3DiVi/nuitrack-sdk

Nuitrack™ is a 3D tracking middleware developed by 3DiVi Inc.

What it solves

Nuitrack SDK provides a unified 3D body and skeletal tracking library that works across a wide variety of depth sensors, hardware platforms, and operating systems. It eliminates the need to develop separate tracking logic for different sensors (like Kinect, Intel Realsense, or Orbbec), acting as a "Kinect for everything."

How it works

The SDK processes data from 3D/depth sensors to provide human-centric spatial understanding. It offers two skeletal tracking engines: a "classical" engine for speed and stability on embedded hardware, and an AI-based deep-learning engine for better coverage of complex poses.

Who it’s for

Developers creating immersive or analytical applications, including those in gaming, medical rehabilitation, smart home technology, natural user interfaces (NUI), AR/VR full-body tracking, audience analytics, and robot vision.

Highlights

  • Broad Sensor Support: Compatible with sensors from Orbbec, Microsoft Kinect (v1/v2/Azure), Intel Realsense, Asus Xtion, and others.
  • Multi-platform Support: Works on Windows, Linux, Android, and iOS across x64, x86, ARMv7, and ARMv8 architectures.
  • Comprehensive Tracking: Includes 3D skeletal tracking, pixel-perfect person segmentation, floor plane detection, basic facial analysis (age/emotion), and hand/gesture recognition.
  • Extensive Integration: Provides APIs for C++, C#, and Python, and native support for Unity, Unreal Engine 5, and TouchDesigner.

Related

  • Project
    stereolabs/zed-sdk

    A cross-platform spatial perception SDK for ZED cameras that provides real-time depth sensing, object detection, and positional tracking.

  • 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.

  • Project
    InsightSoftwareConsortium/ITK

    An open-source, cross-platform toolkit for N-dimensional scientific image processing, segmentation, and registration, primarily used for medical image analysis.

  • Project
    Faceplugin-ltd/Open-Source-Face-Recognition-SDK

    An open-source face recognition SDK for Windows and Linux that provides on-premise deep learning-based face detection and identity verification.

  • Project
    nutonomy/nuscenes-devkit

    A software development kit for the nuScenes and nuImages datasets, providing tools to load, analyze, and evaluate multimodal sensor data for autonomous driving research.