LEADER 02336oam 2200409zu 450 001 9910141001403321 005 20241212220051.0 010 $a1-4244-8834-6 035 $a(CKB)2670000000082935 035 $a(SSID)ssj0000668748 035 $a(PQKBManifestationID)12278218 035 $a(PQKBTitleCode)TC0000668748 035 $a(PQKBWorkID)10700406 035 $a(PQKB)11308052 035 $a(NjHacI)992670000000082935 035 $a(EXLCZ)992670000000082935 100 $a20160829d2010 uy 101 0 $aeng 135 $aur||||||||||| 181 $ctxt 182 $cc 183 $acr 200 10$a2010 IEEE Applied Imagery Pattern Recognition Workshop 210 31$a[Place of publication not identified]$cIEEE$d2010 215 $a1 online resource $cillustrations 300 $aBibliographic Level Mode of Issuance: Monograph 311 08$a1-4244-8833-8 330 $aActivity recognition has been applied to many varied applications ranging from surveillance to medical analysis. Interpreting human actions is often a complex problem for computer vision. Actions can be classified through shape, motion or region based algorithms. While all have their distinct advantages, we consider a feature extraction approach using convexity defects. This algorithmic approach offers a unique method for identifying actions by extracting features from hull convexity defects. Specifically, we create a hull around the segmented silhouette of interest in which the regions that exist in the hull are recognized. A feature database is created through a dataset of features for multiple individuals. These feature points are registered between progressive frames and then normalized for analysis. Using Principal Component Analysis (PCA), the feature points are classified to different poses. From there testing and training is performed to observe the classification into major human activities. This approach offers a robust and accurate method to identify actions and is invariant to size and human shape. 606 $aOptical pattern recognition$vCongresses 615 0$aOptical pattern recognition 676 $a006.42 702 $aIEEE Staff 801 0$bPQKB 906 $aPROCEEDING 912 $a9910141001403321 996 $a2010 IEEE Applied Imagery Pattern Recognition Workshop$92496190 997 $aUNINA