuthian/gaitanalyzer/main/install.sh)"Run the LLM model on GPU
Note: Requires Nvidia drivers and Container Toolkit to be installed.
mkdir gaitanalyzer && cd gaitanalyzer
sh -c "$(curl -fsSL https://raw.githubusercontent.com/abishekmuthian/gaitanalyzer/main/install-gpu.sh)"Copyright (C) 2023 Abishek Muthian (Gait Analyzer)
This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License along with this program. If not, see https://www.gnu.org/licenses/.