Skip to main content
💡 TL;DR

Microsoft has killed the Azure Kinect sensor, leaving many companies with no viable alternatives. If you’re one of those affected by Microsoft’s decision, don’t worry. The LightBuzz Body Tracking SDK is a powerful tool suitable for both desktop and mobile app development. In this guide, we’ll explore the benefits of using LightBuzz and provide examples for migrating your existing Kinect apps.

😵 It’s official: Azure Kinect is dead

In a recent and unexpected move, Microsoft announced the discontinuation of its popular Azure Kinect sensor, sending ripples throughout the tech and development community. Azure Kinect has been the backbone for many applications, particularly those requiring depth sensing and human skeletal tracking capabilities. With this announcement, numerous businesses and developers were left in the lurch, searching for alternatives to keep their applications functional.

For developers who have been coding for the past decade, this may feel like déjà vu. Microsoft stopped making the Kinect for Windows in 2015 and the Kinect for Xbox One in 2017. Now, it’s the Azure Kinect’s turn to be discontinued in 2023. As Brian Heater of TechCrunch put it, “Microsoft can’t stop discontinuing Kinect.” To be fair, this time, Microsoft partnered with companies such as Orbbec and Analog, providing them with technology to develop newer depth cameras. Even though that would help the hardware side, there’s nothing related to the Body Tracking software developers love so much.

Azure Kinect dead (illustration)

🚀 LightBuzz to the rescue

But every cloud has a silver lining. LightBuzz, a frontrunner in advanced AI-powered solutions, has swiftly emerged as the go-to alternative, offering a superior skeleton-tracking solution that’s not just restricted to a particular camera type or operating system.

In this guide, we’ll explore the benefits of using a fast, accurate, cross-platform body tracking solution. We’ll also show you how to migrate your existing projects from Kinect to other depth cameras and mobile platforms.

Vangos Pterneas - Author of the Azure Kinect Book

LightBuzz is not just a Kinect replacement. It's an upgrade.

Vangos PterneasAuthor of "Mastering the Kinect"

LightBuzz Body Tracking

LightBuzz has created the world’s most accurate body-tracking software solution. Companies and universities worldwide use our SDK to develop commercial apps for desktop and mobile devices.

🖥️ Desktop & 📱 Mobile compatibility

Kinect’s main drawback was its confinement to the Windows and Linux ecosystems. In today’s digital age, diversity in platform support isn’t just an advantage; it’s a necessity. Right out of the box, LightBuzz supports the iOS, Android, macOS, Windows, and Ubuntu Linux operating systems. Why’s that important?

  • A World Beyond Desktop: With the mobile revolution at its peak, not providing support for iOS and Android is akin to missing out on a vast ocean of potential users. LightBuzz SDK’s compatibility with these platforms means that developers can design applications for the largest user bases in the tech world.
  • Unified AI Power: One of the most compelling aspects of the LightBuzz SDK is that it doesn’t compromise on AI capabilities, irrespective of the platform it’s on. Whether you’re developing for a high-end PC, a MacBook, an Android tablet, or an iPhone, you can rest assured that the AI performance remains consistent. This consistency guarantees that users get the same high-quality experience no matter their device of choice.
  • Streamlined Development: Developers often grapple with the challenge of creating separate versions of an application for different operating systems. With LightBuzz SDK’s comprehensive OS support, the development process becomes more streamlined. A more unified codebase means fewer bugs, quicker updates, and a more efficient development cycle.
  • Future-Proofing Applications: With technology’s rapid evolution, there’s no telling which platforms will rise in prominence in the future. By offering support for all major operating systems, LightBuzz SDK ensures that applications remain relevant and adaptable to whatever the future holds.
💡 KEY POINT

LightBuzz supports iOS, Android, Windows, macOS, and Linux.

🎥 A vast family of RGB & Depth cameras

Kinect was a trailblazer, but it did come with limitations, one of which was its strict hardware allegiance. The Microsoft BT SDK was crafted explicitly for the Kinect sensor, limiting its application. On the other hand, LightBuzz SDK stands out due to its versatility in hardware compatibility. First, LightBuzz can generate 3D skeleton data from any 2D RGB camera. However, if you rely on depth perception, the LightBuzz SDK supports over twenty commercial models from numerous manufacturers under a unified programming interface! That’s peace of mind!

Apple

iPhone LiDAR, iPad LiDAR, FaceTime

Intel RealSense

D457, D455, D455f, D435, D435i, D435f, D415, L515, D405

Orbbec icon (light)
Orbbec

Femto, Femto W, Femto Mega, Astra+

Luxonis icon (light)
Luxonis

OAK-D, OAK-D Pro, OAK-D Pro W, OAK-D Lite, OAK-D W, OAK-D S2

Structure icon (light)
Structure

Structure Core

Here’s why this adaptability is game-changing:

  • Adaptable Integration: With its support for a diverse range of cameras, LightBuzz SDK allows businesses and developers to integrate gesture and movement-based features without being tied down to a specific hardware brand. Whether it’s Intel RealSense’s depth-perceiving capabilities or Apple LiDAR’s high-resolution depth framework, LightBuzz is ready to harness these technologies.
  • Future Hardware Innovations: The tech landscape is continuously evolving, with new sensors and cameras constantly being developed. LightBuzz SDK’s flexible nature ensures that, as new camera technologies emerge, developers won’t need to switch SDKs or undergo extensive modifications to accommodate them.
  • Cost-Efficiency: By supporting a wide array of cameras, including basic RGB webcams, LightBuzz SDK ensures that businesses don’t always need high-end, expensive hardware to integrate advanced gesture recognition. This makes it possible for smaller businesses or developers on a budget to produce high-quality applications without significant hardware investments.
  • Transforming 2D to 3D: Perhaps one of the most remarkable features of the LightBuzz SDK is its ability to extract 3D joint coordinates from a mere 2D input. This capability amplifies the potential applications of gesture-based tech, making it accessible to developers even without advanced 3D sensors.
💡 KEY POINT

LightBuzz supports Apple LiDAR, Intel RealSense, Luxonis OAK-D, Orbbec series, Structure Core, and RGB cameras.

💪 Unparalleled accuracy

Accuracy is at the heart of gesture and movement recognition. While Kinect certainly brought a degree of precision to the table, it was at the expense of a hefty AI model, narrowing its usability to only top-tier hardware. LightBuzz SDK, with its balanced blend of accuracy and efficiency, has filled this gap brilliantly. Here’s what makes it stand out:

  • Resilient Accuracy: When it comes to tracking human movements, variability is the name of the game. People strike a myriad of poses, often in rapid succession and from various angles. LightBuzz AI maintains its accuracy even under challenging conditions. Whether it’s a yoga pose or a dance move, the AI consistently delivers precise results.
  • Mobile Optimization: In a mobile-first world, the capability to run efficiently on smartphones isn’t just a luxury – it’s essential. LightBuzz ensures that mobile apps provide a seamless and responsive user experience, fostering increased user engagement and satisfaction.
  • Efficient Performance: LightBuzz SDK showcases a prime example of optimized AI design. By achieving higher accuracy with a smaller AI model size, it ensures that applications run smoothly without bogging down the system. This efficiency makes it possible for developers to integrate gesture recognition into a broader range of applications, from high-end gaming rigs to everyday utility apps on mobile phones.
  • Broadened User Base: One of the most significant advantages of LightBuzz SDK’s compatibility with older hardware is the vast expansion of potential users. This democratization means even those with legacy systems can benefit from advanced gesture recognition, opening up new markets and opportunities for developers.
LightBuzz Body Tracking - Fitness Stretch
💡 KEY POINT

LightBuzz provides a higher level of tracking accuracy while keeping hardware specs down.

⚡️ Speed & performance: a notch above the rest

While Kinect is limited to 30 FPS, the LightBuzz SDK has dramatically elevated the stakes.

  • Seamless Real-Time Analysis: At 60 FPS on an iPhone 14 and 90 FPS on an M1 Mac Mini, LightBuzz SDK doesn’t just provide real-time analysis – it’s practically instantaneous. This immediate feedback is crucial for applications that require split-second response times or depend on continuous motion tracking.
  • High-Speed Sports Analytics: Sports like golf and baseball are characterized by rapid, high-intensity movements. For trainers, athletes, and enthusiasts seeking to analyze a golf swing or a baseball pitch, a frame difference can mean missing out on crucial data. LightBuzz SDK’s high frame rate ensures that every intricate movement detail is captured, making analysis more comprehensive and insights more actionable.
  • Enhanced User Experience: A higher frame rate means smoother animations and more responsive feedback, translating to a more immersive user experience. Whether it’s for gaming, fitness applications, or interactive AR and VR environments, the fluidity provided by LightBuzz SDK enhances user engagement and satisfaction.
  • Adaptable Performance: Whether it’s the portability of an Android phone or the powerhouse performance of an M2 Mac, LightBuzz scales beautifully, delivering top-notch performance tailored to the device’s capabilities.
  • Future-Proofing: As technology continues to advance, user expectations rise in tandem. Systems that can’t keep up with demands for speed and responsiveness will quickly become obsolete. By providing FPS rates that exceed today’s standard, LightBuzz SDK is positioned not just for current needs but is also primed for future demands.
LightBuzz Body Tracking 360 degree view
💡 KEY POINT

LightBuzz provides the best performance and accuracy, with 60 FPS real-time on an iPhone and 90 FPS real-time on a Mac.

Try now for free

Don’t just take our word for it. Contact us now to try the LightBuzz Body Tracking SDK for free. Our support team is here to help with your smooth transition.

⏩ Smooth migration (with examples!)

With the LightBuzz SDK, the workflow is streamlined. It’s all about four key steps:

1

Start camera →
2

Acquire frames →
3

Capture data

Here are some common examples of working with frame data.

1) Start a camera

To start a camera, all you need to do is specify the sensor type of your choice. It could be a webcam, a RealSense, etc.

Sensor sensor = Sensor.Create(SensorType.Webcam); // RealSense, LiDAR, etc.
sensor.Open();

2) Acquire frames

Capturing frame data is straightforward: subscribe to the FrameDataArrived event and access Skeleton, Color, Depth, and IMU information.

sensor.FrameDataArrived += (sender, frame) =>
{
    DateTime timestamp = frame.Timestamp;
    int width = frame.Width;
    int height = frame.Height;
    var colorData = frame.ColorData;
    var depth = frame.DepthData;
    var imu = frame.IMUData;
    var bodies = frame.BodyData;
};

3) Capture skeleton joint data

When it comes to accessing the body skeleton data, all you need to do is specify the joints of your choice and retrieve their 2D and 3D positions.

foreach (Body body in bodies)
{
    Joint neck = body.Joints[JointType.Neck];
    TrackingState = neck.TrackingState;
    
    Vector2 position2D = neck.Position2D; // Screen
    Vector3 position3D = neck.Position3D; // World
    Quaternion orientation = neck.Orientation;
}

When it comes to transforming from one coordinate system to another, the LightBuzz API is a breeze.

// Map from screen to world space:
Vector2 point2D = /* a screen-space point */;
Vector3 point3D = frame.Map3D(point2D); // World
// Map from world to screen space:
Vector3 point3D = /* a world-space point */;
Vector2 point2D = frame.Map2D(point3D); // Screen

🚀 Conclusion

See how simple it is? For those looking to streamline their motion-sensing applications and projects, transitioning from the Azure Kinect SDK to the LightBuzz SDK provides a clearer, more straightforward, and efficient programming experience. Embrace the ease and intuitiveness of LightBuzz for your next project.

Try now for free

Don’t just take our word for it. Contact us now to try the LightBuzz Body Tracking SDK for free. Our support team is here to help with your smooth transition.

Vangos Pterneas

Vangos Pterneas is a software engineer, book author, and award-winning Microsoft Most Valuable Professional (2014-2019). Since 2012, Vangos has been helping Fortune-500 companies and ambitious startups create demanding motion-tracking applications. He's obsessed with analyzing and modeling every aspect of human motion using AI and Maths. Vangos shares his passion by regularly publishing articles and open-source projects to help and inspire fellow developers.

4 Comments

  • Horacio SRUR says:

    Subject: Inquiry Regarding Development of HD Projection Device for Moving Human Body

    Dear Vangos,

    I am writing to inquire about the feasibility of developing a high-definition device for virtual and augmented reality projection or any other method, capable of projecting onto the moving human body without distorting the image.

    Specific Requirements:

    Resolution: The projected image must have high definition (HD) for an immersive and realistic experience.
    Virtual and Augmented Reality or any other alternative…The device should be able to overlay virtual elements on the real world or create a complete virtual environment.
    Projection on Moving Body: The image should be projected onto the moving human body without distortions or interruptions.
    Portable Device: The device should be lightweight and compact for use on the head or other parts of the body.
    Additional Considerations:

    The device should be compatible with existing VR and AR technologies or any others.
    The solution should be scalable to accommodate different needs and budgets.
    We are seeking an innovative and cutting-edge solution that represents a significant advancement in projection technology.
    Will be anxiously awaiting for your kind response, while thanking you in advance.
    Horacio SRUR
    +54911 6792 4888
    +1 561 290 5768

    • Hi Horacio! Thanks for your message. LightBuzz is a software provider — we don’t develop hardware devices. If you need help with a software project, we’d be happy to learn more. You can use the contact page to reach out to us.

  • Great article! What about the Cube-eye depth sensor? They are S. Korea based and have decent tracking capabilities:

    https://medium.com/@futuroinfoindia/3d-tof-depth-camera-product-cube-eye-12693709b29d

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.