Director of Computer Vision
Dr. Matt Turek joined Kitware in September 2007 as a Research & Development Engineer and has held positions of increasing responsibility including Technical Leader, Assistant Director, and (currently) Director of Computer Vision. Dr. Turek’s work has focused in multiple areas of computer vision including large scale behavior recognition and modeling; object detection; activity recognition; normalcy modeling and anomaly detection; and image indexing and retrieval. He has made significant contributions to multiple DARPA efforts, including Predictive Analysis for Naval Deployment Activities (PANDA), Persistent Stare Exploitation and Analysis System (PerSEAS), Automated Wide-Area Activity Recognition (AWARE), and Building Labeling for Urban Environments (BLUE) and is principal investigator on multiple efforts with Air Force Research Lab, including BAA and SBIR contracts. Dr. Turek regularly collaborates with a wide variety of government customers, including AFRL, NGA, DARPA, ARL, NRL, ONR, and IARPA and has delivered multiple large scale systems for operational use.
Dr. Turek has over 15 years experience in computer vision, imaging, and visualization. His Ph.D. research focused on applying combinatorial optimization techniques to computer vision problems. In particular, Dr. Turek developed novel approaches for estimating motion under difficult lighting conditions; multiscale segmentation and motion estimation; and deformable multi-object tracking. Prior to completing his PhD, Dr. Turek worked on industrial imaging and medical imaging projects at GE Global Research (1999-2003) and at GE Healthcare (1995-1999).
Dr. Turek received his B.S. in Electrical Engineering from Clarkson University (1995), his M.S. in Electrical Engineering from Marquette University (1999) and his Ph.D. in Computer Science (2007) from Rensselaer Polytechnic Institute (RPI).
- Advanced text and video analytics for proactive decision making," in SPIE Defense and Security, Anaheim, California, 2017. , "
- Deep learning for object detection and object-based change detection in satellite imagery," in National Symposium on Sensor and Data Fusion (NSSDF), 2017. , "
- Automatic pattern of life learning in satellite images through graph kernels," in National Symposium on Sensor and Data Fusion (NSSDF), 2017. , "
- Efficient generation of image chips for training deep learning algorithms," in SPIE Defense and Security, Anaheim, California, 2017. , "
- Deep architecture for small mover detection in overhead infrared imagery," in National Symposium on Sensor and Data Fusion (NSSDF), 2016. , "
- Functional scene element modeling for isr data," in National Symposium on Sensor and Data Fusion (NSSDF), 2016. , "
- Foundations for context-aware information retrieval for proactive decision support," in SPIE Defense and Commercial Sensing Conference - Next Generation Analyst IV, 2016. , "
- Real-time, full-frame wide area motion imagery analytics," in Military Sensing Symposium - Passive EO, 2015. , "
- Real-time multi-target tracking at 210 megapixels/second in wide area motion imagery," in IEEE Winter Conference on Applications of Computer Vision, 2014. , "
- KWIVER: An open source cross-platform video exploitation framework," p. 1–4, Jan. 2014. , "
- Vehicle change detection from aerial imagery using detection response maps," in SPIE Defense+ Security, 2014, p. 908906–908906. , "
- Automatic activity profile generation from detected functional regions for video scene analysis," Video Analytics for Business Intelligence, Studies in Computational Intelligence, vol. 409, p. 241–269, Jan. 2012. , "
- Graph cuts with many-pixel interactions: theory and applications to shape modelling," Image and Vision Computing, vol. 28, no. 3, p. 467–473, Mar. 2010. , "
- Unsupervised learning of functional categories in video scenes," in European Conference on Computer Vision, 2010. , "
- Content-based retrieval of functional objects in video using scene context," in European Conference on Computer Vision (ECCV), 2010. , "
- Designing Tracking Software for Image-Guided Surgery Applications: IGSTK Experience," vol. 3, no. 5, p. 395–403, Jan. 2008. , "
- Combinatorial Optimization for Tracking and Low-level Computer Vision Problems," Jul. 2007. , "
- Multiscale Modeling and Constraints for Max-flow/Min-cut Problems in Computer Vision," Jan. 2006. , "
- Illumination-invariant Tracking via Graph Cuts," vol. 2, p. 10–17, Jan. 2005. , "
- Bias in the Localization of Curved Edges," vol. 2, p. 554–565, Jan. 2004. , "
- Coronary Artery Angiography Using Multislice Computed Tomography Images," vol. 102, p. 1589–, Jan. 2000. , "
- Automated Segmentation and Visualization of the Left Ventricular Epicardium in Short Axis Cardiac Images Using MRI," Aug. 1999. , "