MoVi-MobiSys10 - MoVi:MobilePhonebased VideoHighlightsvia

Info iconThis preview shows pages 1–11. Sign up to view the full content.

View Full Document Right Arrow Icon
James Pittman February 9, 2011 EEL 6788 MoVi: Mobile Phone based  MoVi: Mobile Phone based  Video Highlights via  Video Highlights via  Collaborative Sensing Collaborative Sensing Xuan Bao, Romit Roy Choudhury, “MoVi: mobile phone based video highlights via collaborative sensing,” In Proc. of the 8th international conference on Mobile systems, applications, and services (MobiSys), 2010, pp. 357-370.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Outline Outline Introduction Assumptions System Overview Challenges Design elements Evaluation Experiments and Discussion of  Results Limitations and Conclusions 2
Background image of page 2
Introduction Introduction Basic Concepts Replace sensor motes with mobile  phones in social settings Sensors in these settings will record a  large amount of continuous data How do you distill all of the data from a  group of sensors in a social setting? Can mobile phone sensors in a social  setting be used to create “highlights” of  the occasion? 3
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Introduction Introduction Basic Concepts Develop trigger concepts to know when to  sense with phones Derive values for sensed data to  determine which sensor is recording the  ‘best’ data Combine system based sensor results to  create Highlights of social occasions Compare MoVi Highlights to human  created manual Highlights 4
Background image of page 4
Assumptions Assumptions 5 To make this system work  assumptions about the situation are  required: 1. People are wearing a camera  2. People are wearing a sensor (mobile  phone) These can be the same device
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
System Overview System Overview 6 The MoVi system has 4 parts 1. Group Management Analyze data to compute social groups  among phones 2. Trigger Detection Scan the data for potentially interesting  events
Background image of page 6
System Overview System Overview 7 The MoVi system has 4 parts 1. View Selector Pick a sensor or group with the best  “view” of the event 2. Event Segmentation Extract the appropriate section of video  that fully captures the event
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
System Overview System Overview 8 Client / Server Architecture for MoVi
Background image of page 8
Challenges Challenges Group Management 1. Correctly partitioning the mobile  devices into groups 2. Identifying “social zones” to based on  social context 3. Mapping the phones into the zones  and into groups and keeping them  updated 9
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Challenges Challenges Event Detection 1. Recognizing which events are socially  “interesting” 2. Deriving rules to classify the events as  interesting 10
Background image of page 10
Image of page 11
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 39

MoVi-MobiSys10 - MoVi:MobilePhonebased VideoHighlightsvia

This preview shows document pages 1 - 11. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online