Shiqi Yu

A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition

Gait recognition has gained increasing interest from researchers, but there is still no standard evaluation method to compare the performance of different gait recognition algorithms. In this paper, a framework is proposed in an attempt to tackle this problem. The framework consists of a large gait database, a large set of well designed experiments and some evaluation metrics. There are 124 subjects in the database, and the gait data was captured from 11 views. Three variations, namely view angle, clothing and carrying condition changes, are separately considered in the database. The database is one of the largest database among the existing databases. Three sets of experiments, including a total of 363 experiments, are designed in the framework. Some metrics are proposed to evaluate gait recognition algorithms

A Study on Gait-Based Gender Classification

Gender is an important cue in social activities. In this correspondence, we present a study and analysis of gender classification based on human gait. Psychological experiments were carried out. These experiments showed that humans can recognize gender based on gait information, and that contributions of different body components vary. The prior knowledge extracted from the psychological experiments can be combined with an automatic method to further improve classification accuracy. The proposed method which combines human knowledge achieves higher performance than some other methods, and is even more accurate than human observers. We also present a numerical analysis of the contributions of different human components, which shows that head and hair, back, chest and thigh are more discriminative than other components. We also did challenging cross-race experiments that used Asian gait data to classify the gender of Europeans, and vice versa. Encouraging results were obtained. All the above prove that gait-based gender classification is feasible in controlled environments. In real applications, it still suffers from many difficulties, such as view variation, clothing and shoes changes, or carrying objects. We analyze the difficulties and suggest some possible solutions.

Modelling the effect of view angle variation on appearance-based gait recognition

In recent years, many gait recognition algorithms have been developed, but most of them depend on a specific view angle. However, view angle variation is a significant factor among those that affect gait recognition performance. It is important to find the relationship between the performance and the view angle. In this paper, we discuss the effect of view angle variation on appearance-based gait recognition performance. A multi-view gait database (124 subjects and 11 view directions) is created for our research. We propose two models, a geometrical one and a mathematical one, to model the effect of view angle variation on appearance-based gait recognition. These models will be valuable for designing robust gait recognition systems.

Efficient Night Gait Recognition Based on Template Matching

Gait is a useful biometric which can be used to recognize people at a distance when other biometrics are incapable. However, most work on gait recognition has been visible spectrum-oriented over the past decade, ignoring recognition at night which is in reality demand-imperative. This paper deals with the problem of night gait recognition via thermal infrared imagery. First of all, human detection is accomplished, based on the Gaussian mixture modeling of the background. Then, human silhouettes are extracted on the basis of preceding detection results. Moreover, a new gait representation called HTI is proposed to characterize gait signatures for recognition. An infrared night gait database was built to provide a foundation for night gait recognition. Experimental results on two gait datasets show the effectiveness of this method

Gait analysis for human identification in frequency domain

In this paper, we analyze the spatio-temporal human characteristic of moving silhouettes in frequency domain, and find key Fourier descriptors that have better discriminatory capability for recognition than the other Fourier descriptors. A large number of experimental results and analysis show that the proposed algorithm based on the key Fourier descriptors can not only greatly reduce the gait data dimensionality, but also lighten the computation cost, with a satisfactory CCR. Besides that, classification performance can be further improved using feature fusion.

Uniprojective features for gait recognition

Recent studies have shown that shape cues should dominate gait recognition. This motivates us to perform gait recognition through shape features in 2D human silhouettes. In this paper, we propose six simple projective features to describe human gait and compare eight kinds of projective features to figure out which projective directions are important to walker recognition. First, we normalize each original human silhouette into a square form. Inspired by the pure horizontal and vertical projections used in the frieze gait patterns, we explore the positive and negative diagonal projections with or without normalizing silhouette projections and obtain six new uniprojective features to characterize walking gait. Then this paper applies principal component analysis (PCA) to reduce the dimension of raw gait features. Finally, we recognize unknown gait sequences using the Mahalanobis-distance-based nearest neighbor rule. Experimental results show that the horizontal and diagonal projections have more discriminative clues for the side-view gait recognition and that the projective normalization generally can improve the robustness of projective features against the noise in human silhouettes.

Reducing the effect of noise on human contour in gait recognition

Gait can be easily acquired at a distance, so it has become a popular biometric especially in intelligent visual surveillance. In gait-based human identification there are many factors that may degrade the performance, and noise on human contours is a significant one because to extract contours perfectly is a hard problem especially in a complex background. The contours extracted from video sequences are often polluted by noise. To improve the performance, we have to reduce the effect of noise. Different from the methods which use dynamic time warping (DTW) in previous work to match sequences in the time domain, a DTWbased contour similarity measure in the spatial domain is proposed to reduce the effect of noise. The experiments on a large gait database show the effectiveness of the proposed method.

Walker recognition without gait cycle estimation

Most of gait recognition algorithms involve walking cycle estimation to accomplish signature matching. However, we may be plagued by two cycle-related issues when developing real-time gait-based walker recognition systems. One is accurate cycle evaluation, which is computation intensive, and the other is the inconvenient acquisition of long continuous sequences of gait patterns, which are essential to the estimation of gait cycles. These drive us to address the problem of distant walker recognition from another view toward gait, in the hope of detouring the step of gait cycle estimation. This paper proposes a new gait representation, called normalized dual-diagonal projections (NDDP), to characterize walker signatures and employs a normal distribution to approximately describe the variation of each subjects gait signatures in the statistical sense. We achieve the recognition of unknown gait features in a simplified Bayes framework after reducing the dimension of raw gait signatures based on linear subspace projections. Extensive experiments demonstrate that our method is effective and promising.

Recognizing Night Walkers Based on One Pseudoshape Representation of Gait

Gait is a promising biometric cue which can facilitate the recognition of human beings, particularly when other biometrics are unavailable. Existing work for gait recognition, however, lays more emphasis on the problem of daytime walker recognition and overlooks the significance of walker recognition at night. This paper deals with the problem of recognizing nighttime walkers. We take advantage of infrared gait patterns to accomplish this task: 1) Walker detection is improved using intensity compensation-based background subtraction; 2) pseudoshape-based features are proposed to describe gait patterns; 3) the dimension of gait features is reduced through the principal component analysis (PCA) and linear discriminant analysis (LDA) techniques; 4) temporal cues are exploited in the form of the relevant component analysis (RCA) learning; 5) the nearest neighbor classifier is used to recognize unknown gait. Experimental results justify the effectiveness of our method and show that our method has an encouraging potential for the application in surveillance systems.

SLTP: A Fast Descriptor for People Detection in Depth Images

This paper presents a new feature descriptor for real-time people detection in depth images. The shape cue in depth images can reduce negative impacts of variations of clothing, lighting conditions and the complexity of backgrounds. The proposed Simplified Local Ternary Patterns (SLTP) can take advantage of depth images to describe human body shape with low computational cost. To evaluate the SLTP feature, we establish a dataset with 7260 positive samples. A series of experiments are carried out on this dataset, and the results show that the SLTP feature can achieve a high detection rate with a low false positive rate. Besides, SLTP is easy to implement, and performs fast (over 80 frames per second) on a standard desktop computer.