quickpose/quickpose-ios-sdk

Quickly add MediaPipe Pose Estimation and Detection to your iOS app. Enable powerful features in your app powered by the body or hand.

What it solves

QuickPose is an iOS SDK that simplifies the integration of complex pose estimation and skeleton tracking into mobile applications. It removes the need for developers to build these ML models from scratch, providing production-ready code for fitness tracking, health monitoring, and gesture recognition.

How it works

The SDK processes video frames from the device camera in real-time. It leverages MediaPipe and BlazePose to analyze the user's body position and then returns results that can be used to overlay markings on the image or trigger application logic based on the detected pose.

Who it’s for

iOS developers building health, fitness, or physical therapy apps that require real-time body tracking and exercise counting.

Highlights

  • Exercise Detection & Counting: Built-in support for a wide range of exercises including squats, push-ups, planks, and bicep curls.
  • Range of Motion (ROM) Analysis: Specialized tools for measuring the flexibility and movement range of joints like shoulders, hips, and knees.
  • Visual Overlays: Pre-built overlays for the whole body, upper body, lower body, and specific limbs.
  • Gesture Recognition: Detection of raised fingers and thumbs-up/down gestures.
  • Distance Independent Measuring: Ability to measure relative to body height or in centimeters using body height as input.
  • Flexible Integration: Compatible with Swift Package Manager and CocoaPods, with utility classes for both SwiftUI and UIKit.

Related

  • Project
    yo-WASSUP/Good-GYM

    An AI fitness assistant that uses RTMPose for real-time pose detection and automatic exercise repetition counting via a webcam.

  • Project
    ultralytics/yolo-ios-app

    A Swift-based SDK and demo app that brings real-time YOLO object detection and vision tasks to iOS devices using Core ML.

  • Project
    allenv0/AirPosture

    An iOS app that uses AirPods' head tracking and local AI to provide real-time posture coaching and nudges to reduce neck strain.

  • Project
    3DiVi/nuitrack-sdk

    A 3D body and skeletal tracking library that provides a unified API for various depth sensors across multiple platforms, enabling human-centric spatial understanding.

  • Project
    realsenseai/librealsense

    A cross-platform SDK for RealSense depth cameras that enables depth and color streaming and provides calibration data for computer vision and robotics.