Explainer: Gait Recognition
Gait recognition is a behavioral biometric modality that identifies people based on their unique walking pattern.
In comparison with other first-generation biometric modalities that include fingerprint and iris recognition, gait has the advantage of being unobtrusive, in that it requires no subject contact.
Gait recognition is based on the notion that each person has a distinctive and idiosyncratic way of walking, which can easily be discerned from a biomechanic viewpoint. Human movement does consist of synchronized movements of hundreds of muscles and joints, though basic movement patterns are similar, gait does vary from one person to another in terms of timing and magnitude.
As a consequence, minor variations in gait style can be used as a biometric identifier to identify individuals.
Gait recognition groups spatial-temporal parameters, such as step length, step width, walking speed and cycle time with kinematic parameters, such as joint rotation of the hip, knee and ankle, mean joint angles of the hip, knee and ankle and thigh, trunk and foot angles. Also considered is the correlation between step length and the height of an individual.
Because human ambulation is one form of human movements, gait recognition is closely related to vision methods that detect, track, and analyze human behaviors in human motion analysis. Gait recognition technologies are currently in their infancy. Currently, there are two main types of gait recognition techniques in development.
The first is gait recognition based on the automatic analysis of video imagery. This approach is the most popular approach studied and involves analysis of video samples of a subject’s walk and the trajectories of joints and angles. A mathematical model of the motion is created, and is subsequently compared against other samples in order to determine identity.
The second method uses a radar system, which records the gait cycle that the various body parts of the subject creates. This data is then compared to other samples in order to perform identification.
In both models, human body analysis is employed in an unobtrusive way using technical instrumentation that measures body movements, body mechanics and the activity of specific muscle groups.
Such technologies are projected for use in criminal justice and national security applications. Currently, the technology is under development at the Georgia Institute of Technology, MIT and the Lappeenranta University of Technology.