SlideShare a Scribd company logo
1 of 18
Feng-GUI
Computational Attention
Projects
Embedded
• Complexity = (width*height)*12
• 1280x720 frame takes =~ 100ms
• 320x240 frame takes =~ 10ms
• Memory Peak = (width*height)*1rgb(byte)
• Program Footprint = 10kb
1.5 GHz quad-core ARM Cortex-A9
FG SAAS vs. FG Embedded
Scene Analysis
• Test the embedded version inside a Canon
camera.
• Analyze detected ROIs to adjust factors as focus
and exposure accordingly.
• Similar to auto-area AF & Subject Tracking
Canon CHDK
Retinex
Retina/Cortex
Example: MultiScale Retinex with Contrast Restoration
Photoshop filter
Fovea retinex filter
Fovea filter - original
Fovea filter – Photoshop AC
Fovea filter - Contrast
Viewing 
Retargeting mobile content adaptation. 
crop and resize the photo
leaving most important part of the photo.
benefits: automatic content adaptation services. 
Automatic Thumbnails
Automatic Thumbnails
Automatic Thumbnails
Automatic Thumbnails
Automatic Thumbnails
visual search improves by 25%
Interaction
Enhanced navigation inside images on
handheld devices
Dynamic Ads & creative
optimization (DCO)
miscellaneous
Manufacture: Automatic defect localization in
machine vision
DSP: Automatic event detection in audio signals.
Medical: Automatic pathology detection and
localization in medical imaging.
Surveillance: Efficiently tracking patterns changes in
natural scenes.
miscellaneous
Compression: Region-based coding approach:
lower JPEG compression rates were used for
important areas
Medical: Attention Deficit/Hyperactivity
Disorder (AD/HD)

More Related Content

Similar to Computation Attention Machine Vision Projects

Advantage of IP system & Panasonic Security_Ver1.ppt
Advantage of IP system & Panasonic Security_Ver1.pptAdvantage of IP system & Panasonic Security_Ver1.ppt
Advantage of IP system & Panasonic Security_Ver1.ppt
PawachMetharattanara
 
Realtimeimageprocessing
RealtimeimageprocessingRealtimeimageprocessing
Realtimeimageprocessing
Gopi Nath
 
coach12
coach12coach12
coach12
rnir
 
FS Presentation CCTV solution rev1 (1).pptx
FS Presentation CCTV solution rev1 (1).pptxFS Presentation CCTV solution rev1 (1).pptx
FS Presentation CCTV solution rev1 (1).pptx
PawachMetharattanara
 

Similar to Computation Attention Machine Vision Projects (20)

Advantage of IP system & Panasonic Security_Ver1.ppt
Advantage of IP system & Panasonic Security_Ver1.pptAdvantage of IP system & Panasonic Security_Ver1.ppt
Advantage of IP system & Panasonic Security_Ver1.ppt
 
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati..."Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
"Designing Deep Neural Network Algorithms for Embedded Devices," a Presentati...
 
Realtimeimageprocessing
RealtimeimageprocessingRealtimeimageprocessing
Realtimeimageprocessing
 
“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...
“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...
“Jumpstart Your Edge AI Vision Application with New Development Kits from Avn...
 
Real Time Image Processing
Real Time Image ProcessingReal Time Image Processing
Real Time Image Processing
 
BACOM Project Safe City New 14082012.pptx
BACOM Project  Safe City New 14082012.pptxBACOM Project  Safe City New 14082012.pptx
BACOM Project Safe City New 14082012.pptx
 
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
“Tensilica Processor Cores Enable Sensor Fusion for Robust Perception,” a Pre...
 
Synesis Embedded Video Analytics
Synesis Embedded Video AnalyticsSynesis Embedded Video Analytics
Synesis Embedded Video Analytics
 
LEGaTO: Use cases
LEGaTO: Use casesLEGaTO: Use cases
LEGaTO: Use cases
 
Mx Presentation En 2008
Mx Presentation En 2008Mx Presentation En 2008
Mx Presentation En 2008
 
Remote HD and 3D image processing challenges in Embedded Systems
Remote HD and 3D image processing challenges in Embedded SystemsRemote HD and 3D image processing challenges in Embedded Systems
Remote HD and 3D image processing challenges in Embedded Systems
 
IMAGE PROCESSING
IMAGE PROCESSINGIMAGE PROCESSING
IMAGE PROCESSING
 
Dip sdit 7
Dip sdit 7Dip sdit 7
Dip sdit 7
 
coach12
coach12coach12
coach12
 
FS Presentation CCTV solution rev1 (1).pptx
FS Presentation CCTV solution rev1 (1).pptxFS Presentation CCTV solution rev1 (1).pptx
FS Presentation CCTV solution rev1 (1).pptx
 
Intro to Digital Photography
Intro to Digital PhotographyIntro to Digital Photography
Intro to Digital Photography
 
Circuitos de Video Vigilancia IP
Circuitos de Video Vigilancia IPCircuitos de Video Vigilancia IP
Circuitos de Video Vigilancia IP
 
Circuitos de Video Vigilancia IP
Circuitos de Video Vigilancia IPCircuitos de Video Vigilancia IP
Circuitos de Video Vigilancia IP
 
Emerging vision technologies
Emerging vision technologiesEmerging vision technologies
Emerging vision technologies
 
“Intensive In-camera AI Vision Processing,” a Presentation from Hailo
“Intensive In-camera AI Vision Processing,” a Presentation from Hailo“Intensive In-camera AI Vision Processing,” a Presentation from Hailo
“Intensive In-camera AI Vision Processing,” a Presentation from Hailo
 

Recently uploaded

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 

Recently uploaded (20)

Simplifying Mobile A11y Presentation.pptx
Simplifying Mobile A11y Presentation.pptxSimplifying Mobile A11y Presentation.pptx
Simplifying Mobile A11y Presentation.pptx
 
AI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by AnitarajAI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by Anitaraj
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
Decarbonising Commercial Real Estate: The Role of Operational Performance
Decarbonising Commercial Real Estate: The Role of Operational PerformanceDecarbonising Commercial Real Estate: The Role of Operational Performance
Decarbonising Commercial Real Estate: The Role of Operational Performance
 
Introduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMIntroduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDM
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
Modernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using BallerinaModernizing Legacy Systems Using Ballerina
Modernizing Legacy Systems Using Ballerina
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
API Governance and Monetization - The evolution of API governance
API Governance and Monetization -  The evolution of API governanceAPI Governance and Monetization -  The evolution of API governance
API Governance and Monetization - The evolution of API governance
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 

Computation Attention Machine Vision Projects

Editor's Notes

  1. Automatic Thumbnails for photos galleries
  2. * Automatic Thumbnail View: Instead of simply shrinking the entire original image, AutoThumbnails crops out less informative regions and keeps the most informative part of the image before shrinking. It displays the remaining rectangle, which contains all of the attention objects from the original image, as the thumbnail. * Automatic Zooming-in: This feature allows the viewer to go directly to the most informative part of an image while maintaining an appropriate display ratio. It selects the optimal region by finding the region that contains the most attention objects as possible under the display constraint. * Automatic Navigation: AutoThumbnails offers an optimal browsing path based on the image attention model. It automatically steers the viewing window through this path to show the important parts of the image.
  3. Region-based coding approach: lower JPEG compression rates were used for important areas