context for efficient recognition from
play

Context for Efficient Recognition from Large-Scale Topographic Map - PowerPoint PPT Presentation

Oct 03, 2022 •360 likes •1.25k views

ICC 2017 Washington D.C, USA July 02-07, 2017 Implementing the Concept of Geographic Context for Efficient Recognition from Large-Scale Topographic Map Series Johannes H. Uhl 1 Research Team: Stefan Leyk 1 , Yao-Yi Chiang 2 , Weiwei Duan 3 ,

  1. ICC 2017 Washington D.C, USA July 02-07, 2017 Implementing the Concept of Geographic Context for Efficient Recognition from Large-Scale Topographic Map Series Johannes H. Uhl 1 Research Team: Stefan Leyk 1 , Yao-Yi Chiang 2 , Weiwei Duan 3 , Vinil Jain 2 , Dan Feldman 2 , Craig Knoblock 3 1 Department of Geography 2 Spatial Sciences Institute 3 Computer Science Department University of Colorado Boulder University of Southern California University of Southern California

  2. Outline Map Processing: Impact & Challenges Geographic Context & Map Processing A Case Study and Outlook

  3. Outline I M AP P ROCESSING : I MPACT & C HALLENGES II T HE P RINCIPLE OF G EOGRAPHIC C ONTEXT III C ASE S TUDY : Recognition of Buildings and Urban Areas in Historical Topographic Maps Map Processing: Impact & Challenges Geographic Context & Map Processing A Case Study and Outlook

  4. I Map Processing: Impact & Challenges Map Processing: Impact & Challenges

  5. The Impact of Map Processing (a) Military Geographical Institute, Poland 1930, 1:25K (b) Royal Prussian Surveying Unit, Map of Western Russia, 1915, 1:100K (c) Imperial and Royal Military Geographical Institute, Austria, Map of the Austrian-Hungarian Monarchy and foreign map pages, Russia, 1878, 1:75K (d) Swiss Federal Topographic Bureau, Swiss Topographic Map (Siegfried Map), 1912, 1:25K  Preserving unique witnesses of the past  unlocking geographic information Map Processing: Impact & Challenges

  6. The Impact of Map Processing Map Processing: Impact & Challenges

  7. The Impact of Map Processing - Map processing = Recognition + Extraction - Pattern recognition, computer vision, machine learning... - Creating GIS-readable data from scanned map archives - Retrospective Landscape Analysis - Historians, Geographers, Demographers, Landscape Ecologists, etc… Map Processing: Impact & Challenges

  8. The Impact of Map Processing - Map processing = Recognition + Extraction - Pattern recognition, computer vision, machine learning... - Creating GIS-readable data from scanned map archives - Retrospective Landscape Analysis - Historians, Geographers, Demographers, Landscape Ecologists, etc… Map Processing: Impact & Challenges

  9. Current Challenges in Map Processing Map Processing: Impact & Challenges

  10. Current Challenges in Map Processing Map Processing: Impact & Challenges

  11. Current Challenges in Map Processing • Complexity, graphical quality, data volume • User interaction  Low levels of automation in information extraction Map Processing: Impact & Challenges

  12. Current Challenges in Map Processing • Complexity, graphical quality, data volume • User interaction  Low levels of automation in information extraction Map Processing: Impact & Challenges

  13. Current Challenges in Map Processing • Complexity, graphical quality, data volume • User interaction  Low levels of automation in information extraction Map Processing: Impact & Challenges

  14. Current Challenges in Map Processing Map recognition involving user interaction: Map Processing: Impact & Challenges

  15. Current Challenges in Map Processing Map recognition involving user interaction: Label Learn Extract Map Processing: Impact & Challenges

  16. Current Challenges in Map Processing Map recognition involving user interaction: Label Learn Extract Map Processing: Impact & Challenges

  17. Current Challenges in Map Processing Map recognition involving user interaction: Label Learn Extract shape, color & gradient descriptors Map Processing: Impact & Challenges

  18. Current Challenges in Map Processing Map recognition involving user interaction: Label Learn Extract shape, color & gradient descriptors Map Processing: Impact & Challenges

  19. Current Challenges in Map Processing Map recognition involving user interaction: Label Learn Extract shape, color & gradient descriptors How to overcome user labeling to achieve higher levels of automation? Map Processing: Impact & Challenges

  20. II The Principle of Geographic Context Effective use of external (geographic) data for improved information extraction from maps Geographic Context & Map Processing

  21. Geographic Context?  Map series in digital archives  Large data volume  Dependent editions with incremental change (updates)  Overlap in content to guide learning? 1950 Geographic Context & Map Processing

  22. Geographic Context?  Map series in digital archives  Large data volume 1964  Dependent editions with incremental change (updates)  Overlap in content to guide learning? 1950 Geographic Context & Map Processing

  23. Geographic Context?  Map series in digital archives  Large data volume 1964  Dependent editions with incremental change (updates)  Overlap in content to guide learning? 1950 Geographic Context & Map Processing

  24. 2012 Geographic Context?  Map series in digital archives  Large data volume 1964  Dependent editions with incremental change (updates)  Overlap in content to guide learning? 1950 Geographic Context & Map Processing

  25. 2012 Geographic Context?  Map series in digital archives  Large data volume 1964  Dependent editions with incremental change (updates)  Overlap in content to guide learning? 1950 Geographic Context & Map Processing

  26. 2012 Geographic Context?  Map series in digital archives  Large data volume 1964  Dependent editions with incremental change (updates)  Overlap in content to guide learning? 1950 Geographic Context & Map Processing

  27. 2012 Geographic Context?  Map series in digital archives  Large data volume 1964  Dependent editions with incremental change (updates)  Overlap in content to guide learning?  Generic (not independent) 1950 ancillary data representing feature of interest  Know “where to expect” the feature of interest Geographic Context & Map Processing

  28. Information Extraction & Geographic Context (1) Creating contextual information  Geometry  Attributes Geographic Context & Map Processing

  29. Information Extraction & Geographic Context Vector data (VGI…) Admin (1) Creating contextual information Records (x,y)  Geometry Gazetteer  Attributes Geographic Context & Map Processing

  30. Information Extraction & Geographic Context Vector data (VGI…) Admin (1) Creating contextual information Records (x,y)  Geometry Gazetteer  Attributes Geographic Context & Map Processing

  31. Information Extraction & Geographic Context Vector data (VGI…) Admin (1) Creating contextual information Records (x,y)  Geometry Gazetteer  Attributes (2) Adaptive graphics sampling  Collect spatially constrained graphics examples  Assume overlap: map & context Geographic Context & Map Processing

  32. Information Extraction & Geographic Context Vector data (VGI…) Admin (1) Creating contextual information Records (x,y)  Geometry Gazetteer  Attributes (2) Adaptive graphics sampling  Collect spatially constrained graphics examples  Assume overlap: map & context Geographic Context & Map Processing

  33. Information Extraction & Geographic Context Vector data (VGI…) Admin (1) Creating contextual information Records (x,y)  Geometry Gazetteer  Attributes (2) Adaptive graphics sampling  Collect spatially constrained graphics examples  Assume overlap: map & context Geographic Context & Map Processing

  34. Information Extraction & Geographic Context Vector data (VGI…) Admin (1) Creating contextual information Records (x,y)  Geometry Gazetteer  Attributes (2) Adaptive graphics sampling  Collect spatially constrained graphics examples  Assume overlap: map & context (3) Compute feature descriptors: Create knowledge base  Shape, color, texture descriptors  To be used in learning and extraction Geographic Context & Map Processing

  35. Information Extraction & Geographic Context Vector data (VGI…) Admin (1) Creating contextual information Records (x,y)  Geometry Gazetteer  Attributes (2) Adaptive graphics sampling  Collect spatially constrained graphics examples  Assume overlap: map & context (3) Compute feature descriptors: Create knowledge base  Shape, color, texture descriptors  To be used in learning and extraction Step (1) and (2): Eliminate user interaction Geographic Context & Map Processing

  36. III Case Study Geographic context for automated map symbol recognition: Buildings and Urban Areas Case Study: Building and Urban Area Extraction

  37. The Experiment Case Study: Building and Urban Area Extraction

  38. The Experiment Case Study: Building and Urban Area Extraction

  39. The Experiment Case Study: Building and Urban Area Extraction

  40. The Experiment Case Study: Building and Urban Area Extraction

  41. The Experiment Geographic Context Buildings Case Study: Building and Urban Area Extraction

  42. The Experiment Geographic Context Buildings Case Study: Building and Urban Area Extraction

  43. The Experiment Geographic Context Buildings Case Study: Building and Urban Area Extraction

Recommend

Context in Recognition 1. Note pages are interleaved with slides. These notes cover some of the

Context in Recognition 1. Note pages are interleaved with slides. These notes cover some of the

Context in Recognition 2008-03-27 Context in Recognition Adrian Quark March 27, 2008 Context in Recognition 1. Note pages are interleaved with slides. These notes cover some of the verbal content of the talk. Adrian Quark March 27, 2008

3.03k views • 64 slides
Instance level recognition III: Correspondence and efficient visual search Josef Sivic

Instance level recognition III: Correspondence and efficient visual search Josef Sivic

Computer Vision and Object Recognition 2011 Instance level recognition III: Correspondence and efficient visual search Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire dInformatique, Ecole Normale

1.09k views • 75 slides
Instance level recognition III: Correspondence and efficient visual search Josef Sivic

Instance level recognition III: Correspondence and efficient visual search Josef Sivic

Computer Vision and Object Recognition 2013 Instance level recognition III: Correspondence and efficient visual search Josef Sivic http://www.di.ens.fr/~josef INRIA, WILLOW, ENS/INRIA/CNRS UMR 8548 Laboratoire dInformatique, Ecole Normale

893 views • 74 slides
PROFESSIONAL DESIGNATIONS: RECOGNITION OF PRIOR LEARNING MASA IN CONTEXT A SHORT

PROFESSIONAL DESIGNATIONS: RECOGNITION OF PRIOR LEARNING MASA IN CONTEXT A SHORT

PROFESSIONAL DESIGNATIONS: RECOGNITION OF PRIOR LEARNING MASA IN CONTEXT A SHORT BACKGROUND CREDIBILITY IN CONTEXT THE COMPETENCY FRAMEWORK THE RPL PROCESS CHALLENGES & THE WAY FORWARD MASA IN CONTEXT A short

178 views • 15 slides
Supervised object recognition, unsupervised object recognition then Perceptual organization Bill

Supervised object recognition, unsupervised object recognition then Perceptual organization Bill

Supervised object recognition, unsupervised object recognition then Perceptual organization Bill Freeman, MIT 6.869 April 12, 2005 Readings Brief overview of classifiers in context of gender recognition:

1.48k views • 118 slides
Efficient Multi-Instance Learning for Activity Recognition from Time Series Data Using an

Efficient Multi-Instance Learning for Activity Recognition from Time Series Data Using an

Efficient Multi-Instance Learning for Activity Recognition from Time Series Data Using an Auto-Regressive Hidden Markov Model Xinze Guan, Raviv Raich, Weng-Keen Wong School of EECS, Oregon State University Email:

629 views • 27 slides
Efficient Wireless Data Transfer Ahmad Rahmati and Lin Zhong Rice Efficient Computing Group

Efficient Wireless Data Transfer Ahmad Rahmati and Lin Zhong Rice Efficient Computing Group

Context-for-Wireless: Context-Sensitive Energy- Efficient Wireless Data Transfer Ahmad Rahmati and Lin Zhong Rice Efficient Computing Group (recg.org) Dept. of Electrical & Computer Engineering Rice University Motivation Ubiquitous

663 views • 27 slides
LatentGNN: Learning Efficient Non-local Relations for Visual Recognition Songyang Zhang, Shipeng

LatentGNN: Learning Efficient Non-local Relations for Visual Recognition Songyang Zhang, Shipeng

LatentGNN: Learning Efficient Non-local Relations for Visual Recognition Songyang Zhang, Shipeng Yan, Xuming He ShanghaiTech University Songyang Zhang sy.zhangbuaa@gmail.com June 13, 2019 Goal & Motivation 1 Goal Learning efficient

241 views • 12 slides
Audio recognition, context-awareness, and its applications Yoonchang Han Co-founder & CEO,

Audio recognition, context-awareness, and its applications Yoonchang Han Co-founder & CEO,

Audio recognition, context-awareness, and its applications Yoonchang Han Co-founder & CEO, Cochlear.ai 26 March, 2018 Rule-based Deep learning methods (Source: Softbank Pepper) See Computer vision Understand Natural language

698 views • 35 slides
Towards efficient end-to-end architectures for action recognition and detection in videos Limin

Towards efficient end-to-end architectures for action recognition and detection in videos Limin

Towards efficient end-to-end architectures for action recognition and detection in videos Limin Wang Computer Vision Laboratory, ETH Zurich | | Limin Wang (CVL ETHZ) 17/4/12 1 Outline 1. Overview of action understanding 2. Temporal

578 views • 57 slides
Efficient recognition of totally nonnegative cells Seminar of Representation Theory and Related

Efficient recognition of totally nonnegative cells Seminar of Representation Theory and Related

Efficient recognition of totally nonnegative cells Seminar of Representation Theory and Related Areas: Third Workshop Porto, 9 November 2013 St ephane Launois (University of Kent) http://www.kent.ac.uk/ims/personal/sl261/index.htm

886 views • 49 slides
Efficient Dependency-Guided Named Entity Recognition Zhanming Jie Aldrian Obaja Muis Wei Lu

Efficient Dependency-Guided Named Entity Recognition Zhanming Jie Aldrian Obaja Muis Wei Lu

Efficient Dependency-Guided Named Entity Recognition Zhanming Jie Aldrian Obaja Muis Wei Lu Singapore University of Technology and Design February 7, 2017 Slides: http://www.statnlp.org/project/depner.html Table of Contents Motivation Named

551 views • 21 slides
A Partitioned Approach for Efficient Graph-Based Place Recognition Mattia G. Gollub, Renaud

A Partitioned Approach for Efficient Graph-Based Place Recognition Mattia G. Gollub, Renaud

A Partitioned Approach for Efficient Graph-Based Place Recognition Mattia G. Gollub, Renaud Dub, Hannes Sommer, Igor Gilitschenski, Roland Siegwart Problem Processing 3D point clouds can be computationally expensive. Problem

619 views • 35 slides
RECOGNITION & SUPPORT AN OVERVIEW THE CONTEXT: UK Deaf Sport (UKDS) Deaf Sport in the

RECOGNITION & SUPPORT AN OVERVIEW THE CONTEXT: UK Deaf Sport (UKDS) Deaf Sport in the

RECOGNITION & SUPPORT AN OVERVIEW THE CONTEXT: UK Deaf Sport (UKDS) Deaf Sport in the UK The Deaflympics DeaflympicsGB THE ISSUES: 1. Recognition 2. Support EVERY DEAF PERSON ACTIVE & INSPIRED BY SPORT LEADING

656 views • 10 slides
Instance-level recognition 1) Local invariant features 2) Matching and recognition with local

Instance-level recognition 1) Local invariant features 2) Matching and recognition with local

Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction Establish correspondence

1.77k views • 124 slides
CS 403X Mobile and Ubiquitous Computing Lecture 12: Activity Recognition Emmanuel Agu Activity

CS 403X Mobile and Ubiquitous Computing Lecture 12: Activity Recognition Emmanuel Agu Activity

CS 403X Mobile and Ubiquitous Computing Lecture 12: Activity Recognition Emmanuel Agu Activity Recognition Using Google API Activity Recognition Activity Recognition? Detect what user is doing? Part of users context Examples:

821 views • 24 slides
EARWD: an Efficient Activity Recognition system using Web activity Data A. M. Jehad Sarkar

EARWD: an Efficient Activity Recognition system using Web activity Data A. M. Jehad Sarkar

EARWD: an Efficient Activity Recognition system using Web activity Data A. M. Jehad Sarkar Advisor: Prof. Sungyoung Lee, Ph.D. Co-advisor: Prof. Young-Koo Lee, Ph.D. Department of Computer Engineering Kyung Hee University South Korea Thesis

767 views • 53 slides
Coral Reef Species Recognition and Whale Individual Recognition 09/09/2015 09/09/2015 1 1 1

Coral Reef Species Recognition and Whale Individual Recognition 09/09/2015 09/09/2015 1 1 1

Multimedia Retrieval in CLEF Coral Reef Species Recognition and Whale Individual Recognition 09/09/2015 09/09/2015 1 1 1 Context and challenges Exponential growth of sea-related multimedia data in the forms of images/videos/sounds

411 views • 21 slides
Graph Matching for Context Recognition Adrian Dobrescu and Andrei Olaru Adrian Dobrescu and

Graph Matching for Context Recognition Adrian Dobrescu and Andrei Olaru Adrian Dobrescu and

Graph Matching for Context Recognition Adrian Dobrescu and Andrei Olaru Adrian Dobrescu and Andrei Olaru 1 / 17 AgTAmI 2013 29.05.2013 Graph Matching for Context Recognition Outline Introduction Context Matching for Ambient

317 views • 18 slides
The efficient recognition of annotations by Google for www.seefeld.com Angela Popa, Hannes

The efficient recognition of annotations by Google for www.seefeld.com Angela Popa, Hannes

The efficient recognition of annotations by Google for www.seefeld.com Angela Popa, Hannes Pedevilla www.seefeld.com by Information Office Seefeld provides touristic information about Olympiaregion Seefeld, Leutasch, Msern-Buchen,

604 views • 19 slides
Context and Activity Recognition (aka Sensors + Inference) Varun Manjunatha CMSC 818G

Context and Activity Recognition (aka Sensors + Inference) Varun Manjunatha CMSC 818G

Context and Activity Recognition (aka Sensors + Inference) Varun Manjunatha CMSC 818G Three Papers 1) Zhou, et al. IODetector: A Generic Service for Indoor Outdoor Detection 2) Miluzzo, et al. Sensing Meets Mobile Social Networks: The

1k views • 63 slides
Algorithms for Natural Language Processing Lecture 12: Context-Free Recognition Levels of

Algorithms for Natural Language Processing Lecture 12: Context-Free Recognition Levels of

Algorithms for Natural Language Processing Lecture 12: Context-Free Recognition Levels of Linguistic Representation discourse pragmatics semantics syntax generation analysis most of this class lexemes morphology phonology orthography

706 views • 38 slides
8-Speech Recognition Speech Recognition Concepts Speech Recognition Approaches

8-Speech Recognition Speech Recognition Concepts Speech Recognition Approaches

8-Speech Recognition Speech Recognition Concepts Speech Recognition Approaches Recognition Theories Bayse Rule Simple Language Model P(A|W) Network Types 1 7-Speech Recognition (Cont d) HMM Calculating Approaches

1.08k views • 74 slides
Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 8: Hidden

Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 8: Hidden

Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 8: Hidden Markov Models (IV) - Tied State Models Instructor: Preethi Jyothi Jan 30, 2017 Recap: Triphone HMM Models Each phone is modelled in the context of

542 views • 25 slides

More recommend