A Type-2 fuzzy logic machine vision based approach for human behaviour recognition in intelligent environments

One of the key components in the development of intelligent environments is the recognition and analysis of human behaviour. However, the majority of traditional non-fuzzy machine vision based approaches rely on assumptions such as known spatial locations and temporal segmentations or they employ computationally expensive approaches such as sliding window search through a spatio-temporal volume. Hence, it is difficult for such traditional non-fuzzy methods to scale up and handle the high-levels of uncertainties available in real-world applications. This paper presents a system which is based on Interval Type-2 Fuzzy Logic Systems (IT2FLSs) for robust human behaviour recognition using machine vision in intelligent environments. We will present several experiments which were performed on the publicly available Weizmann human action dataset. It will be shown that the proposed IT2FLS outperformed the Type-1 FLS (T1FLS) counterpart as well as outperforming other traditional non-fuzzy systems.