An FSM based methodology for interleaved and concurrent activity recognition

Research on human activity recognition is one of the most promising research topic and is attracted attention towards a number of disciplines and application domains. Successful research has so far focused on recognizing sequential human activities. In real life people are performing actions not only in sequential but also in complex (concurrent or interleaved) manner. Recognizing complex activities remains a challenging and active area of research. Due to a high degree of freedom of human activities, it is difficult to have a model which can deal with interleaved and concurrent activities. We propose a method that uses automatically constructed finite state automata, stack and queue data structures for recognizing concurrent and interleaved activities.