İkizler, NazlıCinbiş, R. GökberkDuygulu, Pınar2016-02-082016-02-082008-12http://hdl.handle.net/11693/26795Date of Conference: 8-11 Dec. 2008Conference name: 19th International Conference on Pattern Recognition, 2008We present a compact representation for human action recognition in videos using line and optical flow histograms. We introduce a new shape descriptor based on the distribution of lines which are fitted to boundaries of human figures. By using an entropy-based approach, we apply feature selection to densify our feature representation, thus, minimizing classification time without degrading accuracy. We also use a compact representation of optical flow for motion information. Using line and flow histograms together with global velocity information, we show that high-accuracy action recognition is possible, even in challenging recording conditions. © 2008 IEEE.EnglishAction recognitionClassification timeCompact representationFeature representationFeature selectionHigh-accuracyHuman-action recognitionMotion informationShape descriptorsVelocity informationGesture recognitionGraphic methodsOptical flowsFeature extractionConference Paper10.1109/ICPR.2008.4761434