Advanced Topics in Computer Vision

  • 9h 24m
  • Giovanni Maria Farinella, Roberto Cipolla (eds), Sebastiano Battiato
  • Springer
  • 2013

This book presents a broad selection of cutting-edge research, covering both theoretical and practical aspects of reconstruction, registration, and recognition. The text provides an overview of challenging areas and descriptions of novel algorithms. Features: investigates visual features, trajectory features, and stereo matching; reviews the main challenges of semi-supervised object recognition, and a novel method for human action categorization; presents a framework for the visual localization of MAVs, and for the use of moment constraints in convex shape optimization; examines solutions to the co-recognition problem, and distance-based classifiers for large-scale image classification; describes how the four-color theorem can be used for solving MRF problems; introduces a Bayesian generative model for understanding indoor environments, and a boosting approach for generalizing the k-NN rule; discusses the issue of scene-specific object detection, and an approach for making temporal super resolution video.

About the Editors

Giovanni Maria Farinella obtained the Master degree in Computer Science (egregia cum laude) from University of Catania in 2004. He was awarded a Ph.D. degree (Computer Vision) in 2008. He became Associate Member of the Computer Vision and Robotics Research Group at University of Cambridge in 2006. He joined the Image Processing Laboratory (IPLAB) at the Department of Mathematics and Computer Science, University of Catania in 2008 as Contract Researcher. He is Contract Professor of Computer Vision at the School of Arts of Catania (since 2004) and Adjunct Professor of Computer Science at the University of Catania (since 2008). His research interests lie in the fields of Computer Vision, Pattern Recognition and Machine Learning. He has edited three volumes and co-authored more than 50 papers in international journals, conference proceedings and book chapters. He is a co-inventor of 3 international patents. Dr. Farinella also serves as a reviewer and on the programme committee for major international journals and international conferences. He has participated to several international and national research projects. Dr. Farinella founded (in 2006) and currently directs the International Computer Vision Summer School.

Sebastiano Battiato received his degree in computer science (summa cum laude) in 1995 from University of Catania and his Ph.D. in computer science and applied mathematics from University of Naples in 1999. From 1999 to 2003 he was the leader of the "Imaging" team at STMicroelectronics in Catania. He joined the Department of Mathematics and Computer Science at the University of Catania as assistant professor in 2004 and became associate professor in the same department in 2011. His research interests include image enhancement and processing, image coding, camera imaging technology and multimedia forensics. He has edited 4 books and co-authored more than 150 papers in international journals, conference proceedings and book chapters. He is a co-inventor of about 15 international patents, reviewer for several international journals, and he has been regularly a member of numerous international conference committees. Professor Battiato has participated in many international and national research projects. Chair of several international events (IWCV2012, ECCV2012, VISAPP 2012-2013-2014, ICIAP 2011, ACM Mi-For 2010-2011, SPIE EI Digital Photography 2011-2012-2013, etc.). He is an associate editor of the IEEE Transactions on Circuits and System for Video Technology and of the SPIE Journal of Electronic Imaging. Guest editor of the following special issues: "Emerging Methods for Color Image and Video Quality Enhancement" published on EURASIP Journal on Image and Video Processing (2010) and "Multimedia in Forensics, Security and Intelligence" published on IEEE Multimedia Magazine (2012). He is the recipient of the 2011 Best Associate Editor Award of the IEEE Transactions on Circuits and Systems for Video Technology. He is director (and co-founder) of the International Computer Vision Summer School (ICVSS). He is a senior member of the IEEE.

Roberto Cipolla obtained the B.A. degree (Engineering) from the University of Cambridge in 1984 and an M.S.E. (Electrical Engineering) from the University of Pennsylvania in 1985. From 1985 to 1988 he studied and worked in Japan at the Osaka University of Foreign Studies (Japanese Language) and Electrotechnical Laboratory. In 1991, he was awarded a D.Phil. (Computer Vision) from the University of Oxford and from 1991–1992 was a Toshiba Fellow and engineer at the Toshiba Corporation Research and Development Centre in Kawasaki, Japan. He joined the Department of Engineering, University of Cambridge in 1992 as a Lecturer and a Fellow of Jesus College. He became a Reader in Information Engineering in 1997 and a Professor in 2000. He is a Fellow at the Royal Academy of Engineering (since 2010); also a Professor of Computer Vision at the Royal Academy of Arts, London (since 2004) and Director of Toshiba's Cambridge Research Laboratory (since 2007). His research interests are in computer vision and robotics and include the recovery of motion and 3D shape of visible surfaces from image sequences; object detection and recognition; novel man–machine interfaces using hand, face and body gestures; real-time visual tracking for localization and robot guidance; applications of computer vision in mobile phones, visual inspection and image-retrieval and video search. He has authored 3 books, edited 8 volumes and co-authored more than 300 papers. Professor Cipolla founded (in 2006) and currently directs the International Computer Vision Summer School.

In this Book

  • Visual Features—From Early Concepts to Modern Computer Vision
  • Where Next in Object Recognition and How Much Supervision Do We Need?
  • Recognizing Human Actions by Using Effective Codebooks and Tracking
  • Evaluating and Extending Trajectory Features for Activity Recognition
  • Co-recognition of Images and Videos: Unsupervised Matching of Identical Object Patterns and its Applications
  • Stereo Matching—State-of-the-Art and Research Challenges
  • Visual Localization for Micro Aerial Vehicles in Urban Outdoor Environments
  • Moment Constraints in Convex Optimization for Segmentation and Tracking
  • Large Scale Metric Learning for Distance-Based Image Classification on Open Ended Data Sets
  • Top–Down Bayesian Inference of Indoor Scenes
  • Efficient Loopy Belief Propagation Using the Four Color Theorem
  • Boosting k-Nearest Neighbors Classification
  • Learning Object Detectors in Stationary Environments
  • Video Temporal Super-resolution Based on Self-similarity
SHOW MORE
FREE ACCESS