Explaining Optical Flow Events with Parameterized Spatio-Temporal Models Export

@article{citeulike:3149379, abstract = {A spatio-temporal representation for complex optical flow events is developed that generalizes traditional parameterized motion models (e.g. affine). These generative spatio-temporal models may be non-linear or stochastic and are event-specific in that they characterize a particular type of object motion (e.g. sitting or walking). Within a Bayesian framework we seek the appropriate model, phase, rate, spatial position, and scale to account for the image variation. The posterior distribution over this parameter space conditioned on image measurements is typically non-Gaussian. The distribution is represented using factored sampling and is predicted and updated over time using the Condensation algorithm. The resulting framework automatically detects, localizes, and recognizes motion events.}, address = {Los Alamitos, CA, USA}, author = {Black, Michael J.}, citeulike-article-id = {3149379}, citeulike-linkout-0 = {http://doi.ieeecomputersociety.org/10.1109/CVPR.1999.786959}, citeulike-linkout-1 = {http://dx.doi.org/10.1109/CVPR.1999.786959}, doi = {10.1109/CVPR.1999.786959}, issn = {1063-6919}, journal = {cvpr}, keywords = {computer\_vision, motion}, posted-at = {2008-08-22 16:47:13}, priority = {2}, publisher = {IEEE Computer Society}, title = {Explaining Optical Flow Events with Parameterized Spatio-Temporal Models}, url = {http://dx.doi.org/10.1109/CVPR.1999.786959}, volume = {01}, year = {1999} }

TY - JOUR ID - citeulike:3149379 L3 - citeulike-article-id:3149379 N2 - A spatio-temporal representation for complex optical flow events is developed that generalizes traditional parameterized motion models (e.g. affine). These generative spatio-temporal models may be non-linear or stochastic and are event-specific in that they characterize a particular type of object motion (e.g. sitting or walking). Within a Bayesian framework we seek the appropriate model, phase, rate, spatial position, and scale to account for the image variation. The posterior distribution over this parameter space conditioned on image measurements is typically non-Gaussian. The distribution is represented using factored sampling and is predicted and updated over time using the Condensation algorithm. The resulting framework automatically detects, localizes, and recognizes motion events. JF - cvpr SN - 1063-6919 AD - Los Alamitos, CA, USA TI - Explaining Optical Flow Events with Parameterized Spatio-Temporal Models PB - IEEE Computer Society VL - 01 KW - computer_vision KW - motion AU - Black, Michael PY - 1999/// UR - http://dx.doi.org/10.1109/CVPR.1999.786959 ER -