Faraz M. Mirzaei
University of Minnesota 612-***-****
*-*** **/** ********, 200 Union St. SE
Information abpou6@r.postjobfree.com
Minneapolis, MN 55455 umn.edu/~faraz
5+ years of experience in computer vision, image processing, and machine learning
Summary of
Qualifications 2+ years of experience in leading graduate and undergrad students in computer vision research
University of Minnesota, Minneapolis, MN
Education
Ph.D. in Computer Science Dec. 2011 (expected)
Thesis: Extrinsic and Intrinsic Sensor Calibration
Adviser: Prof. Stergios I. Roumeliotis
M.S. in Computer Science Jul. 2007
Shiraz University, Shiraz, Iran
B.Sc. in Electrical Engineering May 2004
Senior Project: Remote Rain Gauge Data Transfer System
Computer vision (Structure from motion, stereo/mono reconstruction, motion estimation)
Technical
Image processing (Segmentation, edge detection, denoising, feature detection/matching)
Skills
Machine learning and pattern recognition (Object detection/classi cation, SVM, K-PCA)
Estimator design (Extended/Unscented Kalman lter, particle lter, MAP, non-linear LS)
Robotics (Sensor calibration, SLAM, GPS/vision/laser-aided inertial navigation)
Extensive hardware experience (Camera, LiDAR, GPS, IMU, magnetometers)
Toshiba Medical Systems, Minnetonka, MN May 2011 Sep. 2011
Professional
Experience Intern Scientist
Contributed to a large project on o ine preprocessing of 3D medical images to improve the
quality and speed of organ segmentation/visualization algorithms
Developed a prototype for automatic hierarchical segmentation of 3D medical images (CT)
University of Minnesota, Minneapolis, MN Jan. 2005 May 2011
Research Assistant, Dept. of Computer Science and Engineering
Designed, implemented, and tested high-precision algorithms for:
Robust and real-time vanishing point estimation in urban environments with application
to localization, place recognition, and augmented reality
Laser-aided inertial navigation system for localization of the visually impaired inside build-
ings, achieving 10 cm accuracy in position and sub-degree accuracy in orientation
Intrinsic/extrinsic calibration of the Velodyne 3D LiDAR and the Ladybug spherical vision
system for use in photorealistic 3D reconstruction
SVM-based detection and classi cation of tra c signs for driving assistance
Simultaneous Localization and Mapping (SLAM) using 3D line segments and gyroscope/od-
ometry measurements in indoor environments
Line-segment extraction from range and image measurements using Probabilistic PCA
Showcased various robotic systems developed at the University of Minnesota to visitors from
industry (including executive teams), academia, and K12 schools
Faraz M. Mirzaei Page 2
Led team meetings to design and manufacture a new tracked ground robot
Participated in writing grant proposals for projects in robotics and computer vision
Corrosion Control & Management Co., Ahvaz, Iran Jun. 2004 Dec. 2004
Instrumentation Engineer
Worked with a team of programmers to develop industrial preventive maintenance software
Developed instruction manuals for calibration and maintenance of sensors in oil industry
Iran Telecommunication Research Center, Tehran, Iran Jun. 2002 Sep. 2002
Mobile/Cellular Communications Intern
Simulated a spread-spectrum smart antenna system for 3rd generation cellular communication
in Matlab and Simulink
C/C++, STL, Boost, Matlab, Python, Perl, VTune, CUDA, SWIG, Maple, Subversion
Computer
OS: GNU/Linux, Solaris, Windows
Skills
Doctoral Dissertation Fellowship, Graduate School, University of Minnesota 2008 2009
Awards &
Excellence in Research Award, Dept. of Computer Science, University of Minnesota 2007
Honors
Mentored 4 graduate students to implement computer vision and sensor calibration algorithms
Leadership
Led 5 undergrad students to design and manufacture a tracked robot and its electronic systems
roles
Reviewer of: IEEE Transactions on Robotics; International Journal of Robotic Research; IEEE
Services
International Conference on Robotics and Automation (ICRA); IEEE/RSJ International Con-
ference on Intelligent Robotics and Systems (IROS); Robotics: Science and Systems (RSS)
F. M. Mirzaei and S. I. Roumeliotis, Optimal estimation of vanishing points in a Manhattan
Selected
world, to appear in IEEE Int. Conf. Comput. Vis. (ICCV), Barcelona, Spain, Nov. 2011.
Publications
F. M. Mirzaei, D. G. Kottas and S. I. Roumeliotis, 3D Lidar-camera intrinsic and extrinsic
calibration: observability analysis and analytical least squares-based initialization, submitted
to Int. J. Robot. Research.
F. M. Mirzaei and S. I. Roumeliotis, Globally optimal pose estimation from line-to-line
correspondences, in Proc. IEEE Int. Conf. Robot. Autom. (ICRA), Shanghai, May 2011.
J. A. Hesch, F. M. Mirzaei, G. L. Mariottini, and S. I. Roumeliotis, A laser-aided inertial
navigation system (L-INS) for human localization in unknown indoor environments, in Proc.
IEEE Int. Conf. Robot. Autom. (ICRA), Anchorage, AK, May 2010.
F. M. Mirzaei and S. I. Roumeliotis, A Kalman lter-based algorithm for IMU-camera
calibration: observability analysis and performance evaluation, IEEE Trans. Robot., 24(5),
pp. 1143 1156, Oct. 2008. Top citation for IMU-camera calibration.
F. M. Mirzaei, A. I. Mourikis, and S. I. Roumeliotis, On the performance of multi-robot
target tracking, in Proc. IEEE Int. Conf. Robot. Autom. (ICRA), Rome, Italy, Apr. 2007.