Ph.D. thesis

Probabilistic models for motion segmentation in image sequences [pdf]


Machine Vision and Applications (MVA) - "Background subtraction - separating the modeling and the inference", M. Narayana, E. Learned-Miller, A. Hanson, To appear Dec 2013. [pdf]


ICCV 2013 - "Coherent motion segmentation in moving camera videos using optical flow orientations", M. Narayana, A. Hanson, E. Learned-Miller [pdf]
Supplementary material with video results and additional comparisons[zip file].

"Modeling complex camera rotation using optical flow orientations for motion segmentation", M. Narayana, A. Hanson, E. Learned-Miller, in submission [pdf to come]

BMVC 2012 - "Improvements in joint domain-range modeling for background subtraction", M. Narayana, E. Learned-Miller, A. Hanson, The BMVA British Machine Vision Conference, 2012.[pdf]

CVPR 2012 - "Background modeling using adaptive pixelwise kernel variances in a hybrid feature space", M. Narayana, E. Learned-Miller, A. Hanson, The IEEE Conference on Computer Vision and Pattern Recognition, 2012.[pdf]

CVPR 2008 Workshop - "Towards unconstrained face recognition", G. B. Huang, M. Narayana, and E. Learned-Miller, The Sixth IEEE Computer Society Workshop on Perceptual Organization in Computer Vision IEEE CVPR, 2008.[pdf]

AAAI 2008 TADA Workshop - "Applications of classifying bidding strategies for the CAT tournament", M. Gruman, M. Narayana, AAAI Workshop on Trading Agent Design and Analysis, 2008.[pdf]

CVPR 2007 Workshop - A Bayesian algorithm for tracking multiple moving objects in outdoor surveillance video, M. Narayana and D. Haverkamp, IEEE International Workshop on Object Tracking and Classification in and Beyond Visual Spectrum, CVPR 2007. [pdf]

Presentations and Reports

Classification of Trading Strategies in Adaptive Markets - Course project, Machine Learning, 2008 [paper] [presentation]

MS Honors Thesis, 2007 - Automatic Tracking of Moving Objects in Video for Surveillance Applications