3D Object Tracking for Augmented Reality: Handling Multiple Objects, Motion-Blur, & Lack of Texture

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=eqlEzWmuijs


Duration: 1:25:01
3,131 views
15

Augmented Reality (AR) is implemented by superimposing virtual entities on the real scene so that they appear registered with the related real entities. For the registration to be reliable, qualified object tracking technologies are necessary. In this talk, we address the problems of 3D object tracking in implementing practical AR systems: handling multiple 3D objects, motion blur, and texture-less objects. Presenting the solutions for these problems, we focus on reducing the tracking dependency on the complex texture. Finally, in the texture-less object tracking, we show how to exploit the depth information obtained in real-time using Microsoft Kinect.



Other Videos By Microsoft Research


2016-07-27Analyzing Investments in Innovation: Private and Public Perspectives
2016-07-27Managing data in your app
2016-07-27A system for programming and verifying interacting state machines
2016-07-27Inference and Learning in Structured-Output Models for Computer Vision
2016-07-27Accelerating Dynamic Software Analyses
2016-07-27SocialTFS: Augmenting Social Awareness in a Collaborative Development Environment
2016-07-27Coding for a Network Coded Fountain
2016-07-27Experiences and Progresses on Binary Translation system for Loongson Processor
2016-07-27Optimization Problems in Network Connectivity
2016-07-27Gaussian Processes for Inference with Implicit Likelihoods
2016-07-273D Object Tracking for Augmented Reality: Handling Multiple Objects, Motion-Blur, & Lack of Texture
2016-07-27Robust Shallow Semantic Parsing of Text
2016-07-27Enabling Trustworthy Users
2016-07-27Video-based In Situ Tagging for Mobile Augmented Reality
2016-07-27Metric Learning and Manifolds: Preserving the Intrinsic Geometry
2016-07-27Making money with �free� apps
2016-07-27Collecting a Heap of Shapes
2016-07-27Automatically Assessing Personality from Speech
2016-07-27Ten User Experience Best Practices for Windows Phone Application Development
2016-07-27Generalization Bounds and Consistency for Latent-Structural Probit and Ramp Loss
2016-07-27Structured Prediction in NLP: Dual Decomposition and Structured Sparsity


Tags:
microsoft research