Detects the sitting position of a person

Posture recognition based on common camera

Real-time lateral sitting posture detection to predict good and bad postures using YOLOv5

We got your back!

Open closed eyes classification. Ultra-fast wink and blink estimation model.

Realtime detection of incorrect sitting posture

Visual only speech detection by lip movement. There are countless situations where you can't hear the audio, and it's really frustrating.

Detects your posture in 3D space, and delivers you a warning when you slouch!

The repository for the source code of the Motus system

Ultrafast sitting classification. 32x24 pixels is sufficient for estimating the state of the whole human body.

Postrue is a Python-based application that empowers users to enhance their posture in real-time by detecting and correcting incorrect postures using Mediapipe and OpenCV libraries.

Hackathon Implementation for Gymansts to become more perfect.

ESC102 Praxis II Design Project

Machine learning fall detection and posture detection

Waving Hand Classification. Ultrafast 1x3x4x32x32 3DConv gesture estimation.

Happy smile classifier. The estimation is done on the entire head, 48x48 pixels, rather than the face.

This project includes multiple models, loss functions, optimizers and image augmentations for image classification task

Real-time posture detector.

Phone Usage Classifier (PUC) is a three-class image classification pipeline for understanding how people interact with smartphones.

Pointing gesture classification. Classify whether the finger is pointing near the center of the camera lens. A resolution of 32x32 is sufficient for human hand gesture classification.