1.Vision: Extraordinary Computing Experiences & 2. Robots for the Masses: Fiction or Reality

Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=S8XyFzS70rc



Duration: 1:20:39
37 views
0


Part I: Vision:  Extraordinary Computing Experiences Imagine walking into a room with your camera phone, seeing a book you like, and in one snap of the camera the book is yours.  This and many other applications are closer to reality today than ever before thanks to advancements in mobile computing, wireless technologies, and computer vision.  In this talk, I will discuss computer vision technologies that enable such extraordinary computing experiences and the tremendous business potential that this introduces.  I will describe ViPR™ an algorithm for Visual Pattern Recognition which provides a robust solution to several fundamental and longstanding computer vision problems including the correspondence problem and reliable object recognition.  I will give examples of how this technology can be used for a wide variety of applications for shopping, working, and playing.  For shopping, I will describe LaneHawk™, a retail loss-prevention solution consisting of a camera mounted on the side of the checkout aisle to monitor the bottom of the shopping cart items that the cashier may have forgotten to ring up.  For camera phone applications I will give examples of how the camera could become a one-snap interface to connecting the real world to the world-wide-web. Finally, I will discuss how ViPR could support a visual interface for Xbox and Sony AIBO® for game-play and entertainment. These examples represent the tip of the iceberg for what we believe is possible with these new generation vision technologies and the potential business opportunities that they create.  Part II:  Robots for the Masses:  Fiction or Reality Over the recent years we have witnessed a growing number of robotic technologies make their way into the consumer market. These interactive, talking and walking toys and autonomous vacuum cleaners may not be viewed as robots but they bring robotics to the mass consumer market in subtle ways. Do these robotic products represent the early stages of an emerging consumer robotics industry that may grow as large as the PC industry? It can be argued that the growth of the robotics industry can be accelerated by a set of common, core technology components including navigation, human-robot interaction, and system architecture. I will describe how we have used vision for developing a cost-effective visual simultaneous localization and mapping technology called vSLAM™ for short.  vSLAM enables an autonomous robot to build a visual map of the environment consisting of a database of 'locations' that it can recognize later to estimate its position. I will describe NorthStar™ , an optical sensing technology for indoor localization that introduces a breakthrough in price-performance for autonomous navigation.  Finally, I will describe the Evolution Robotics Software Platform, ERSP™, a standard software platform for application development. These core technologies are key building blocks for developing powerful robot applications at the right price point for the consumer market.




Other Videos By Microsoft Research


2016-09-05Resource acquisition via an unsupervised WSD system
2016-09-05Fast Infinite-State Model Checking in Integer-Based Systems
2016-09-05WeΓÇÖre Friends, Right?: Inside KidsΓÇÖ Culture [1/4]
2016-09-05Accelerated Democracy: How technology might change voting
2016-09-05When Can Formal Methods Make a Real Difference?
2016-09-05Dynamic Semantics of Programming Languages and Applications to Testing
2016-09-05Error Detection using Shape Analysis with Local Reasoning
2016-09-05Type-Safe, Generative, Binding Macros
2016-09-05Social Network Analysis meets the Semantic Web: What FOAF Reveals About LiveJournal
2016-09-05Distributed Multi-robot Exploration and Mapping
2016-09-051.Vision: Extraordinary Computing Experiences & 2. Robots for the Masses: Fiction or Reality
2016-09-05Modeling and Facilitating Human Communication [1/5]
2016-09-05Reducing Errors in Computer Recognition of Handwritten Material
2016-09-05Information wants to be free (but is everywhere in chains)
2016-09-05The art and technology of electronic textiles
2016-09-05Quantum Loop Gas Approach to Topological Phases of Correlated Electrons
2016-09-05Computational History In Action: Discovering Gutenberg's Printing Process
2016-09-05A World Filled With Cameras: Security at the Cost of Freedom? Or Can We Have Both?
2016-09-05Resisting Denial of Service Attacks by Puzzle Outsourcing
2016-09-05Transition Invariants
2016-09-05Declarative querying of sensor networks through automatic service planning



Tags:
microsoft research