<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<holdercode>{ibi 8JMKD3MGPEW34M/46T9EHH}</holdercode>
		<identifier>8JMKD3MGPBW4/35S6KT8</identifier>
		<repository>sid.inpe.br/sibgrapi@80/2009/08.17.22.40</repository>
		<lastupdate>2009:08.17.22.40.22 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi@80/2009/08.17.22.40.23</metadatarepository>
		<metadatalastupdate>2022:06.14.00.14.02 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2009}</metadatalastupdate>
		<doi>10.1109/SIBGRAPI.2009.29</doi>
		<citationkey>GuoIshwKonr:2009:AcReVi</citationkey>
		<title>Action recognition in video by covariance matching of silhouette tunnels</title>
		<format>Printed, On-line.</format>
		<year>2009</year>
		<numberoffiles>1</numberoffiles>
		<size>207 KiB</size>
		<author>Guo, Kai,</author>
		<author>Ishwar, Prakash,</author>
		<author>Konrad, Janusz,</author>
		<affiliation>Boston University</affiliation>
		<affiliation>Boston University</affiliation>
		<affiliation>Boston University</affiliation>
		<editor>Nonato, Luis Gustavo,</editor>
		<editor>Scharcanski, Jacob,</editor>
		<e-mailaddress>pi@bu.edu</e-mailaddress>
		<conferencename>Brazilian Symposium on Computer Graphics and Image Processing, 22 (SIBGRAPI)</conferencename>
		<conferencelocation>Rio de Janeiro, RJ, Brazil</conferencelocation>
		<date>11-14 Oct. 2009</date>
		<publisher>IEEE Computer Society</publisher>
		<publisheraddress>Los Alamitos</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Full Paper</tertiarytype>
		<transferableflag>1</transferableflag>
		<versiontype>finaldraft</versiontype>
		<keywords>video analysis, action recognition, silhouette tunnel, covariance matching, generalized eigenvalues.</keywords>
		<abstract>Action recognition is a challenging problem in video analytics due to event complexity, variations in imaging conditions, and intra- and inter-individual action-variability. Central to these challenges is the way one models actions in video, i.e., action representation. In this paper, an action is viewed as a temporal sequence of local shape-deformations of centroid-centered object silhouettes, i.e., the shape of the centroid-centered object silhouette tunnel. Each action is represented by the empirical covariance matrix of a set of 13-dimensional normalized geometric feature vectors that capture the shape of the silhouette tunnel. The similarity of two actions is measured in terms of a Riemannian metric between their covariance matrices. The silhouette tunnel of a test video is broken into short overlapping segments and each segment is classified using a dictionary of labeled action covariance matrices and the nearest neighbor rule. On a database of 90 short video sequences this attains a correct classification rate of 97%, which is very close to the state-of-the-art, at almost 5-fold reduced computational cost. Majority-vote fusion of segment decisions achieves 100% classification rate.</abstract>
		<language>en</language>
		<targetfile>IEEE-PID949748_final_submission.pdf</targetfile>
		<usergroup>pi@bu.edu</usergroup>
		<visibility>shown</visibility>
		<nexthigherunit>8JMKD3MGPEW34M/46SJQ2S</nexthigherunit>
		<nexthigherunit>8JMKD3MGPEW34M/4742MCS</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2022/05.14.19.43 4</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi@80/2009/08.17.22.40</url>
	</metadata>
</metadatalist>