Human action classification system with pose-based (MediaPipe) and video-based (3D CNN) models. Features 100+ architectures for real-time pose classification and temporal models pretrained on UCF-101/HMDB51. Applications include autonomous vehicles, video surveillance, and action recognition research.

AI-based pose tracking and repetitions counter to help everyone do the workout.

AI-powered padel analytics

NeurIPS 2024 | 🤸‍♂️💥🚗Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective

A Flutter Package to use Google Teachable Machine. To make a Pose classifier

Studies on Pose Estimation and Classification with PoseNet using ml5.js and p5.js libraries.

control go1 pro robot using hand/body poses

Pose Classification using OpenPose from OpenCV library.

Machine Learning Model for Oh Dance Applications.

Yoga Pose Detection using GANs and Real-Time Pose Estimation is a computer vision project that detects and classifies yoga poses from static images or webcam feeds. It uses GANs for data augmentation, keypoint detection models like OpenPose and PoseNet, and machine learning classifiers to evaluate pose accuracy and provide real-time feedback.

Build models to detect poses in FPS game

Specialization in Computer vision and Deep learning

Pose Estimation Using Mediapipe

This project is the Hand Gesture Slider web application. Control a beautiful, interactive slider with your hand gestures using your webcam!