Abstract:
It is very unreliable to implement manual analysis on crowd due to the density of
human’s unstructured behaviour, it is difficult to manage the abnormal behaviour of
the crowd. The target of this project is to develop image recognition algorithms to
recognize the physical behaviour of an individual. This report explores various
techniques utilized forthe recognition ofhuman’s physical behaviour. Different stages
involving image processing like the pre-processing stage, feature extraction and pose
estimation are studied and discussed in the report. The main advantage of using this
technique is that it provides features extraction and detection that is suitable for
character recognition
