Dr. Roddy Collins joined the computer vision team at Kitware as an R&D engineer in September 2007. For over 15 years, he has collaborated in research programs across various areas of computer vision, including object-level change detection, applications of scene content analysis to object tracking, object segmentation via semantic ontologies, motion pattern learning and anomaly detection, and optical metrology. He has served as the Kitware principal investigator for the Intelligence Advanced Research Projects Activity (IARPA) Deep Intermodal Video Analytics (DIVA) program; the Defense Advanced Research Projects Agency (DARPA) Probabilistic Programming for Advancing Machine Learning (PPAML) program; and the Air Force Research Laboratory (AFRL) Hierarchical Dynamic Exploitation of FMV (full-motion video), or HiDEF, program. In addition, he has contributed to numerous other efforts for DARPA; IARPA; the U.S. Army Research, Development and Engineering Command (RDECOM); and AFRL. He was also a lead architect of the DARPA Video and Image Retrieval and Analysis Tool (VIRAT) system, and he developed and maintains the evaluation and metrics systems of the Kitware computer vision team.
Dr. Collins received his B.S. in computer science from the University of Virginia. He then completed his M.S and Ph.D. in computer science at Rensselaer Polytechnic Institute (RPI). His research at RPI aimed to reformulate the debugging process to show how semantic constraints can be evaluated in a reference implementation of a target semantic domain that can, in turn, be coupled to diverse, independently-developed target programs.
Prior to joining Kitware, Dr. Collins worked at the Visualization and Computer Vision Lab at GE Global Research Center. He has co-authored papers published in the IEEE Transactions on Pattern Analysis and Machine Intelligence and the International Journal of Computer Vision. He has reviewed papers for conferences such as Computer Vision and Pattern Recognition, Communication Networks and Services Research, and Machine Vision Applications. His work has appeared at both the International Conference on Pattern Recognition and the Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence.
- An End-to-End System for Content-Based Video Retrieval using Behavior, Actions, and Appearance with Interactive Query Refinement," Aug. 2015. , "
- KWIVER: An open source cross-platform video exploitation framework," p. 1–4, Jan. 2014. , "
- 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. , "
- Human-Robot Teamwork using Activity Recognition and Human Instruction," Oct. 2012. , "
- Unsupervised Learning of Functional Categories in Video Scenes," Sep. 2010. , "
- Content-based Retrieval of Functional Objects in Video using Scene Context," Sep. 2010. , "
- Evaluation of Compression Schemes for Wide Area Video," Oct. 2008. , "
- Evaluation of localized semantics: data, methodology, and experiments," International Journal of Computer Vision, vol. 77, no. 1, p. 199–217, May 2008. , "
- Object Boundary Detection in Images using a Semantic Ontology," vol. 21, no. 1, p. 956–957, Jan. 2006. , "
- Multi-view detection and tracking of travelers and luggage in mass transit environments," Jun. 2006. , "
- Recognition and Segmentation of Scene Content using Region-Based Classification," vol. 1, Jan. 2006. , "
- Restoring semantic context: a domain-aware debugger," PhD Thesis, Aug. 2004. , "
- A common set of perceptual observables for grouping, figure-ground discrimination and texture classification," Transactions on Pattern Analysis and Machine Intelligence, vol. 4, no. 25, p. 458–474, Apr. 2003. , "
- Classification of 3D Macro Texture Using Perceptual Observables," vol. 4, p. 113–117, Jan. 2002. , "
- Using Video for Recovering Texture," Oct. 2001. , "