Recognition of human action in motion detected images with GMACA


Creative Commons License

Peldek S., BECERİKLİ Y.

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, cilt.34, ss.1026-1043, 2019 (SCI İndekslerine Giren Dergi) identifier identifier

  • Cilt numarası: 34 Konu: 2
  • Basım Tarihi: 2019
  • Doi Numarası: 10.17341/gazimmfd.460500
  • Dergi Adı: JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY
  • Sayfa Sayıları: ss.1026-1043

Özet

In this article, recognition of human action was performed using motion detection images obtained with Generalized Multiple Attractor Cellular Automata (GMACA). GMACA is the type of Cellular Automata applied to more than one cell using the rule vector. Obtaining the rule vector in the application of the GMACA has a critical precaution. In this study, the GMACA rule vector, which is required to produce a single-length cycle attractor, was obtained using reachability tree-based methods. Detection of human motion in video images has been accomplished using attractors generated by the rule vector. In the developed action recognition method, the images are first converted to the gray color space. Then, the GMACA rule vector to be used for motion detection is created. Motion detection is performed using GMACA. The HOG feature vector is extracted from the motion detection images and the resulting HOG feature vectors are labeled according to their motion. The dataset is created in this way. The generated dataset is decomposed into training and test data sets by cross-validation. Recognition of human action is performed by the SVM method. Experimental results are shown by the confusion matrix. The classification performance of the recognition method developed using the confusion matrix has been demonstrated. Motion recognition with motion detection images obtained with GMACA is as good as existing background subtraction studies. The obtained results show that motion detection images obtained by GMACA can be used for action recognition. The weakness of GMACA is that it can be applied on binary patterns.