Matt Leotta

Matt Leotta

Technical Leader

Dr. Leotta graduated summa cum laude from Rensselaer Polytechnic Institute in 2003 with a dual bachelor’s of science in Computer Science and Computer Systems Engineering. He received both his MS in Applied Mathematics in 2007 and his PhD in Engineering in 2010 from Brown University.  His PhD work at Brown was supervised by Dr. Joseph Mundy and focused on tracking vehicles in traffic video while simultaneously reconstructing 3D models of the vehicles by fitting a generic deformable model.

Dr. Leotta joined Kitware in 2009 as an R&D Engineer and has made key technical contributions to various government and commercial computer vision projects.  He helped advance kinematic-based activity recognition for DARPA programs including the Video and Image Retrieval and Analysis Toolkit (VIRAT) and the Persistent Stare Exploitation and Analysis System (PerSEAS).  He helped develop road sign detection in street-level imagery for a commercial application.  He developed dense 3D surface reconstruction from aerial video for DARPA and demonstrated its application to improve video compression and super resolution.

More recently, as a technical lead, Dr. Leotta has been leading various programs with a focus on 3D reconstruction and navigation from video.  He led a commercial effort to develop algorithms for visual navigation of an endoscope for medical applications.  He also served as PI on a SBIR with the Air Force to develop better camera calibration through bundle adjustment of aerial video.  This work produced the open source Motion-imagery Aerial Photogrammetry Toolkit (MAP-Tk).  Dr. Leotta has also lead efforts with other government customers to apply the 3D reconstruction and super resolution work to satellite imagery.

Dr. Leotta has published several papers in peer-reviewed international conferences and journals. He is a strong proponent of open source computer vision software.  He has helped lead the development of the Kitware Image and Video Exploitation and Retrieval (KWIVER) toolkit.  Dr. Leotta also organized and presented related tutorials at CVPR 2012 and CVPR 2015 on open source computer vision using Python and open source structure-from-motion. He regularly serves on program committees for primary computer vision and robotics conferences (CVPR, ECCV, ICCV, WACV, ICRA, IROS).

  1. M. Leotta et al., "Open Source Structure-from-Motion for Aerial Video," Mar. 2016.
  2. K. Fieldhouse, M. J. Leotta, A. Basharat, R. Blue, D. Stoup, C. Atkins, L. Sherrill, B. Boeckel, P. Tunison, J. Becker, M. Dawkins, M. Woehlke, R. Collins, M. Turek, and A. Hoogs, "KWIVER: An open source cross-platform video exploitation framework," pp. 1--4, Jan. 2014.
  3. Z. H. Sun, M. Leotta, A. Hoogs, R. Blue, R. Neuroth, J. Vasquez, A. Perera, M. Turek, and E. Blasch., "Vehicle change detection from aerial imagery using detection response maps ," pp. 908906--908906, Jan. 2014.
  4. A. Perera, S. Oh, M. Leotta, I. Kim, B. Byun, C. Lee, S. McCloskey, J. Liu, B. Miller, Z. Huang, A. Vahdat, W. Yang, G. Mori, K. Tang, D. Koller, L. Fei-Fei, K. Li, G. Chen, J. Corso, Y. Fu, and R. Srihari, "GENIE TRECVID 2011 Multimedia Event Detection: Late-Fusion Approaches to Combine Multiple Audio-Visual features," Nov. 2011.
  5. A. Perera, S. Oh, M. Leotta, I. Kim, B. Byun, C. Lee, S. McCloskey, J. Liu, B. Miller, Z. Huang, A. Vahdat, W. Yang, G. Mori, K. Tang, D. Koller, L. Fei-Fei, K. Li, G. Chen, J. Corso, Y. Fu, and R. Srihari, "GENIE TRECVID 2011 Multimedia Event Detection: Late-Fusion Approaches to Combine Multiple Audio-Visual Features," Nov. 2011.
  6. M. Leotta and J. Mundy, "Vehicle surveillance with a generic, adaptive, 3d vehicle model," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 7, pp. 1457--1469, Jun. 2011.
  7. M. Leotta, "Generic, deformable models for 3-d vehicle surveillance," Ph.D Thesis, May 2010.
  8. M. Leotta and J. Mundy, "Predicting High Resolution Image Edges with a Generic, Adaptive, 3-D Vehicle Model," pp. 1311--1318, Jun. 2009.
  9. C. Tsai, B. Madore, M. Leotta, M. Sofka, G. Yang, A. Majerovics, H. Tanenbaum, C. Stewart, and B. Roysam, "Automated retinal image analysis over the internet," IEEE Transactions on Information Technology in Biomedicine, vol. 12, no. 4, pp. 480--487, Jul. 2008.
  10. M. Leotta et al., "3d slit scanning with planar constraints," Computer Graphics Forum, vol. 27, no. 8, pp. 2066--2008, Dec. 2008.
  11. M. Leotta et al., "Interactive 3D Scanning Without Tracking.," pp. 205--212, Oct. 2007.
  12. M. Leotta and J. Mundy, "Epipolar Curve Tracking in 3-D," vol. 6, pp. 325--328, Sep. 2007.
  13. M. Leotta and J. Mundy, "Learning Background and Shadow Appearance with 3-D Vehicle Models," vol. 2, pp. 649--658, Sep. 2006.
  14. D. Han, M. Leotta, D. Cooper, and J. Mundy, "Vehicle class recognition from video-based on 3D curve probes," pp. 871--878, Oct. 2005.