Object detection, tracking, and 6DoF Pose Estimation in web browser - Integrated Training Environment to train your own neural network models

Real-time virtual try-on engine built with React, Three.js, and Mediapipe — where digital fashion meets motion tracking.

Yolo pose estimation browser, power by onnxruntim web, support WebGPU wasm(cpu). Webcam support for live detection, Add your custom model

Yolo11 multi task browser, Object Detection, Pose Estimation, Instance Segmentation Power by onnx-web. support WebGPU wasm(cpu). Realtime process camera, Add your custom model

👁 零代码零标注 CV AI 自动化测试工具 🚀 免除大量人工画框和打标签等，直接零代码快速自动化测试 CV 计算机视觉 AI 人工智能图像识别算法：行人检测、动植物分类、人脸识别、OCR 车牌识别、旋转校正、舞蹈姿态、抠图分割 等，还可一键 下载测试报告、导出训练和测试数据集

This simple web-app written only on js uses mediapipe to detect human body pose in 3D

FitX is an advanced fitness tracking application built using React and TensorFlow.js for real-time pose estimation. The application helps users monitor their workouts, set fitness goals, and track progress with AI-powered assistance. It offers an interactive workout experience with guided commands and video instructions.

V-QUIP: A Vision-based Quick Impromptu Polling System for the Classroom

Real-Time Pose Estimation

Super simple app that estimates the angles in the shoulders based on YOLO pose estimation.

Control a synthesizer by tracking your hands

Quickly add Pose Estimation and Detection to your React Native app. Enable powerful features in your app powered by your user body tracking !.

Human Pose estimation with TensorFlow framework

ergoSmart is an AI-powered posture coach using React.js, TensorFlow.js, and MediaPipe Pose for real-time webcam-based posture analysis and personalized feedback.

A machine learning-based in-browser pose detection

Create experiential NFTs from your body movements

[JS/TensorFlow] JavaScript library that implements machine learning-based models for human pose estimation and human movement analysis. It allows you to easily implement three neural network models for human pose estimation: MoveNet, PoseNet, and BlazePose. No Node.js is required. TensorFlowJS was used, and an example app is included.

Playing and discovering computer vision with TensorFlow.js (old repo)

Codefest 2024 Submission: Virtual AI Gym Companion

Data labeling react app that is backend agnostic and can be embedded into your applications — distributed as an NPM package