Automatically Identifying Automatically Identifying and - - PowerPoint PPT Presentation

Sneha Sneha Desai, Craig A. Desai, Craig A. Knoblock Knoblock, , Yao Yao-

• Yi Chiang,

Yi Chiang, Ching Ching-

• Chien

Chien Chen Chen and and Kandarp Kandarp Desai Desai

University of Southern California University of Southern California Department of Computer Science and Department of Computer Science and Information Sciences Institute Information Sciences Institute

Automatically Identifying Automatically Identifying and and Georeferencing Georeferencing Street Maps on the Web Street Maps on the Web

Outline Outline

• Introduction and Motivation
• Overall Approach and Algorithms
• Experimental Results
• Related Work
• Conclusion and Future Work

Introduction and Motivation Introduction and Motivation

• Various street maps are available on the

Various street maps are available on the web, but many of them web, but many of them

• cannot be easily distinguished with other

cannot be easily distinguished with other images images

• lack of the metadata that describes the

lack of the metadata that describes the geocoordinates geocoordinates and scales and scales

Introduction and Motivation Introduction and Motivation

Street Maps Scanned Documents Photographs Political, state, area maps

• Non street maps :
• Irrelevant for the applications

that seek only street maps

• Street maps :
• lack of metadata

Introduction and Motivation Introduction and Motivation

• In this work, we

In this work, we

• identify the street maps among different

identify the street maps among different images images

• a

apply our previous work pply our previous work to automatically extract road intersections from the street maps (Chiang et al.)

apply conflation techniques to find the

geocoordinates and align the streets on the maps with imagery (Chen et al.)

Outline Outline

• Introduction and Motivation
• Overall Approach and Algorithms
• Experimental Results
• Related Work
• Conclusion and Future Work

Overall Approach Overall Approach

Map Filter

Phase 2: Identifying street maps Phase 1: Retrieving images from different sources

Images

Intersections on the street Maps

s

Google Images Yahoo images

Street maps of the city queried Geocoordinates and scales of the street maps

Module 1: Automatic classification of street maps Module 2 : Automatic extraction of intersections Module 3 : Automatic georeferencing street maps

City name (Query String)

Identifying Street Maps Identifying Street Maps

• Law’s Texture Classification Algorithm

(K. Laws. 1980)

Street maps have the unique textures

lines, labels, characters

Generate 75 different attributes

(25R,25G,25B) to distinguish these textures on the images.

Identifying Street Maps Identifying Street Maps

• (note)

(note) SVMlight V2.0 Support Vector Machine (T. Joachims, 1999)

Training :

We provided 1150 different positive and negative

examples of images

75 attributes per image

Classification:

Using the trained SVM model to classify test images

Identifying Street Maps Identifying Street Maps

Filter 1 Filter 2 Street Maps Dense and Sparse Street Maps Detailed Street Maps Photographs, scanned docs, Political, area climate maps, icons (Non Street Maps) Different types of Images from Image Search

Georeferencing Georeferencing Street Maps Street Maps

• In our previous work:

In our previous work:

• Automatically and Accurately Conflating

Automatically and Accurately Conflating Orthoimagery Orthoimagery and Street Maps (Chen et al.) and Street Maps (Chen et al.)

• Integrate raster map and other sources.

Integrate raster map and other sources.

• Utilize the

Utilize the layout of the road intersections within a local area to determine the map to determine the map’ ’s s location. location.

Imagery with geocoordinate information

Vector data with geocoordinate information Raster map without geocoordinate information

Outline Outline

• Introduction and Motivation
• Overall Approach and Algorithms
• Experimental Results
• Related Work
• Conclusion and Future Work

Experimental Results Experimental Results

(name of the, p, r ) 5 Total retrieved image URLs from image sources 198 Non-Street Maps 113 (R=100%, P=97.35%) Street Maps 39 (R=92.86%, P=100%) Nonworking URLs + Duplicate URLs 46 Working URLs 152 Remove nonworking and duplicate URLs Filter-1 Street maps not of the city queried 15 (R=88.24%, P=100%) Automatically georeferenced street maps of the city queried 7 (R=100%, P=71.43%) Dense and sparse street maps 17 (R=94.44%, P=100%) Street maps, found by Filter2 22 (R=100%, P=95.45%) Filter-2

Experimental Results Experimental Results

• On the stage of
• Identifying street maps,

100% recall, 95.45% precision

• Georeferencing,

100% recall, 71.43% precision

• The average computation time for

identifying one street map 29.65 seconds

Outline Outline

• Introduction and Motivation
• Overall Approach and Algorithms
• Experimental Results
• Related Work
• Conclusion and Future Work

Related Work Related Work

• “Functionality Based Web Image Categorization.”

Hu et al.

• Focus on frequency domain and image features

like uniformity, size and aspect ratio. (put the difference)

• “Webseer: an image search engine for the world

wide web.” Frankel et al.

• Searching images by image context (file name-type-size

and color depth) and by content based tests (put the difference)

Outline Outline

• Introduction and Motivation
• Overall Approach and Algorithms
• Experimental Results
• Related Work
• Conclusion and Future Work

Conclusion and Future Work Conclusion and Future Work

Main Contribution:

• Identification of the street maps (precision

Identification of the street maps (precision = 95.45%) = 95.45%)

• Automatically

Automatically georeferencing georeferencing street maps street maps (precision = 71.43%) (precision = 71.43%)

• determine the

determine the geocoordinates geocoordinates, scales , scales

• align the map with satellite imagery

align the map with satellite imagery

Conclusion and Future Work Conclusion and Future Work

We plan to :

Classify the images into categories

political maps weather maps etc.

Reduce the number of feature dimensions Combine OCR-related techniques

Thank you Thank you