Federico Tombari, PhD Computer Vision Lab. DEIS - ARCES, University of Bologna Viale Risorgimento, 2 40136 - Bologna, ITALY email: Federico DOT Tombari AT unibo DOT it Hi, and welcome to my home page. Here you can find my research interests and a summary of my experiences and personal news. SHORT BIO I received my B.Eng. and M.Eng. from University of Bologna, Italy, respectively in 2003 and 2005. In 2006 I joined DEIS (Dipartimento di Elettronica, Informatica e Sistemistica), University of Bologna as a Ph.D. student, and ARCES (Advanced Research Center on Electronic Systems), University of Bologna, Italy, as a collaborator. In April 2009 I received my Ph.D from University of Bologna, with a dissertation on "methodologies for visual correspondence".Currently I am a senior Post-doc at  Computer Vision Lab, University of Bologna. I am a member of IEEE and IAPR-GIRPR. My research interests focus on computer vision and pattern recognition, in particular they include stereo vision and 3D reconstruction, algorithms for video-surveillance, object recognition. In summer 2008 I had a great internship period at Willow Garage, California (USA) focusing on stereo algorithms for robots and accurate 3D reconstruction techniques based on stereo. During fall 2004 I spent one semester at UTS, Sydney (Australia) as an exchange student. RESEARCH ACTIVITY Stereo correspondence: "Fast-Aggregation": a novel algorithm deploying segmentation and incremental techniques to perform near real-time and accurate dense stereo matching (ICPR08). Preliminary experimental results available here.  A classification and performance evaluation of cost aggregation strategies for stereo matching (CVPR08). Detailed information, experimental results and software are available at this Web Site. "Segment-support": accurate dense local stereo matching using an aggregation strategy based on a variable support (PSIVT07). Experimental results here "SO+borders": accurate stereo matching based on cost aggregation  and a  Scanline  Optimization  framework (ACCV07). Experimental results here 3D Reconstruction: 3D reconstruction of scenes with moving objects/people using regularization methods, stereo matching and pattern projection (ICINCO 09)  Video analysis for video-surveillance: A novel multi-view change detection approach used to perform automatic detection of vandal act events such as graffiti (ECCV-VS08). Video 1 | Video 2 | Video 3 | Video 4  Automatic graffiti detection deploying a Time-of-Flight (TOF) sensor (ACIVS08). Video analysis with multimodal sensors (e.g. a PIR sensor and a camera) and embedded architectures (AVSS09, ECCV-MF2SFA209) Reliable access monitoring and singularization in interlocks (AVSS08). More Info available. Change detection approach based on background subtraction robust to sudden illumination changes occurring in the scene. (WACCV07). More Info and Software  | Demo Video  How to usefully deploy scene 3D information coming from a 3D device (e.g. a stereo vision system) in order to enhance robustness of a video-surveillance system (WACCV07). Preliminary experimental results available here.    Fast exhaustive pattern matching and block matching: Incremental Dissimilarity Approximations (IDA): fast exhaustive pattern matching based on Lp norm-based measures  (AVSS06, PAMI09)  Enhanced Bounded Correlation (EBC): an exhaustive technique to speed-up template matching based on Normalized Cross Correlation (NCC) (TIP08) ZEBC: a generalization of EBC to the ZNCC measure (ICIP08) Fast exhaustive block matching for motion estimation (ICIAP07),  A generalization of the Bounded Partial Correlation (BPC) technique to the ZNCC measure (ICIAR04, JPRL05) Use of SIMD instructions to increase the efficiency of template matching methods based on correlation measures (CAMP05). Robust visual correspondence: A class of matching measures for visual correspondence that are robust toward disturbance factors such as sudden illumination changes, noise, occlusions. They can be usefully adopted for tasks such a pattern matching, image registration, stereo vision, change detection (ICIAP07). More Info available. Performance evaluation of robust matching measures proposed in literature for the pattern matching task (VISAPP2008). Here you can find more information and a dataset for evaluation.  Robust methods for the registration of multi-modal and multi-temporal images, such as medical, remote sensing and industrial images. INDUSTRIAL PARTNERSHIPS and RESEARCH PROJECTS 2009/2010: SCALOPES European Project - SCalable LOw Power Embedded platformS 2008: "Advanced stereo matching algorithms for industrial applications" (with Datasensor SpA) 2007-2008: ARIS Project - automatic assistance for aeronautical maintenance procedures through augmented reality (with CIRA and V-Lab) 2006-2007: "Access monitoring and singularization for high security gates" (with Plexa Srl) 2006: "Vision-based systems for industrial safety applications" (with Datasensor SpA) 2006: "Vision-based quality control for the ceramic industry" (with System) TALKS and SEMINARS June 3, 2009: "Early processing of video sequences for video surveillance applications", IIT Demokritos, Athens, Greece November 26, 2008: "Recent research trends in stereo vision", University of Verona, Italy November 20, 2008: "Stereo for robots", University of Bologna, Italy April 28, 2008: "Algoritmi per la corrispondenza stereo", Datasensor SpA, Bologna, Italy TEACHING Spring, 2008/09: TA for RETI LOGICHE LA (digital design principles, under-grad.), University of Bologna Fall, 2008/09: TA for ELABORAZIONE DELL'IMMAGINE LS (image processing, post-grad.), University of Bologna Spring 2007/08: Lecturer, DISTEF project ("Integrated devices to record the thermal history of drugs"), Bologna, Italy Fall 2007/08: Lecturer, Master MIMA (“Metodologie Innovative per la Manutenzione Aeronautica"), Capua, Italy Fall, 2007/08: TA for ELABORAZIONE DELL'IMMAGINE LS (image processing, post-grad.), University of Bologna Spring, 2006/07: TA for RETI LOGICHE LA (digital design principles, under-grad.), University of Bologna Fall, 2006/07: TA for ELABORAZIONE DELL'IMMAGINE LS (image processing, post-grad.) , University of Bologna Materiale per gli studenti del corso di Elaborazione dell'Immagine LS:   Seminario sulla visione stereoscopica e sugli algoritmi per la corrispodenza stereo (pdf) Esercitazione n°1: introduzione a OpenCV (pdf) Esercitazione n° 2: operatori puntuali e convoluzione (pdf) Breve tutorial su come creare un nuovo progetto VisualStudio nel framework OpenCV (pdf) Il ricevimento in merito alle esercitazioni del corso è disponibile su appuntamento (inviandomi una email al mio indirizzo in calce). Tutto il materiale utile per il corso (incluso il progetto VisualStudio utilizzato durante le esercitazioni) è scaricabile al sito del corso. PUBLICATIONS INTERNAT. JOURNALS F. Tombari, S. Mattoccia, L. Di Stefano "Full search-equivalent pattern matching with Incremental Dissimilarity Approximations" IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI),  31(1), pp 129-141, January 2009 [Abstract] [Pdf] [Bibtex] S. Mattoccia, F. Tombari, L. Di Stefano "Fast  full-search equivalent template matching by Enhanced Bounded Correlation" IEEE Transactions on Image Processing (TIP),17(4), pp 528-538, April 2008 [Abstract] [Pdf] [Bibtex] L. Di Stefano, S. Mattoccia, F. Tombari “ZNCC-based template matching using Bounded Partial Correlation" Pattern Recognition Letters (JPRL), Vol. 16, No 14, pp 2129-2134, October 2005 [Abstract] [Pdf] [Bibtex] BOOK CHAPTERS F. Tombari, L. Di Stefano, S. Mattoccia Book title: "Stereo vision", Chapter "Robust visual correspondence: theory and applications" Edited by Asim Bhatti, November 2008, ISBN  978-953-7619-22-0 Publisher: I-Tech Education and Publishing Kirchengasse 43/3, A-1070, Vienna, Austria [Table of contents] [Pdf] INTERNAT. CONFERENCES and WORKSHOPS 2009 F. Tombari, A. Lanza, L. Di Stefano, S. Mattoccia "Non-linear Parametric Bayesian Regression for Robust Background Subtraction" Workshop on Motion and Video Computing (WMCV/MOTION) as part of IEEE Winter Vision Meetings 09 December 7-10, 2009, Snowbird, Utah, USA [Abstract] [Pdf] [Bibtex] F. Tombari, S. Mattoccia, L. Di Stefano, F. Regoli, R. Viti "A template analysis methodology to improve the efficiency of fast matching algorithms" Advanced Concepts for Intelligent Vision Systems (ACIVS 2009) September 28-October 2, 2009,  Bordeaux, France [Abstract] [Pdf] [Bibtex] S. Mattoccia, F. Tombari, L. Di Stefano "Enhanced low-resolution pruning for fast  full-search template matching" Advanced Concepts for Intelligent Vision Systems (ACIVS 2009) September 28-October 2, 2009, Bordeaux, France [Abstract] [Pdf] [Bibtex] M. Magno, F. Tombari, D. Brunelli, L. Di Stefano, L. Benini “Multimodal abandoned/removed object detection for low power video surveillance systems" IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2009) September 2-4, 2009, Genoa, Italy [Abstract] [Pdf] [Bibtex] F. Tombari, K. Konolige "A practical stereo system based on regularization and texture projection" 6th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2009) July 2-5, 2009, Milan, Italy [Abstract] [Pdf] [Bibtex] 2008 F. Tombari, S. Mattoccia, L. Di Stefano, E. Addimanda “Near real-time stereo based on effective cost aggregation" International Conference on Pattern Recognition (ICPR 2008) December 8-11, 2008, Tampa, Florida, USA [Abstract] [Pdf] [Bibtex] F. Tombari, L. Di Stefano, S. Mattoccia, A. Zanetti “Graffiti detection using a Time-Of-Flight camera" Advanced Concepts for Intelligent Vision Systems (ACIVS 2008) October 20-24, 2008, Juan-les-Pins, France [Abstract] [Pdf] [Bibtex] M. Magno, F. Tombari, D. Brunelli, L. Di Stefano, L. Benini "Multi-modal video surveillance aided by pyroelectric infrared sensors" ECCV Workshop on Multi-camera and Multi-modal Sensor Fusion, Algorithms and Applications (M2SFA2) October 18, 2008, Marseille, France [Abstract] [Pdf] [Bibtex] L. Di Stefano, F. Tombari, A. Lanza, S. Mattoccia, S. Monti "Graffiti detection using two views" ECCV 8th International Workshop on Visual Surveillance (VS 2008) October 17, 2008, Marseille, France [Abstract] [Pdf] [Bibtex] S. Mattoccia, F. Tombari, L. Di Stefano “Reliable rejection of mismatching candidates for efficient ZNCC template matching" IEEE International Conference on Image Processing (ICIP 2008) October 12-15, 2008, San Diego, California,  USA [Abstract] [Pdf] [Bibtex] L. Di Stefano, F. Tombari,  S. Mattoccia, M. Balasso “Multi-view access monitoring and singularization in interlocks" IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2008) September 1-3, 2008, Santa Fe, New Mexico,  USA [Abstract] [Pdf] [Bibtex] P. Azzari, L. Di Stefano, F. Tombari, S. Mattoccia “Markerless augmented reality using image mosaics" International Conference on Image and Signal Processing (ICISP 2008) July 1-3, 2008, Cherbourg-Octeville, Normandy, France [Abstract] [Pdf] [Bibtex] F. Tombari, S. Mattoccia, L. Di Stefano, E. Addimanda “Classification and evaluation of cost aggregation methods for stereo correspondence" IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2008) June 24-26, 2008, Anchorage, Alaska [Abstract] [Pdf] [Bibtex] F. Tombari, L. Di Stefano, S. Mattoccia, A. Galanti “Performance evaluation of robust matching measures" 3rd International Conference on Computer Vision Theory and Applications (VISAPP 2008) January 22-25, 2008, Funchal, Madeira Island, Portugal [Abstract] [Pdf] [Bibtex] 2007 F. Tombari, S. Mattoccia, L. Di Stefano “Segmentation-based adaptive support for accurate stereo correspondence" IEEE Pacific-Rim Symposium on Image and Video Technology  (PSIVT 2007) December 17-19, 2007, Santiago, Chile [Abstract] [Pdf] [Bibtex]  F. Tombari, S. Mattoccia, L. Di Stefano, F. Tonelli “Detecting motion by means of 2D and 3D information" ACCV'07 Workshop on Multi-dimensional and Multi-view Image Processing (ACCV WS 2007) November 19, 2007, Tokyo, Japan [Abstract] [Pdf] [Bibtex] L. Di Stefano, F. Tombari, S. Mattoccia, E. De Lisi “Robust and accurate change detection under sudden illumination variations" ACCV'07 Workshop on Multi-dimensional and Multi-view Image Processing (ACCV WS 2007) November 19, 2007, Tokyo, Japan [Abstract] [Pdf] [Bibtex] S. Mattoccia, F. Tombari, L. Di Stefano “Stereo vision enabling precise border localization within a scanline optimization framework" 8th Asian Conference on Computer Vision  (ACCV 2007) November 18-22, 2007, Tokyo, Japan [Abstract] [Pdf] [PS] [Bibtex] F. Tombari, L. Di Stefano, S. Mattoccia “A robust measure for visual correspondence" 14th IAPR International Conference on Image Analysis and Processing  (ICIAP 2007) September 10-13, 2007, Modena, Italy [Abstract] [Pdf] [PS] [Bibtex] S. Mattoccia, F. Tombari, L. Di Stefano, M. Pignoloni “Efficient and optimal block matching for motion estimation" 14th IAPR International Conference on Image Analysis and Processing  (ICIAP 2007) September 10-13, 2007, Modena, Italy [Abstract] [Pdf] [PS] [Bibtex] 2006 - previous F. Tombari, S. Mattoccia, L. Di Stefano “Template Matching based on the Lp norm using sufficient conditions with incremental  approximations" IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2006) November  22-24, 2006, Sydney, Australia [Abstract] [Pdf] [Bibtex] L. Di Stefano, S. Mattoccia, F. Tombari “Speeding-up NCC-based template matching using parallel multimedia instructions" IEEE International Workshop on Computer Architecture for Machine Perception (CAMP 2005) pp 193-197, July 4-6, 2005, Palermo, Italy [Abstract] [Pdf] [Bibtex] L. Di Stefano, S. Mattoccia, F. Tombari “An algorithm for efficient and exhaustive template matching" International Conference on Image Analysis and Recognition (ICIAR 2004) Lecture Notes in Computer Science 3212, Springer 2004 pp  408-415, September 29-October 1, 2004, Porto, Portugal [Abstract] [Pdf] [Bibtex] TECHNICAL REPORTS L. Di Stefano, S. Mattoccia, F. Tombari “Improving efficiency of ZNCC-based template matching: theory and experimental results” Technical Report IEIIT-BO-04-04, Bologna, March 2004 [Abstract] [Pdf] [PS] [Bibtex] S. Mattoccia, F. Tombari “About the accuracy of performance evaluation metrics aimed at estimating the Bounded Partial Correlation benefits” Technical Report IEIIT-BO-01-04, Bologna, January 2004 [Abstract] [Pdf] [PS] [Bibtex] LAST UPDATE: 27 October 2009 COPYRIGHT NOTICE: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.