1 / 12

Towards Solving Real-World Vision Problems with RGB-D Cameras

CPVR 2013 Tutorial. Towards Solving Real-World Vision Problems with RGB-D Cameras. Kinect for Windows SDK+Toolkit Alisson Sol Microsoft. Before I Forget…. Lots of people helped to create the content for this presentation… Not only from K4W, but also DPE, Xbox, MSR, etc.

bryony
Télécharger la présentation

Towards Solving Real-World Vision Problems with RGB-D Cameras

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. CPVR 2013 Tutorial Towards Solving Real-World Vision Problems with RGB-D Cameras Kinect for Windows SDK+Toolkit Alisson SolMicrosoft

  2. Before I Forget… • Lots of people helped to create the content for this presentation… • Not only from K4W, but also DPE, Xbox, MSR, etc.

  3. Kinect for Windows releases • 1.0: Feb/01/2012 • 1.5: May/21/2012 • 1.6: Oct/04/2012 • 1.7: Mar/18/2013 • Future • 1.X investment • New sensor

  4. Environment Differences… Xbox Windows Intel, AMD, … USB 2.0+ Multiple devices 1 per USB controller Win32, x64 V1: no GPU requirement General audience Unbounded scenarios… • Known CPU: PPC • Known bus • 1 device per machine • Only 1 supported • Known architecture • Known GPU • Selected audience • Mainly games

  5. K4W SDK Block Diagram Managed Applications Runtime Toolkit Native Skeletal Tracking Drivers

  6. KINECT SENSOR IR Emitter Color Sensor IR Depth Sensor Tilt Motor Microphone Array

  7. Drivers

  8. Runtime • Sensor discovery, initialization and notification • Frame delivery supports event-based notification and polling models • Emphasis on low-latency, low per-frame allocations • Supports virtual sensors, including test tools and Kinect Studio

  9. Skeletal Tracking - Output KinectSensorkinect = null; voidStartKinectST() { kinect= KinectSensor.KinectSensors.FirstOrDefault(s => s.Status== KinectStatus.Connected); // Get first Kinect Sensor kinect.SkeletonStream.Enable(); // Enable skeletal tracking skeletonData = newSkeleton[kinect.SkeletonStream.FrameSkeletonArrayLength]; // Allocate ST data kinect.SkeletonFrameReady+= new EventHandler<SkeletonFrameReadyEventArgs>(kinect_SkeletonFrameReady); // Get Ready for Skeleton Ready Events kinect.Start(); // Start Kinect sensor } privatevoidkinect_SkeletonFrameReady(object sender, SkeletonFrameReadyEventArgs e) { using (SkeletonFrameskeletonFrame = e.OpenSkeletonFrame()) // Open the Skeleton frame { if (skeletonFrame != null && this.skeletonData != null) // check that a frame is available { skeletonFrame.CopySkeletonDataTo(this.skeletonData); // get the skeletal in this frame ... HANDLE SKELETAL DATA HERE ... } } }

  10. Questions? • K4W links • Download the SDK & Toolkithttp://go.Microsoft.com/fwlink/?LinkId=236070 • Software support forumshttp://go.Microsoft.com/fwlink/?LinkId=236056 • Sensor support and repairhttp://go.Microsoft.com/fwlink/?LinkId=236069 • Samples onlinehttp://kinectforwindows.codeplex.com/

More Related