Large-Scale Visual Geo-Localization

ISBN-13: 9783319257792 / Angielski / Twarda / 2016 / 351 str.

Amir Roshan Zamir; Asaad Hakeem; Mubarak Shah

Opis

This timely and authoritative volume explores the bidirectional relationship between images and locations. The text presents a comprehensive review of the state of the art in large-scale visual geo-localization, and discusses the emerging trends in this area. Valuable insights are supplied by a pre-eminent selection of experts in the field, into a varied range of real-world applications of geo-localization. Topics and features: discusses the latest methods to exploit internet-scale image databases for devising geographically rich features and geo-localizing query images at different scales; investigates geo-localization techniques that are built upon high-level and semantic cues; describes methods that perform precise localization by geometrically aligning the query image against a 3D model; reviews techniques that accomplish image understanding assisted by the geo-location, as well as several approaches for geo-localization under practical, real-world settings.

Spis treści

Introduction to Large Scale Visual Geo-Localization
Amir R. Zamir, Asaad Hakeem, Luc Van Gool, Mubarak Shah, and Richard Szeliski

Part I: Data-Driven Geo-Localization

Discovering Mid-Level Visual Connections in Space and Time
Yong Jae Lee, Alexei A. Efros, and Martial Hebert

Where the Photos Were Taken: Location Prediction by Learning from Flickr Photos
Li-Jia Li, Rahul Kumar Jha, Bart Thomee, David Ayman Shamma, Liangliang Cao, and Yang Wang

Cross-View Image Geo-Localization
Tsung-Yi Lin, Serge Belongie, and James Hays

Ultra-Wide Baseline Facade Matching for Geo-Localization
Mayank Bansal, Kostas Daniilidis, and Harpreet Sawhney

Part II: Semantic Reasoning-Based Geo-Localization

Semantically Guided Geo-Localization and Modeling in Urban Environments
Gautam Singh and Jana Košecká

Recognizing Landmarks in Large-Scale Social Image Collections
David J. Crandall, Yunpeng Li, Stefan Lee, and Daniel P. Huttenlocher

Part III: Geometric Matching-Based Geo-Localization

Worldwide Pose Estimation Using 3D Point Clouds
Yunpeng Li, Noah Snavely, Dan Huttenlocher, and Pascal Fua

Exploiting Spatial and Co-Visibility Relations for Image-Based Localization
Torsten Sattler, Bastian Leibe, and Leif Kobbelt

<3D Point Cloud Reduction Using Mixed-Integer Quadratic Programming
Hyun Soo Park, Yu Wang, Eriko Nurvitadhi, James C. Hoe, Yaser Sheikh, and Mei Chen

Image-Based Large-Scale Geo-Localization in Mountainous Regions
Olivier Saurer, Georges Baatz, Kevin Köser, L’ubor Ladický, and Marc Pollefeys

Adaptive Rendering for Large-Scale Skyline Characterization and Matching
Jiejie Zhu, Mayank Bansal, Nick Vander Valk, and Hui Cheng

User-Aided Geo-Localization of Untagged Desert Imagery

Visual Geo-Localization of Non-Photographic Depictions via 2D-3D Alignment
Mathieu Aubry, Bryan Russell, and Josef Sivic

Part IV: Real-World Applications

A Memory Efficient Discriminative Approach for Location-Aided Recognition
Sudipta N. Sinha, Varsha Hedau, C. Lawrence Zitnick, and Richard Szeliski

A Real-World System for Image/Video Geo-Localization
Himaanshu Gupta, Yi Chen, Minwoo Park, Kiran Gunda, Gang Qian, Dave Conger, and Khurram Shafique

Photo Recall: Using the Internet to Label Your Photos
Neeraj Kumar and Steven Seitz

O autorze

Dr. Amir R. Zamir is a postdoctoral researcher at the Computer Science Department of Stanford University, CA, USA.

Dr. Asaad Hakeem is a Principal Research Scientist in the Machine Learning Division at Decisive Analytics Corporation, Arlington, VA, USA.

Dr. Luc Van Gool is a Full Professor and Head of the Computer Vision Lab at ETH Zurich, Switzerland, and the VISICS Computer Vision at KU Leuven, Belgium. His other publications include the Springer title Detection and Identification of Rare Audio-visual Cues.

Dr. Mubarak Shah is Agere Chair Professor and Director of the Center for Research in Computer Vision at the University of Central Florida, Orlando, FL, USA. He is the Series Editor of Springer’s International Series in Video Computing, and he served as an Editor-in-Chief of the Springer journal Machine Vision and Applications from 2004 to 2015.

Dr. Richard Szeliski is the Director and a founding member of the Computational Photography applied research group at Facebook, Seattle, WA, USA. He is also the author of the best-selling Springer textbook Computer Vision – Algorithms and Applications.

Blurb

This timely and authoritative volume explores the bidirectional relationship between images and locations. The text presents a comprehensive review of the state of the art in large-scale visual geo-localization, and discusses the emerging trends in this area. Valuable insights are supplied by a pre-eminent selection of experts in the field, into a varied range of real-world applications of geo-localization.

Topics and features:

• Discusses the latest methods to exploit internet-scale image databases for devising geographically rich features and geo-localizing query images at different scales
  
• Investigates geo-localization techniques that are built upon high-level and semantic cues
  
• Describes methods that perform precise localization by geometrically aligning the query image against a 3D model
  
• Reviews techniques that accomplish image understanding assisted by the geo-location, as well as several approaches for geo-localization under practical, real-world settings
  
• Presents contributions from the leading and most active researchers in the field from both academia and industry
  

This invaluable text/reference is a must-read for all researchers interested in developing automatic methods for image geo-localization, whether for commercial, academic, or military domains. Professionals involved in computer vision, computer graphics, photogrammetry, computational optimization, geographic information systems, and other related disciplines, will also benefit from the detailed coverage of this emerging field.