Human Activity Recognition in Archaeological Sites by Hidden Markov Models

This work deals with the automatic recognition of human activities embedded in video sequences acquired in an archeological site. The recognition process is performed in two steps: first of all the body posture of segmented human blobs is estimated frame by frame and then, for each activity to be recognized, a temporal model of the detected postures is generated by Discrete Hidden Markov Models. The system has been tested on image sequences acquired in a real archaeological site meanwhile actors perform both legal and illegal actions. Four kinds of activities have been automatically classified with high percentage of correct decisions. Time performance tests are very encouraging for using the proposed method in real time applications.