Conference Paper

Advances in Automatic Gait Recognition.

Sch. of Electron. & Comput. Sci., Southampton Univ., UK
DOI: 10.1109/AFGR.2004.1301521 Conference: Sixth IEEE International Conference on Automatic Face and Gesture Recognition (FGR 2004), May 17-19, 2004, Seoul, Korea
Source: DBLP


Automatic recognition by gait is subject to increasing interest and has the unique capability to recognize people at a distance when other biometrics are obscured. Its interest is reinforced by the longstanding computer vision interest in automated non-invasive analysis of human motion. Its recognition capability is supported by studies in other domains such as medicine (biomechanics), mathematics and psychology, which continue to suggest that gait is unique. Further, examples of recognition by gait can be found in literature, with early reference by Shakespeare concerning recognition by the way people walk. Current approaches confirm the early results that suggested gait could be used for identification, and now on much larger databases. This has been especially influenced by the human ID at a distance research program with its wide scenario of data and approaches. Gait has benefited from the developments in other biometrics and has led to new insight particularly in view of covariates. As such, gait is an interesting research area, with contributions not only to the field of biometrics but also to the stock of new techniques for the extraction and description of objects moving within image sequences.

  • Source
    • "Of these characteristics, we focus on gait, which is a particular way or manner of moving on foot. Considerable evidence that gait is unique in its ability to determine one’s identity [2,3], thus supporting the use of one’s gait in recognition, has been reported in other domains such as biomechanics, mathematics, and psychology. Gait is attractive as a biometric identifier because it is unobtrusive and typifies the motion characteristics specific to an individual because it can be detected and measured at both a low resolution and a long distance [4]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a system of identifying individuals by their gait patterns. We take into account various distinguishable features that can be extracted from a user's gait and then divide them into two classes: walking pattern and stepping pattern. The conditions we assume are that our target environments are domestic areas, the number of users is smaller than 10, and all users ambulate with bare feet considering the everyday lifestyle of the Korean home. Under these conditions, we have developed a system that identifies individuals' gait patterns using our biometric sensor, UbiFloorII. We have created UbiFloorII to collect walking samples and created software modules to extract the user's gait pattern. To identify the users based on the gait patterns extracted from walking samples over UbiFloorII, we have deployed multilayer perceptron network, a feedforward artificial neural network model. The results show that both walking pattern and stepping pattern extracted from users' gait over the UbiFloorII are distinguishable enough to identify the users and that fusing two classifiers at the matching score level improves the recognition accuracy. Therefore, our proposed system may provide unobtrusive and automatic user identification methods in ubiquitous computing environments, particularly in domestic areas.
    Full-text · Article · Dec 2011 · Sensors
  • Source
    • "walking gait cycle of a particular leg describes the movements that takes place during the walk, from the time of one heel touching the ground until the same heel retouches the ground as illustrated in the Figure 1. There are two major approaches to gait recognition; appearance based (model free) and model based [14]. The majority of early approaches were appearance based, using features such as the silhouette. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Gait recognition approaches continue to struggle with challenges including view-invariance, low-resolution data, robustness to unconstrained environments, and fluctuating gait patterns due to subjects carrying goods or wearing different clothes. Although computationally expensive, model based techniques offer promise over appearance based techniques for these challenges as they gather gait features and interpret gait dynamics in skeleton form. In this paper, we propose a fast 3D ellipsoidal-based gait recognition algorithm using a 3D voxel model derived from multi-view silhouette images. This approach directly solves the limitations of view dependency and self-occlusion in existing ellipse fitting model-based approaches. Voxel models are segmented into four components (left and right legs, above and below the knee), and ellipsoids are fitted to each region using eigenvalue decomposition. Features derived from the ellipsoid parameters are modeled using a Fourier representation to retain the temporal dynamic pattern for classification. We demonstrate the proposed approach using the CMU MoBo database and show that an improvement of 15-20% can be achieved over a 2D ellipse fitting baseline.
    Preview · Conference Paper · Oct 2011
  • Source
    • "A gait cycle is the time interval between successive instances of initial foot-to-floor contact 'heel strike' for the same foot. Each leg has two distinct periods: a stance phase, when the foot is in contact with the floor, and a swing phase, when the foot is off the floor moving forward to the next step [3]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Gait as a behavioural biometrics has been the subject of recent investigations. One of the unique advantages of human gait is that it can be perceived from a distance. A varied range of research has been undertaken within the field of gait recognition. A gait describes the manner of a person's walking. It can be acquired at a distance and if necessary without consent or knowledge of the subject. Human gait representation can be roughly divided into two categories. One is model-based gait approach and other is model free gait approach. A human body feature that contributes more to an automatic gait classification is subdivided into two i.e. static (body shape) or dynamic (the movement of legs and arms). In this research work, we have considered dynamic features of human body for gait recognition. In our proposed research work, we have considered two features of human body i.e hand and feet for gait recognition. Second feature feet is subdivided into two i.e toe and heel. Both left and right legs toe and heel are considered. We follow an approach of parametric line equation for formulating two triangles between these features i.e first triangle is formed between hand and toe of both legs(right and left) and second triangle is formed between same hand and heel of both legs(right and left). After triangles formation we have find two intersecting points between these triangles and angles at these intersecting points. We have then calculated mean value of angles and intersecting points of an individual subject gait cycle frames and match mean value with database for recognition. We have designed a gait system using Matlab R2007b to accomplish this research work. We have worked on gray level images. Evaluation about the proposed gait recognition method is given according to experiments on CASIA gait database and the experimental results demonstrate the encouraging performance.
    Full-text · Conference Paper · Jan 2011
Show more