Human Activity Recognition Using Gait Pattern

Introduction

Nowadays, huge number of images and videos are developed and uploaded on a daily basis in different fields and for different purposes for example news, sport, entertainment, and education. The continued rapid growth in digital visualization makes it increasingly difficult to find, organize, access, and maintain user’s visual information. Video has become a pervasive media type over the last decade. The rapid progress in imaging sensor technology, faster data transmission, larger data storage and increasing computational power, all contribute to the ubiquitous availability of this media type. The fast growing number of video media has led to a significantly increased interest in automatic video analysis in recent years.

The goal of automatic video analysis is to use computer algorithms to automatically extract information from unstructured data such as video frames and generate structured description of objects and events that are present in the scene. Among many objects under consideration, humans are of special significance because they play a major role in most activities of interest in daily life. Therefore, being able to recognize basic human actions in an indispensable component towards this goal and has many important applications. For example, detection of unusual actions such as jumping, running can provide timely alarm for enhanced security (e.g. in a video surveillance environment) and safety (e.g. in a life-critical environment such as a patient monitoring system).

The capability of understanding human gestures offers users a new means of human interaction and can bring brand new gaming experience (e.g. using body pose to control the character in the game) to video players. Human activity recognition is also useful in video content indexing which makes searching in large volume of video data more accessible and efficient.

In this paper, we use the concept of Gait for human activity recognition. The definition of Gait is defined as: “A particular way or manner of moving on foot”. Using gait as a biometric is a relatively new area of study, within the realms of computer vision. It has been receiving growing interest within the computer vision community and a number of gait metrics have been developed. Early psychological Gait studies by Murray (1967) suggest that gait is a unique personal characteristic, with cadence and cyclic in nature.

We use the term Gait recognition to signify the identification of an individual from a video sequence of the subject walking. This does not mean that Gait is limited to walking, it can also be applied to running or any means of movement on foot. Gait as a biometric can be seen as advantageous over other forms of biometric identification techniques for the following reasons:

• •

  Unobtrusive: The gait of a person walking can be extracted without user knowing that they are being analyzed and without any cooperation from the user in the information gathering stage unlike fingerprinting or retina scans.

• •

  Distance Recognition: The gait of an individual can be captured at a distance unlike other biometrics such as fingerprint recognition and face recognition.

• •

  Reduced Detail: Gait recognition does not require images that have been captured to be of a very high quality unlike other biometrics such as face recognition, which can be easily affected by low resolution images.

• •

  Difficult to Conceal: The gait of an individual is difficult to disguise, by trying to do so the individual will probably appear more suspicious. With other biometric techniques such as face recognition, the individuals face can easily be altered or hidden.

Implementing real life activity recognition system is a daunting task considering the challenges at each stage of the system like background clutter, dynamic illumination changes, camera movements etc. in the background subtraction stage, partial occlusions in the tracking and feature extraction stages. The performance of the recognition system depends upon these stages. The activity recognition problem is characterized by large intra class variability introduced by various sources like the changes in camera viewpoint, anthropometry (body shapes and sizes of different actors), different dressing styles, changes in execution rate of activity, individual styles of actors, skin colors, etc. as shown in Figure 1, Figure 2, Figure 3, and Figure 4.