Human Action Recognition using a Hybrid NTLD Classifier

This work proposes a hybrid classifier to recognize humanactions in different contexts. In particular, the proposedhybrid classifier (a neural tree with linear discriminantnodes NTLD), is a neural tree whose nodes can be eithersimple preceptrons or recursive fisher linear discriminant(RFLD) classifiers. A novel technique to substitute badtrained perceptron with more performant linear discriminatorsis introduced. For a given frame, geometrical featuresare extracted from the skeleton of the human blob (silhouette).These geometrical features are collected for a fixednumber of consecutive frames to recognize the correspondingactivity. The resulting feature vector is adopted as inputto the NTLD classifier. The performance of the proposedclassifier has been evaluated on two available databases.

[1]  Ho Joon Kim,et al.  Human Action Recognition Using a Modified Convolutional Neural Network , 2007, ISNN.

[2]  Jean-Pierre Nadal,et al.  Neural trees: a new tool for classification , 1990 .

[3]  Gian Luca Foresti,et al.  Exploiting neural trees in range image understanding , 1998, Pattern Recognit. Lett..

[4]  Tim J. Ellis,et al.  ViHASi: Virtual human action silhouette data for the performance evaluation of silhouette-based action recognition methods , 2008, ICDSC.

[5]  Thomas Serre,et al.  A Biologically Inspired System for Action Recognition , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Paul E. Utgoff,et al.  Perceptron Trees : A Case Study in ybrid Concept epresentations , 1999 .

[7]  Ronald Poppe,et al.  Vision-based human motion analysis: An overview , 2007, Comput. Vis. Image Underst..

[8]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Balasubramanian Raman,et al.  Automated Stroke Classification in Tennis , 2007, ICIAR.

[10]  Pong C. Yuen,et al.  Human action recognition using boosted EigenActions , 2010, Image Vis. Comput..

[11]  Tong Heng Lee,et al.  Face recognition using recursive Fisher linear discriminant , 2006, IEEE Transactions on Image Processing.

[12]  Richard J. Mammone,et al.  Optimal pruning of neural tree networks for improved generalization , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[13]  Hironobu Fujiyoshi,et al.  Real-time human motion analysis by image skeletonization , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[14]  Juan Carlos Niebles,et al.  A Hierarchical Model of Shape and Appearance for Human Action Classification , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Ronen Basri,et al.  Actions as Space-Time Shapes , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Balasubramanian Raman,et al.  A classical approach for thinning of binary images using divergence of the potential field , 2005, Int. J. Comput. Math..

[17]  Greg Mori,et al.  Action recognition by learning mid-level motion features , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.