Body Language Based Individual Identification in Video Using Gait and Actions

In intelligent surveillance systems, recognition of humans and their activities is generally the most important task. Two forms of human recognition can be useful: the determination that an object is from the class of humans (which is called human detection), and determination that an object is a particular individual from this class (this is called individual recognition). This paper focuses on the latter problem. For individual recognition, this report considers two different categories. First, individual recognition using “Style of walk” i.e. gait and second “style of doing similar actions” in video sequences. The “style of walk” and “style of actions” are proposed as a cue to discriminate between two individuals. The “style of walk” and “style of actions” for each individual is called their “body language” information.