This project develops a fall detection system using Pose Estimation and Optical Flow data with LSTM networks. It enhances detection accuracy for elderly care by analyzing body movements in real-time. Key technologies include the MoveNet model for pose estimation, Optical Flow analysis and LSTM networks for temporal analysis.

Tracking objects in 2D

Python interface of C3Dserver software for reading and editing C3D motion capture files

Analysis of the possibility of movement measurement on video recordings of the ICSI procedure using machine learning methods.

Realtime Human Motion Tracking and Analysis

Compute causal relationships between individual pixels in 2D videos over space and time to reveal salient dynamics using a variety of causal measures

In-depth motion analysis of mobile lung cancer tumors. Designed for 4D-CT scans of the thorax and provide valuable information for proton therapy treatment planning

Natural Coordinates with python for biomechanics

The source code and pre-trained models for Motion Matters: Neural Motion Transfer for Better Camera Physiological Sensing (WACV 2024, Oral).

General motion analysis. Used by GonioAnalysis.

A library for modelling racing subjects

This repository contains Python code used for the extraction and clustering of muscle and kinematic synergies from preprocessed EMG data, as described in the research paper . The data was initially imported from Vicon c3d files.

PyTorch implementation of our graph convolutional network (GCN) for human motion generation from music. Also with paired dance-music data for training!

Goniometric motion analysis software

Official implementation of AAAI 2023 Oral Paper "Frame-Level Label Refinement for Skeleton-Based Weakly-Supervised Action Recognition"

Wearable gait event detection device with real-time gait event-dependent feedback. Heel-strike events accuracy was validated with floor-embedded force plates.

Usage of direct linear transformation (camera calibration and point reconstruction) for accurate motion analysis in biomechanical applications.

Extract and visualize gait data

(CVPR 2023) MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds