Resume:  D. M. Gavrila
        Home Gavrila
        Resume
        Research
        People
        Publications
        Datasets
        Media Coverage
       Student Openings
        News
        Search

Biography (Short)

Dariu M. Gavrila received the PhD degree in computer science from the University of Maryland at College Park, USA, in 1996. From 1997 till 2016 he has been with Daimler R&D in Ulm, Germany, where he eventually became a Distinguished Scientist. In 2003, he was appointed professor at the University of Amsterdam, chairing the area of Intelligent Perception Systems (part-time). Since 2016 he heads the Intelligent Vehicles and Cognitive Robotics section at the TU Delft as a Full Professor.
 
Over the past 15 years, Prof. Gavrila has focused on visual systems for detecting humans and their activity, with application to intelligent vehicles, smart surveillance and social robotics. He led the multi-year pedestrian detection research effort at Daimler, which was incorporated in the Mercedes-Benz S-, E-, and C-Class models (2013-2014). He is frequently cited in the scientific literature and received the I/O 2007 Award from the Netherlands Organisation for Scientific Research (NWO) and the IEEE Intelligent Transportation Systems Application Award 2014. His personal Web site is www.gavrila.net.



Biography (Longer)

Dariu M. Gavrila is the son of the Romanian pianist Liana Serbescu and the Romanian physicist Prof. Mihai Gavrila. He completed secondary school at the Barlaeus Gymnasium in Amsterdam, The Netherlands (NL), in 1986. He received the MSc degree in computer science from the Vrije University in Amsterdam, NL, in 1990. He received the PhD degree in computer science from the University of Maryland at College Park, USA, in 1996. He was a Visiting Researcher at the MIT Media Laboratory in 1996.  For nearly 20 years, from 1997 till 2016, he has been with Daimler R&D in Ulm, Germany, where he raised through the ranks from Senior Scientist and Principal Scientist to Distinguished Scientist. In 2003, he was further appointed professor in the Faculty of Science at the University of Amsterdam, chairing the area of Intelligent Perception Systems (part-time). Since 2016 he heads the Intelligent Vehicles and Cognitive Robotics section at the TU Delft as a Full Professor.
 
Over the past 15 years, Prof. D. M. Gavrila has worked on perception systems for detecting humans and their activity, with application to intelligent vehicles, smart surveillance and social robotics. At the University of Amsterdam he investigated 3D person localization, pose estimation and tracking from overlapping cameras and video-audio sensor fusion. In his first years at Daimler, he developed the Chamfer System, a generic system for Bayesian, exemplar-based hierarchical shape matching. His main focus at Daimler thereafter turned to the active safety of pedestrians. He contributed to most EU and German research projects in this area during the past 15 years, from project acquisition to algorithm development and vehicle prototype testing. He published several pedestrian benchmark datasets, which are meanwhile widely used in the scientific community. He led the multi-year pedestrian detection research effort at Daimler which was incorporated in the Mercedes-Benz S-, E-, and C-Class models (2013-2014). He is currently working on a new generation of more effective active safety systems for vulnerable road users, that use body pose- and scene context features to anticipate future movement and possible collisions.  

Prof. D. M. Gavrila graduated seven Ph.D. students and over 15 MS students. He published 50+ papers in first-tier conferences and journals, and is frequently cited in the area of computer vision and intelligent vehicles (Google Scholar: about 10.000 times). He served as Area Chair at previous IEEE Intelligent Vehicles (IV), Int. Conf. on Computer Vision (ICCV), IEEE Advanced Video and Signal based Surveillance (AVSS) and German Pattern Recognition (DAGM) conferences; he is currently Program Co-Chair for the upcoming IV’2016 conference in Gotheborg, Sweden. He delivered keynotes at past IV’2012, Int. Conf. on Computer Vision Systems (ICVS’2013), AVSS’2007, Computer Analysis of Images and Patterns (CAIP’2003) and Austrian Pattern Recognition (ÖAGM’2014) conferences.

For the societal impact of his research, he received the I/O 2007 Award from the Netherlands Organisation for Scientific Research (NWO) and the IEEE Intelligent Transportation Systems Application Award 2014 (the latter as part of a Daimler team). He has had regular appearances in the German/Dutch broadcast and print media. His personal Web site is www.gavrila.net.



Areas of Interest

Perception and modeling, enabling systems to interact intelligently and effortlessly with human-inhabited environment. Primary application in intelligent vehicle domain. Other applications in smart surveillance and social robotics.



Current Positions

Principal Scientist (1997 to present)
Environment Perception Dept, Daimler Research and Technology, Ulm, Germany

Responsible for ``Looking at People'' technology for the next-generation intelligent vehicles at Daimler (i.e. active pedestrian and cyclist safety, driver monitoring)

Led the multi-year pedestrian detection research effort, which was incorporated in the 2013-2014 Mercedes-Benz S-, E-, and C-Class models (2000-2012), See also Pedestrian Detection and Media Coverage.

Acquired and managed several EU and national projects on active pedestrian safety on behalf of Daimler: EU WATCH-OVER (2006-2008), EU SAVE-U (2002-2005), EU PROTECTOR (2000-2002), DE AKTIV-SFR (2006-2010) and URBAN-SVT (2012-2016)

Developed the Chamfer System, a real-time vision system for shape-based object detection, with applications in intelligent vehicles, industrial vision and defense industry (1998-2005).

Professor (2003 to present, 1/5 part-time)
Intelligent Autonomous Systems Group, Informatics Institute, Univ. of Amsterdam, NL

Chair in “Intelligent Perception Systems”. Computational models for the recognition of human activities in dynamic environments. Research involves aspects in machine learning, computer vision, multi-modal perception, and autonomous systems.

Several guest lectures in machine learning and intelligent systems at the Bachelor and Master level yearly.



Previous Positions

Research Affiliate (Spring 1996)
Media Laboratory, Massachusetts Institute of Technology, Cambridge, U.S.A.
Collaboration with Prof. A. Pentland´s group on 3-D head model acquisition from single-view image sequences, as part of my Dissertation.

Research Assistant (1992-1996)
Center for Automation Research, University of Maryland, College Park,  U.S.A.
M
y Dissertation introduced a framework for multi-view 3-D tracking of humans in action.



Education

Ph.D. Degree in Computer Science (1996),

University of Maryland, College Park, U.S.A.,
Dissertation Title: 3-D Model-based Tracking of Humans in Action,
Advisor: Prof. Dr. Larry Davis.

Doctoraal Degree - B.S. and M.S. - in Computer Science (1990),
VU University, Amsterdam, The Netherlands,
Thesis Title: 3-D Object Recognition from 2-D Images using Geometric Hashing, Advisor: Prof. Dr. Frans Groen.

Propaedeuse Degree - preliminary comprehensive exam - in Physics (1987), VU University, Amsterdam, The Netherlands.

V.W.O. Degree - secondary school - (1986),
Barlaeus Gymnasium, Amsterdam, The Netherlands.



Keynote Speeches (Conferences, Symposia)

  • Automotive Innovation Award Symposium, Eindhoven, The Netherlands, 2015.
  • 38-th Annual Symposium of the Austrian Association for Pattern Recognition (ÖAGM), Klosterneuburg, Austria, 2014
  • 9-th International Conference on Computer Vision Systems (ICVS), St. Petersburg, Russia, 2013
  • 8th IEEE Int. Conf. on Intell. Comp. Communication and Processing (ICCP), Cluj, Romania, 2012
  • IEEE Intelligent Vehicles Symposium, Alcala de Henares, Spain, 2012. Watch keynote.
  • 1st IFAC Conf. on Embedded Systems, Computational Intelligence and Telematics in Control, Würzburg, Germany, 2012
  • 12th Jornadas de Automatica, Sevilla, Spain, 2011
  • 6th IEEE Conference on Advanced Video- and Signal-based Surveillance (AVSS), London, UK, 2007
  • 2nd IEEE International Conference on Intelligent Computer Communication and Processing (ICCP),  Cluj, Romania, 2006.
  • 10th International Conference on Computer Analysis of Images and Patterns (CAIP), Groningen, The Netherlands, 2003.
  • 6th Conference of the Advanced School for Computing and Imaging (ASCI), Lommel, Belgium, 2000.



Invited Talks (Workshops, Seminars)

  • Workshop “Image Processing Days” at AIRBUS (Manching, DE, 2014)
  • Workshop “Computer Vision for Road Scene Understanding and Autonomous Driving” at ECCV conference (Zürich, CH, 2014)
  • Workshop “Vehicle Autonomy in Urban Transportation Systems” at ICRA conference (Karlsruhe, DE, 2013)
  • Workshop “Computer Vision in Vehicle Technology” at ECCV conference (Florence, I, 2012)
  • Seminar ``Mens voor de Lens'' (Amsterdam, NL, 2012 and 2014)
  • Intelligent Machines Symposium (Nijmegen, 2010)
  • 10th Anniversary of Brain Institute at Brown University (Providence, USA, 2010) -
    panel with Peter Norvig (head Google Research) and Rodney Brooks (prof. em MIT),
  • NWO ToKeN Symposium (Tilburg, NL, 2010)
  • Int. Computer Vision Summer School (Sicily, IT, 2009)
  • Heidelberger Bildverarbeitungsforum (Heidelberg, DE, 2008)
  • WIC Public Safety Meeting (Eindhoven, NL, 2008)


Other Talks

  • 2015: TU Munich (Munich, DE), TU Prague (Prague, CZ), TNO Automotive (Helmond, NL)
  • 2014: Tsinghua Univ. (Beijing, CN), CLVP (Bucharest, RO), TU Delft (Delft, NL), MIT AI Laboratory (Cambridge, USA), NYU (New York, USA), Univ. of MD (College Park, USA), George Mason Univ. (Fairfax, USA), EPFL (Lausanne, CH), 
  • 2013: Microsoft Research (Cambridge, UK) watch talk online, Oxford Univ. (Oxford, UK), Imperial College (London, UK)
  • 2012: RWTH Aachen (Aachen, DE), Univ. Zaragoza (Zaragoza, ES), TU Delft (Delft, NL)
  • 2011: Philips Research (Eindhoven, NL, 2011), TU Darmstadt (Darmstadt, DE)
  • 2010: MIT AI Laboratory (Cambridge, USA), Brown Univ. (Providence, USA), Autonom. Univ. of Barcelona (Barcelona, ES)
  • 2009: TNO Automotive (Helmond, NL), Univ. Freiburg (Freiburg, NL), TU Twente (Enschede, NL)
     



Honors & Awards

  • IEEE Intelligent Transportation Systems Outstanding Application Award 2014 (part of a Daimler team)
  • IEEE Intelligent Transportation Systems Society Best Dissertation Award 2012 and Uni-DAS Research Award 2012 for Markus Enzweiler (supervised Ph.D. student)
  • DAGM 2011 Prize by the German Pattern Recognition Association
  • I/O 2007 Award by the Netherlands Organisation for Scientific Research (NWO),
    for quality of ICT research and outreach towards the general public
  • Best Paper Award at the IEEE AVSS 2007 conference
  • Graduate School Fellowship of the University of Maryland (top 1%)
  • Cum Laude at the Doctoraal Degree in Computer Science (top 1%)
  • Cum Laude at the Propaedeuse Degree in Physics (top 5%)
  • Cum Laude at the V.W.O. Degree (top 2%)



Thesis Supervision & Examination

  • (Co) Supervised seven Ph.D. Theses and 15+ M.Sc. Theses at Daimler and Univ. of Amsterdam. Three further PhD Theses are in progress. See People.
  • Served on 20+ Ph.D. Committees at the Univ. of Aalborg, Univ. of Amsterdam, Autonomous Univ. of Barcelona, TU Cluj, TU Darmstadt, Univ. of Heidelberg, Univ. of Mannheim, TU Twente, Univ. of Zaragoza and ETH Zürich (2002 to present)



Publications

See Publications.



Scientific Impact

  • Among the 3 / 300 most cited authors in Intelligent Vehicles / Computer Vision according to Google Scholar (January 2016)
  • h-index: 38, total 10200+ citations, see my Google Scholar page



Other Professional Activities

  • Organizing Committee Member for the workshops
    • 4th IEEE Workshop on Computer Vision in Vehicle Technology (at ICCV 2013 conference)
    • 3rd IEEE Workshop on Computer Vision in Vehicle Technology (at ECCV 2012 conference)
    • Interactive Human Behavior Analysis in Open or Public Spaces (at AMI 2011 conference)
    • 2nd IEEE Workshop on Computer Vision in Vehicle Technology (at ICCV 2011 conference)
  • Program Committee Member of the conferences
    • European Conference on Computer Vision (ECCV, 2004 and 2008)
    • Deutsche Arbeitsgemeinschaft für Mustererkennung (DAGM, 2001, 2004, 2007-2010)
    • Face and Gesture (FG, 2008)
  • Area Chair for the conferences
    • IEEE Advanced Video and Signal-Based Surveillance (AVSS, 2010)
    • IEEE Intelligent Vehicles (IV, 2011, 2013-2015)
    • IEEE Conference on Computer Vision (ICCV, 2011, 2015)
  • Reviewer for the journals
    • International Journal of Computer Vision
    • IEEE Trans. on Pattern Analysis and Machine Intelligence
    • IEEE Trans. on Intelligent Transportation Systems
  • Evaluator of proposals at EU FP6 and FP7 calls
    • Cognitive Systems (2005 and 2009)
    • Advanced Robotics (2006)
  • Member of professional societies
    • the Institute of Electrical and Electronics Engineers (IEEE)
    • the Dutch Pattern Recognition Society (NVBVPH)



Patent

German patent granted in the area of vision-based driver assistance, 2002



Media Coverage

See listing.


Languages

Fluent in English, German, Dutch and Romanian. Proficiency in French and Spanish.



References

Upon request.

 

[Home Gavrila] [Resume] [Research] [People] [Publications] [Datasets] [Media Coverage] [Open Positions] [News] [Search]

Copyright © 2001-2015 Gavrila. All rights reserved. Disclaimer.