Human identification by spatio-temporal symmetry

Hayfron-Acquah, J. B.; Nixon, Mark S.; Carter, J.N.

doi:10.1109/icpr.2002.1044824

Cited by 12 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Obviously, it could be seen that the results by using video snapshots are much better than using only one image for different number of persons walking with different styles. It is worth pointing out the difference between Tan et al in [14][15] and ours. We use focus on the cues in horizontal projections, but Tan et al in [14] use a focus on the cues in two diagonal directions and Tan et al in [15] use a focus on the cues in pseudo shape representation of Gait.…”

Section: Methodscontrasting

confidence: 69%

See 1 more Smart Citation

Human Verification System Based on Gait Recognition using Active Horizontal Levels (AHL) Feature

Almohammad

Salama

Mahmoud

et al. 2010

The International Conference on Electrical Engineering

View full text Add to dashboard Cite

Nowadays, Gait is a crucial field for many Pattern Recognition researchers. It is considered as a good way for biometric authentication in many surveillance systems. The most important issue in gait recognition is the features extraction from the silhouettes which are converted from walkers' images or videos. In this paper a new method has been introduced to identify night walker images, which are captured by infrared cameras. The new method depends on the silhouette's presence percentage on different horizontal levels. Minimum distance classifier has been used to choose the active horizontal levels that lead to the highest identification rate. A proposed algorithm which is used to select the Active Horizontal Levels (AHLs) has been presented. The proposed method was evaluated against CASIA silhouette database, to recognize walker into one, or multi silhouettes. The experimental results reveal the effectiveness of our new method against other Gait recognition methods to achieve a better recognition rate.Gait has played an important role in biometric authentication due to its unique characteristics compared with other biometrics. Gait can be captured at a distance and without requiring the prior consent of the observed subject. Most other biometrics such as fingerprints [1], face [2], hand geometry [3], iris [4], voice [5], and signature [6] can be captured only by physical contact or at a close distance from the recording probe. Gait also has the advantage of being difficult to hide, steal, or fake. The techniques used for gait recognition can be divided into two categories: model-based methods and motion-based methods. Model-based methods aim to explicitly model human body or motion, and they usually perform model matching in each frame of a walking sequence so that the parameters such as trajectories are measured on the model. Tao et al. [7] introduced a set of Gabor-based human-gait appearance models and propose a general tensor discriminant analysis (GTDA) to solve the carrying status in gait recognition. Rong Zhang et al. [8] proposed a 2-step, model-based approach, in which reliable gait features we re extracted by fitting a five-link biped human locomotion model for each image to avoid shape information. Sundaresan et al. [9] proposed a hidden-Markov models-based framework for individual recognition by gait. Tan et al. [10] used Orthogonal diagonal projection for gait recognition. Tan et al.[11] recognized night walkers based on one pseudo shape representation of Gait. The effectiveness of model-based methods, especially in body structure/motion modeling and parameter recovery from a walking video, is still limited allowing for current imperfect vision techniques (e.g., tracking and localizing human body accurately in 2D or 3D space has been a long-term challenging and unsolved problem). Further, the computational cost of model-based methods is relatively high. However, motion-based approaches can be further divided into two main classes. The first class called the state space methods. These methods consid...

show abstract

Section: Methodscontrasting

confidence: 69%

“…BenAbdelkader et al [14] used image self-similarity plots of a moving person to recognize gait. More recently, Hayfron-Acquah et al [15] described an automatic gait recognition method using the spatiotemporal symmetry. Collins et al [16] established a method based on template matching of body silhouettes in key frames for human identification.…”

mentioning

confidence: 99%

Human Verification System Based on Gait Recognition using Active Horizontal Levels (AHL) Feature

Almohammad

Salama

Mahmoud

et al. 2010

The International Conference on Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…An automatic gait recognition method using spatiotemporal symmetry was introduced in Hayfron-Acquah et al [18]. Generalized symmetry operator is used for extracting the features.…”

Section: Motion-based or Holistic Approachesmentioning

confidence: 99%

Occlusion detection and gait silhouette reconstruction from degraded scenes

Roy

Sural

Mukherjee

et al. 2011

SIViP

View full text Add to dashboard Cite

Gait, which is defined as the style of walking of a person, has been recognized as a potential biometric feature for identifying human beings. The fundamental nature of gait biometric of being unconstrained and captured often without a subject's knowledge or co-operation has motivated many researchers over the last one decade. However, all of the approaches found in the literature assume that there is little or no occlusion present at the time of capturing gait images, both during training and during testing and deployment. We look into this challenging problem of gait recognition in the presence of occlusion. A novel approach is proposed, which first detects the presence of occlusion and accordingly extracts clean and unclean gait cycles from the whole input sequence. In the second step, occluded silhouette frames are reconstructed using Balanced Gaussian Process Dynamical Model (BGPDM). We evaluated our approach on a new data set TUM-IITKGP featuring inter-object occlusion. Algorithms have also been tested on CMU's Mobo data set by introducing synthetic occlusion of different degrees.

show abstract

“…These show promise for baseline approaches that impose low computational and storage cost, together with deployment and development of new computer vision techniques for sequence-based analysis. These factors have also motivated our own approaches that range from a baselinetype approach by measuring area [22], to extension of technique for object description including symmetry [25] and statistical moments [23]. Further, we have extended our model-based technique to include full limb movement [28] and show how a model-based approach can facilitate greater application capabilities, especially that it can be used to recognise subjects not just by the way they walk, but also by how they run [29].…”

Section: Automatic Recognition By Gaitmentioning

confidence: 99%

“…Similarly, inclusion of time within symmetry calculation can be achieved [25] by reformulating the distance functional to operate over time as well as space, as in equation (2) above where Tj, t describes a point j in the silhouette at time t. The relative contribution of spatial and temporal symmetry is controlled by choice of the weighting W and their individual contributions moderated by choice of values for σs and µs and for σ T and µ T , respectively. Equation 2 is the modified distance functional in the discrete symmetry operator for which the other functionals (phase and intensity) remain unchanged.…”

Section: Figure 1: Gait Recognition By Silhouette Analysismentioning

confidence: 99%

New Advances in Automatic Gait Recognition

Nixon

Carter

Shutler

et al. 2002

Information Security Technical Report

View full text Add to dashboard Cite

Recognising people by their gait is an emergent biometric. Until recently there was evaluation by few techniques on relatively small databases though with encouraging results. The potential of gait as a biometric has further been encouraged by the considerable amount of evidence available, especially in medicine and literature. This evident potential motivated development of new databases, new technique and more rigorous evaluation procedures. We describe the new techniques we have developed and their evaluation on our database to gain insight into the potential for gait as a biometric. We also describe some of our new approaches aimed to aid generalization capability for deployment of gait recognition. We show on these new and much larger databases, how our novel techniques continue to provide encouraging results for gait as a biometric, let alone as a human identifier, with especial regard for recognition at a distance.

show abstract

Human identification by spatio-temporal symmetry

Abstract: We describe spatio-temporal

Cited by 12 publications

References 9 publications

Human Verification System Based on Gait Recognition using Active Horizontal Levels (AHL) Feature

Human Verification System Based on Gait Recognition using Active Horizontal Levels (AHL) Feature

Occlusion detection and gait silhouette reconstruction from degraded scenes

New Advances in Automatic Gait Recognition

Contact Info

Product

Resources

About