SlideShare una empresa de Scribd logo
1 de 13
1 
ViaSat Proprietary Information 
HIGH QUALITY 
SIMULATED VIDEO 
FROM STILL IMAGES 
presented by Alexander Chan & Nima Hashemi 
Advisor – Dr. Shay Har-Noy | Technical Lead – David 
Schmidt
|Typical UAV System 
1. UAV captures video of ground in real time 
2. Data transmitted via airborne modem 
3. Data passes through 10 mb/s data link 
4. Video received through ground modem and 
ViaSat Proprietary Information 
viewed 
(2) 
(3) 
(4) (1)
|Motivation: Pen or Marker? 
ViaSat Proprietary Information 
3 
Problem: 
Detecting small features in 
video is difficult. 
Resolution: 
Use high resolution still 
images to create 
simulated video.
| Comparing Video and Still 
Images 
ViaSat Proprietary Information 
4 
 Spatial versus Temporal Resolution 
 HD Video 
 1920x1080 = 2 Mp per frame. 3.2 pixel/inch 
 Still Images 
 4743 x 3162 = 15 Mp per frame. 7.9 pixel/inch
| Approach 
ViaSat Proprietary Information 
5 
(1) 
(3) 
(2) (4)
|System Overview 
ViaSat Proprietary Information 
6
|Image Stitching Algorithm 
ViaSat Proprietary Information 
7
|Image Stitching Visualized 
ViaSat Proprietary Information 
8 
Extracted Stitched Paired Mosaic FFeeaattuurree (Feature PPooiinnttss R(SeUmRaFin) Mapping (FLANN and Blurring) 
Matching & 
RANSAC) 
A B 
A & B
|Demonstration 
ViaSat Proprietary Information 
9 
 Zooming into video for visual feature detection 
 Synchronization between video and image 
windows
|Current Limitations and Future 
Steps 
ViaSat Proprietary Information 
10 
 Increase robustness of stitching algorithm 
 Increase accuracy of time relation between 
video feed and image viewer 
 Optimize CPU consumption throughout 
system
|What We Learned 
ViaSat Proprietary Information 
11 
 Image Processing and User Interface 
 Project Management and Spiral Development 
 “Integration takes longer than development” 
 Integrating Open Source Libraries 
 (OpenCV, IJG Library, and existing EnerView 
system)
|Conclusion & Applications 
ViaSat Proprietary Information 
12
|Acknowledgements 
ViaSat Proprietary Information 
13 
 Dr. Shay Har-Noy, Dave Schmidt, Steve 
Gardner 
 Fran Abrams and the ViaSat HR team 
 OpenCV Community, IJG Community 
 Kevin, Andy, Brian, Ricky, and our intern family 
 The Antarctic Penguins

Más contenido relacionado

Similar a Presentation: Simulating High Quality Video from Still Images

Emc vi pr global data services
Emc vi pr global data servicesEmc vi pr global data services
Emc vi pr global data servicessolarisyougood
 
"Portable Performance via the OpenVX Computer Vision Library: Case Studies," ...
"Portable Performance via the OpenVX Computer Vision Library: Case Studies," ..."Portable Performance via the OpenVX Computer Vision Library: Case Studies," ...
"Portable Performance via the OpenVX Computer Vision Library: Case Studies," ...Edge AI and Vision Alliance
 
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre..."Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...Edge AI and Vision Alliance
 
"Implementing Histogram of Oriented Gradients on a Parallel Vision Processor,...
"Implementing Histogram of Oriented Gradients on a Parallel Vision Processor,..."Implementing Histogram of Oriented Gradients on a Parallel Vision Processor,...
"Implementing Histogram of Oriented Gradients on a Parallel Vision Processor,...Edge AI and Vision Alliance
 
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual RealityFixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual RealityWen-Chih Lo
 
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...University of Southern California
 
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...University of Southern California
 
High Quality Video Simulation from Still Images
High Quality Video Simulation from Still ImagesHigh Quality Video Simulation from Still Images
High Quality Video Simulation from Still ImagesAlexander Chan
 
Case Study: Datalink—Manage IT monitoring the MSP way
Case Study: Datalink—Manage IT monitoring the MSP wayCase Study: Datalink—Manage IT monitoring the MSP way
Case Study: Datalink—Manage IT monitoring the MSP wayCA Technologies
 
SolarWinds Federal Webinar: Technical Update & New Feature Demo May 16, 2017
SolarWinds Federal Webinar: Technical Update & New Feature Demo May 16, 2017SolarWinds Federal Webinar: Technical Update & New Feature Demo May 16, 2017
SolarWinds Federal Webinar: Technical Update & New Feature Demo May 16, 2017SolarWinds
 
SolarWinds Federal Webinar: Technical Update & Demo of New Features
SolarWinds Federal Webinar: Technical Update & Demo of New FeaturesSolarWinds Federal Webinar: Technical Update & Demo of New Features
SolarWinds Federal Webinar: Technical Update & Demo of New FeaturesSolarWinds
 
Tim Malthus_Towards standards for the exchange of field spectral datasets
Tim Malthus_Towards standards for the exchange of field spectral datasetsTim Malthus_Towards standards for the exchange of field spectral datasets
Tim Malthus_Towards standards for the exchange of field spectral datasetsTERN Australia
 
Gain of Grain: A Film Grain Handling Toolchain for VVC-based Open Implementat...
Gain of Grain: A Film Grain Handling Toolchain for VVC-based Open Implementat...Gain of Grain: A Film Grain Handling Toolchain for VVC-based Open Implementat...
Gain of Grain: A Film Grain Handling Toolchain for VVC-based Open Implementat...Vignesh V Menon
 
Cisco Live Take Two: Network Troubleshooting Product Overview
Cisco Live Take Two: Network Troubleshooting Product OverviewCisco Live Take Two: Network Troubleshooting Product Overview
Cisco Live Take Two: Network Troubleshooting Product OverviewSolarWinds
 
Novel large scale digital forensics service platform for internet videos
Novel large scale digital forensics service platform for internet videosNovel large scale digital forensics service platform for internet videos
Novel large scale digital forensics service platform for internet videosAbdul-Fattah Mahran
 
OptIPuter Overview
OptIPuter OverviewOptIPuter Overview
OptIPuter OverviewLarry Smarr
 
Bd 2-577 big-data_video_surveillance_storage_solution-bc
Bd 2-577 big-data_video_surveillance_storage_solution-bcBd 2-577 big-data_video_surveillance_storage_solution-bc
Bd 2-577 big-data_video_surveillance_storage_solution-bcJoel W. King
 
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming ApplicationsSARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming ApplicationsAlpen-Adria-Universität
 
Zenoss as Core Element for Video QOS
Zenoss as Core Element for Video QOS Zenoss as Core Element for Video QOS
Zenoss as Core Element for Video QOS Zenoss
 

Similar a Presentation: Simulating High Quality Video from Still Images (20)

Awalin viz sec
Awalin viz secAwalin viz sec
Awalin viz sec
 
Emc vi pr global data services
Emc vi pr global data servicesEmc vi pr global data services
Emc vi pr global data services
 
"Portable Performance via the OpenVX Computer Vision Library: Case Studies," ...
"Portable Performance via the OpenVX Computer Vision Library: Case Studies," ..."Portable Performance via the OpenVX Computer Vision Library: Case Studies," ...
"Portable Performance via the OpenVX Computer Vision Library: Case Studies," ...
 
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre..."Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
"Fast Deployment of Low-power Deep Learning on CEVA Vision Processors," a Pre...
 
"Implementing Histogram of Oriented Gradients on a Parallel Vision Processor,...
"Implementing Histogram of Oriented Gradients on a Parallel Vision Processor,..."Implementing Histogram of Oriented Gradients on a Parallel Vision Processor,...
"Implementing Histogram of Oriented Gradients on a Parallel Vision Processor,...
 
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual RealityFixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
Fixation Prediction for 360° Video Streaming in Head-Mounted Virtual Reality
 
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
 
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
Crowdsourcing the Acquisition and Analysis of Mobile Videos for Disaster Resp...
 
High Quality Video Simulation from Still Images
High Quality Video Simulation from Still ImagesHigh Quality Video Simulation from Still Images
High Quality Video Simulation from Still Images
 
Case Study: Datalink—Manage IT monitoring the MSP way
Case Study: Datalink—Manage IT monitoring the MSP wayCase Study: Datalink—Manage IT monitoring the MSP way
Case Study: Datalink—Manage IT monitoring the MSP way
 
SolarWinds Federal Webinar: Technical Update & New Feature Demo May 16, 2017
SolarWinds Federal Webinar: Technical Update & New Feature Demo May 16, 2017SolarWinds Federal Webinar: Technical Update & New Feature Demo May 16, 2017
SolarWinds Federal Webinar: Technical Update & New Feature Demo May 16, 2017
 
SolarWinds Federal Webinar: Technical Update & Demo of New Features
SolarWinds Federal Webinar: Technical Update & Demo of New FeaturesSolarWinds Federal Webinar: Technical Update & Demo of New Features
SolarWinds Federal Webinar: Technical Update & Demo of New Features
 
Tim Malthus_Towards standards for the exchange of field spectral datasets
Tim Malthus_Towards standards for the exchange of field spectral datasetsTim Malthus_Towards standards for the exchange of field spectral datasets
Tim Malthus_Towards standards for the exchange of field spectral datasets
 
Gain of Grain: A Film Grain Handling Toolchain for VVC-based Open Implementat...
Gain of Grain: A Film Grain Handling Toolchain for VVC-based Open Implementat...Gain of Grain: A Film Grain Handling Toolchain for VVC-based Open Implementat...
Gain of Grain: A Film Grain Handling Toolchain for VVC-based Open Implementat...
 
Cisco Live Take Two: Network Troubleshooting Product Overview
Cisco Live Take Two: Network Troubleshooting Product OverviewCisco Live Take Two: Network Troubleshooting Product Overview
Cisco Live Take Two: Network Troubleshooting Product Overview
 
Novel large scale digital forensics service platform for internet videos
Novel large scale digital forensics service platform for internet videosNovel large scale digital forensics service platform for internet videos
Novel large scale digital forensics service platform for internet videos
 
OptIPuter Overview
OptIPuter OverviewOptIPuter Overview
OptIPuter Overview
 
Bd 2-577 big-data_video_surveillance_storage_solution-bc
Bd 2-577 big-data_video_surveillance_storage_solution-bcBd 2-577 big-data_video_surveillance_storage_solution-bc
Bd 2-577 big-data_video_surveillance_storage_solution-bc
 
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming ApplicationsSARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
SARENA: SFC-Enabled Architecture for Adaptive Video Streaming Applications
 
Zenoss as Core Element for Video QOS
Zenoss as Core Element for Video QOS Zenoss as Core Element for Video QOS
Zenoss as Core Element for Video QOS
 

Último

"Lesotho Leaps Forward: A Chronicle of Transformative Developments"
"Lesotho Leaps Forward: A Chronicle of Transformative Developments""Lesotho Leaps Forward: A Chronicle of Transformative Developments"
"Lesotho Leaps Forward: A Chronicle of Transformative Developments"mphochane1998
 
Introduction to Serverless with AWS Lambda
Introduction to Serverless with AWS LambdaIntroduction to Serverless with AWS Lambda
Introduction to Serverless with AWS LambdaOmar Fathy
 
Computer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to ComputersComputer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to ComputersMairaAshraf6
 
Moment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilMoment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilVinayVitekari
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXssuser89054b
 
AIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech studentsAIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech studentsvanyagupta248
 
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKARHAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKARKOUSTAV SARKAR
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptxJIT KUMAR GUPTA
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTbhaskargani46
 
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...Call Girls Mumbai
 
Online food ordering system project report.pdf
Online food ordering system project report.pdfOnline food ordering system project report.pdf
Online food ordering system project report.pdfKamal Acharya
 
Thermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - VThermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - VDineshKumar4165
 
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptxA CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptxmaisarahman1
 
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLEGEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLEselvakumar948
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueBhangaleSonal
 
kiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadkiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadhamedmustafa094
 
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxOrlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxMuhammadAsimMuhammad6
 
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptxHOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptxSCMS School of Architecture
 

Último (20)

"Lesotho Leaps Forward: A Chronicle of Transformative Developments"
"Lesotho Leaps Forward: A Chronicle of Transformative Developments""Lesotho Leaps Forward: A Chronicle of Transformative Developments"
"Lesotho Leaps Forward: A Chronicle of Transformative Developments"
 
Introduction to Serverless with AWS Lambda
Introduction to Serverless with AWS LambdaIntroduction to Serverless with AWS Lambda
Introduction to Serverless with AWS Lambda
 
Computer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to ComputersComputer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to Computers
 
Moment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilMoment Distribution Method For Btech Civil
Moment Distribution Method For Btech Civil
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 
AIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech studentsAIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech students
 
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKARHAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
 
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced LoadsFEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPT
 
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
 
Online food ordering system project report.pdf
Online food ordering system project report.pdfOnline food ordering system project report.pdf
Online food ordering system project report.pdf
 
Thermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - VThermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - V
 
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptxA CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
 
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLEGEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torque
 
Integrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - NeometrixIntegrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - Neometrix
 
kiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadkiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal load
 
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxOrlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
 
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptxHOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
 

Presentation: Simulating High Quality Video from Still Images

  • 1. 1 ViaSat Proprietary Information HIGH QUALITY SIMULATED VIDEO FROM STILL IMAGES presented by Alexander Chan & Nima Hashemi Advisor – Dr. Shay Har-Noy | Technical Lead – David Schmidt
  • 2. |Typical UAV System 1. UAV captures video of ground in real time 2. Data transmitted via airborne modem 3. Data passes through 10 mb/s data link 4. Video received through ground modem and ViaSat Proprietary Information viewed (2) (3) (4) (1)
  • 3. |Motivation: Pen or Marker? ViaSat Proprietary Information 3 Problem: Detecting small features in video is difficult. Resolution: Use high resolution still images to create simulated video.
  • 4. | Comparing Video and Still Images ViaSat Proprietary Information 4  Spatial versus Temporal Resolution  HD Video  1920x1080 = 2 Mp per frame. 3.2 pixel/inch  Still Images  4743 x 3162 = 15 Mp per frame. 7.9 pixel/inch
  • 5. | Approach ViaSat Proprietary Information 5 (1) (3) (2) (4)
  • 6. |System Overview ViaSat Proprietary Information 6
  • 7. |Image Stitching Algorithm ViaSat Proprietary Information 7
  • 8. |Image Stitching Visualized ViaSat Proprietary Information 8 Extracted Stitched Paired Mosaic FFeeaattuurree (Feature PPooiinnttss R(SeUmRaFin) Mapping (FLANN and Blurring) Matching & RANSAC) A B A & B
  • 9. |Demonstration ViaSat Proprietary Information 9  Zooming into video for visual feature detection  Synchronization between video and image windows
  • 10. |Current Limitations and Future Steps ViaSat Proprietary Information 10  Increase robustness of stitching algorithm  Increase accuracy of time relation between video feed and image viewer  Optimize CPU consumption throughout system
  • 11. |What We Learned ViaSat Proprietary Information 11  Image Processing and User Interface  Project Management and Spiral Development  “Integration takes longer than development”  Integrating Open Source Libraries  (OpenCV, IJG Library, and existing EnerView system)
  • 12. |Conclusion & Applications ViaSat Proprietary Information 12
  • 13. |Acknowledgements ViaSat Proprietary Information 13  Dr. Shay Har-Noy, Dave Schmidt, Steve Gardner  Fran Abrams and the ViaSat HR team  OpenCV Community, IJG Community  Kevin, Andy, Brian, Ricky, and our intern family  The Antarctic Penguins

Notas del editor

  1. Let the audience know who we are Name Major Year Aspirations (tech entrepreneur, business development ?)
  2. COINSTRAINTS: Video feed from UAV inherently mediocre quality: 10 mb/s data link limits video quality Zooming for video is sub-optimal Take this sample video frame: With regards to being able to detect small changes in landscape – it’s easy to see that there’s significant room for improvement.
  3. Mention Visionary Steve Gardner- “penguins”
  4. We take the conventional Video Feed and sort of turn it on its head. Mapping video feed to mosaic coordinates based on timestamp Displaying selected region in Image Viewer at high resolution and zoom Mosaic continues to be stitched dynamically as video plays Arrows represent direction of motion. Note that the small rectangle’s movement translates to the movement the image viewer
  5. Building a dialogue box off of the existing EnerView System
  6. I will go over this briefly. Start with a directory of images. Downsample images to decrease computation time. Extract features Find matching features between images RANSAC filters out bad matches Create homography out of accurate feature relationships -> this describes the overall translation of one image into another Finally apply the homography and combine the images -> through a short mapping and blurring algorithm
  7. Robustness – meaning it can extrapolate relationships between two images even if they are rotated, stretched, zoomed at different angles, etc. As of now, we are simply using a linear approach. Optimizing – multithreading, further downsampling of images,
  8. Various algorithms Zooming and aspect ratios Gained extensive experience in agile development cycle, unit testing, and core development
  9. A static image mosaic approach absolutely allows users to visually detect features more easily. Ecological surveying Disaster relief IED Detection