Description

Human action recognition is the process of labeling image sequences with action labels. Robust solutions to this problem have applications in domains such as visual surveillance, video retrieval and human–computer interaction. The task is challenging due to variations in motion performance, recording settings and inter-personal differences. Recognizing basic human actions from a monocular view is an important task for many applications such as video surveillance, human computer interaction and video content retrieval. Automatic recognition of human activities in video would be useful for surveillance, content-based summarization, and human-computer interaction applications, yet it remains a challenging problem. Some approaches seek ways to measure directly how humans are moving in the scene, using techniques for tracking, body pose estimation, or space-time shape templates while others aim to categorize activities based on the video’s over- all pattern of appearance and motion, often using spatio-temporal interest operators and local descriptors to build the representation. In this project, the system uses Binary Motion Image (BMI) to perform human activity recognition.