Improved gait recognition through gait energy image partitioning

Recently, human gait pattern has turned into an essential biometric feature to recognize an individual remotely. Gait as a feature becomes challenging owing to variation in appearance under different covariate conditions (eg, shoe, surface, haul, viewpoint and attire). The covariates may alter few fragment of gait while other fragment stay unaltered, leading to lower the probability of correct identification. To overcome such variation, an improved gait recognition strategy is proposed in this article by gait energy image partitioning and selection processing. Our method involves pre-processing of raw video for silhouette extraction, gait cycle detection, segmentation into different regions, and histogram of gradients feature extraction from selected segments. In this way, the specific features across complete gait cycles are extracted precisely. Finally, recognition is done by using K-NN. The proposed strategy has been assessed using the CASIA B gait database. Our outcomes shows a particular proposed strategy accomplishes high recognition rate and outperforms the advanced gait recognition mechanism.     

基于时间保持能量图和Radon变换的步态识别

Radon变换把图像从坐标空间映射到Radon空间,因其可以保存频率信息而被应用在步态识别算法中。主要从频率角度入手,着力提高基于Radon变换的步态识别算法的识别正确率,提出了基于时间保持能量图的Radon变换步态识别算法。传统的步态能量图是对步态周期中经过归一化的人体轮廓图求算术平均而得到的步态特征表示,最近提出的时间保持能量图在保持步态能量图的优点的基础上,保留了步态序列的时间信息,在改进的步态周期检测算法的基础上,提出将时间保持能量图和Radon变换结合到一起的步态识别算法。也对结合不同数据空间的特征如频率、形状等做了初步探讨。     

傅里叶变换的多视角步态识别

步态识别作为一种全新的生物特征识别技术,通过人走路的姿势实现对个人身份的识别和认证。步态能量图将一个周期的步态组合在一起,增强了各帧的相关性,减少了噪声的干扰。对步态能量图进行傅里叶变换,利用傅里叶变换的低频分量对多个视角的步态进行识别。在CASIA数据库中进行实验,结果表明算法简单快速,取得了较好的识别效果。     

A noise robust gait representation: Motion energy image

Gait-based human identification aims to discriminate individuals by the way they walk. A unique advantage of gait as a biometric is that it requires no subject contact and is easily acquired at a distance, which stands in contrast to other biometric techniques involving face, fingerprints, iris, etc. This paper proposes a new gait representation called motion energy image (MEI). Compared with other gait features, MEI is more robust against noise that can be included in binary gait silhouette images due to various factors. The effectiveness of the proposed method for gait recognition is demonstrated using experiments performed on the NLPR database. Recommended by Editorial Board member Jang Myung Lee under the direction of Editor Jae-Bok Song. This work was supported by the Korea Science and Engineering Foundation (KOSEF) through the Biometrics Engineering Research Center (BERC) at Yonsei University. Grant Number: R11-2002-105-09002-0 (2009). Heesung Lee received the B.S. and M.S. degrees in Electrical and Electronic Engineering, from Yonsei University, Seoul, Korea, in 2003 and 2005, respectively. He is currently a Ph.D. candidate of Dept. of Electrical and Electronic Engineering at Yonsei University. His current research interests include computational intelligence, pattern recognition, biometrics, and neural network. Sungjun Hong received the B.S. degrees in Electrical and Electronic Engineering and Computer Science, from Yonsei University, Seoul, Korea, in 2005. He is a graduate student of the combined master’s and doctoral degree programs at Yonsei University. He has studied machine learning, biometrics and optimization Imran Fareed Nizami received the B.S. degree from University of Engg. & Tech. Taxila, Pakistan and the M.S. degree in the Electrical and Electronic Engineering from Yonsei University, Seoul, Korea. He is currently a senior lecturer in Bahria University, Islamabad, Pakistan. His research interests include biometrics, gait recognition, Bayesian and neural networks. Euntai Kim received the B.S. (with top honors), M.S. and Ph.D. degrees in Electronic Engineering from Yonsei University, Seoul, Korea, in 1992, 1994, and 1999, respectively. From 1999 to 2002, he was a Full-time Lecturer with the Department of Control and Instrumentation Engineering at Hankyong National University, Gyeonggi-do, Korea. Since 2002, he has been with the School of Electrical and Electronic Engineering at Yonsei University, where he is currently an associate professor. He was a Visiting Scholar with the University of Alberta, Edmonton, Canada, and the Berkeley Initiative in Soft Computing (BISC), UC Berkeley, USA, in 2003 and 2008, respectively. His current research interests include computational intelligence and machine learning and their application to intelligent service robots, unmanned vehicles, home networks, biometrics, and evolvable hardware.     

用侧影特征分析和识别人的异常步态

基于计算机视觉的步态分析是计算机视觉领域的研究热点。目前的研究大多集中在通过对正常步态的分析实现身份识别,而通过异常步态分析来识别人的异常状况方面的研究却很少。提出了一种简单有效的基于计算机视觉的异常步态识别方法,通过人的宽高比提取反应步态特征的特征向量,然后用支持向量机进行异常步态的识别。实验结果表明了该方法的有效性。     

Model-based human gait recognition using leg and arm movements

We have presented a model-based approach for human gait recognition, which is based on analyzing the leg and arm movements. An initial model is created based on anatomical proportions, and a posterior model is constructed upon the movements of the articulated parts of the body, using active contour models and the Hough transform. Fourier analysis is used to describe the motion patterns of the moving parts. The k-nearest neighbor rule applied to the phase-weighted Fourier magnitude of each segment’s spectrum is used for classification. In contrast to the existing approaches, the main focus of this paper is on increasing the discrimination capability of the model through extra features produced from the motion of the arms. Experimental results indicate good performance of the proposed method. The technique has also proved to be able to reduce the adverse effects of self-occlusion, which is a common incident in human walking.     

Human gait recognition using GEI-based local multi-scale feature descriptors

Multimedia Tools and Applications - Human gait recognition is a biometric technique for persons identification based on their walking manner. This paper proposes a novel gait recognition approach...     

基于步态能量图的KPCA和SVM的步态识别方法

采用了一种基于步态能量图（GEI）的步态特征提取方法,主要是通过得到的步态侧影图像进行规格化并进行周期分析,然后提取其步态能量图。同时针对传统主成分分析（PCA）方法只能处理线性和服从指数型分布的情况,提出了采用基于核方法的主成分分析（KPCA）来对数据进行特征降维,然后采用泛化能力较强的分类器SVM来对特征进行识别。应用上述方法在CASIA数据库上进行了实验,结果表明采用上述方法取得了较理想的效果。     

A cascade fusion scheme for gait and cumulative foot pressure image recognition

Cumulative foot pressure images represent the 2D ground reaction force during one gait cycle. Biomedical and forensic studies show that humans can be distinguished by unique limb movement patterns and ground reaction force. Considering continuous gait pose images and corresponding cumulative foot pressure images, this paper presents a cascade fusion scheme to represent the potential connections between them and proposes a two-modality fusion based recognition system. The proposed scheme contains two stages: (1) given cumulative foot pressure images, canonical correlation analysis is employed to retrieve corresponding gait pose image candidates in gallery dataset; (2) pedestrian recognition is achieved via small samples matching between retrieved gait pose images and unlabeled ones. The proposed fusion recognition system is not only insensitive to slight changes of environment and the individual users, but also can be extended to multiple biometrics retrieval. Experimental results are conducted on the CASIA gait–footprint dataset, which contains cumulative foot pressure images and its corresponding gait pose image sequence from 88 subjects. Evaluation results suggest the effectiveness of the proposed scheme compared to other related approaches.     

Improved gait recognition by gait dynamics normalization

Potential sources for gait biometrics can be seen to derive from two aspects: gait shape and gait dynamics. We show that improved gait recognition can be achieved after normalization of dynamics and focusing on the shape information. We normalize for gait dynamics using a generic walking model, as captured by a population Hidden Markov Model (pHMM) defined for a set of individuals. The states of this pHMM represent gait stances over one gait cycle and the observations are the silhouettes of the corresponding gait stances. For each sequence, we first use Viterbi decoding of the gait dynamics to arrive at one dynamics-normalized, averaged, gait cycle of fixed length. The distance between two sequences is the distance between the two corresponding dynamics-normalized gait cycles, which we quantify by the sum of the distances between the corresponding gait stances. Distances between two silhouettes from the same generic gait stance are computed in the linear discriminant analysis space so as to maximize the discrimination between persons, while minimizing the variations of the same subject under different conditions. The distance computation is constructed so that it is invariant to dilations and erosions of the silhouettes. This helps us handle variations in silhouette shape that can occur with changing imaging conditions. We present results on three different, publicly available, data sets. First, we consider the HumanlD Gait Challenge data set, which is the largest gait benchmarking data set that is available (122 subjects), exercising five different factors, i.e., viewpoint, shoe, surface, carrying condition, and time. We significantly improve the performance across the hard experiments involving surface change and briefcase carrying conditions. Second, we also show improved performance on the UMD gait data set that exercises time variations for 55 subjects. Third, on the CMU Mobo data set, we show results for matching across different walking speeds. It is worth noting that there was no separate training for the UMD and CMU data sets.     

Clothing-invariant human gait recognition using an adaptive outlier detection method

Multimedia Tools and Applications - Human gait as a behavioral biometric identifier has received much attention in recent years. But there are some challenges which hinder using this biometric in...     

Intelligent control of a prosthetic ankle joint using gait recognition

Desire for better prosthetic feet for below-knee amputees has motivated the development of several active and highly functional devices. These devices are equipped with controlled actuators in order to replicate biomechanical characteristics of the human ankle, improve the amputee gait, and reduce the amount of metabolic energy consumed during locomotion. However, the functioning of such devices on human subjects is difficult to test due to changing gait, unknown ankle dynamics, complicated interaction between the foot and the ground, as well as between the residual limb and the prosthesis. Commonly used approaches in control of prosthetic feet treat these effects as disturbances and ignore them, thereby degrading the performance and efficiency of the devices. In this paper, an artificial neural network-based hierarchical controller is proposed that first recognizes the amputees' intent from the actual measured gait data, then selects a displacement profile for the prosthetic joint based on the amputees' intent, and then adaptively compensates for the unmodeled dynamics and disturbances for closed loop stability with guaranteed tracking performance. Detailed theoretical analysis is carried out to establish the stability and robustness of the proposed approach. The performance of the controller presented in this paper is demonstrated using actual gait data collected from human subjects. Numerical simulations are used to demonstrate the advantages of the proposed strategy over conventional approaches to the control of the prosthetic ankle, especially when the presence of noise, uncertainty in terrain interaction, disturbance torques, variations in gait parameters, and changes in gait are considered.     

利用图像校正的快速目标识别算法

提出了一种基于图像校正的快速目标识别算法,特别适合于航拍照片中地面上面目标的识别。算法可以使目标模型单一化,在很大程度上克服了目标识别模型复杂、数据运算量大、计算实时性差等缺点,提高了目标识别的实时性和精确性。首先对图像进行感兴趣区域的检测;对检测出的区域进行图像的正视校正;然后对校正后的区域进行特征提取;最后进行目标识别,并输出目标信息,完成识别过程。实验表明,该算法用于大倾角航片目标识别是有发展潜力和前途的。     

Human gait recognition using extraction and fusion of global motion features

This paper proposes a novel computer vision approach that processes video sequences of people walking and then recognises those people by their gait. Human motion carries different information that can be analysed in various ways. The skeleton carries motion information about human joints, and the silhouette carries information about boundary motion of the human body. Moreover, binary and gray-level images contain different information about human movements. This work proposes to recover these different kinds of information to interpret the global motion of the human body based on four different segmented image models, using a fusion model to improve classification. Our proposed method considers the set of the segmented frames of each individual as a distinct class and each frame as an object of this class. The methodology applies background extraction using the Gaussian Mixture Model (GMM), a scale reduction based on the Wavelet Transform (WT) and feature extraction by Principal Component Analysis (PCA). We propose four new schemas for motion information capture: the Silhouette-Gray-Wavelet model (SGW) captures motion based on grey level variations; the Silhouette-Binary-Wavelet model (SBW) captures motion based on binary information; the Silhouette–Edge-Binary model (SEW) captures motion based on edge information and the Silhouette Skeleton Wavelet model (SSW) captures motion based on skeleton movement. The classification rates obtained separately from these four different models are then merged using a new proposed fusion technique. The results suggest excellent performance in terms of recognising people by their gait.     

多部位特征增强的步态识别算法

目的 基于步态剪影的方法取得了很大的性能提升,其中通过水平划分骨干网络的输出从而学习多身体部位特征的机制起到了重要作用。然而在这些方法对不同部位的特征都是以相对独立的方式进行提取,不同部位之间缺乏交互,有碍于识别准确率的进一步提高。针对这一问题,本文提出了一个新模块用于增强步态识别中的多部位特征学习。方法 本文将“分离—共享”机制引入到步态识别的多部位特征学习过程中。分离机制允许每个部位学习自身独有的特征,主要通过区域池化和独立权重的全连接层进行实现。共享机制允许不同部位的特征进行交互,由特征归一化和特征重映射两部分组成。在共享机制中,特征归一化不包含任何参数,目的是使不同部位的特征具有相似的统计特性以便进行权值共享;特征重映射则是通过全连接层或逐项乘积进行实现,并且在不同部位之间共享权重。结果 实验在步态识别领域应用最广泛的数据集CASIA-B(Institute of Automation, Chinese Academy of Sciences)和OUMVLP上进行,分别以GaitSet和GaitPart作为基线方法。实验结果表明,本文设计的模块能够带来稳定的性能提升。在CASI...     

Handwritten Chinese character recognition using fuzzy image alignment

The task of handwritten Chinese character recognition is one of the most challenging areas of human handwriting classification. The main reason for this is related to the writing system itself which encompasses thousands of characters, coupled with high levels of diversity in personal writing styles and attributes. Much of the existing work for both online and off-line handwritten Chinese character recognition has focused on methods which employ feature extraction and segmentation steps. The preprocessed data from these steps form the basis for the subsequent classification and recognition phases. This paper proposes an approach for handwritten Chinese character recognition and classification using only an image alignment technique and does not require the aforementioned steps. Rather than extracting features from the image, which often means building models from very large training data, the proposed method instead uses the mean image transformations as a basis for model building. The use of an image-only model means that no subjective tuning of the feature extraction is required. In addition by employing a fuzzy-entropy-based metric, the work also entails improved ability to model different types of uncertainty. The classifier is a simple distance-based nearest neighbour classification system based on template matching. The approach is applied to a publicly available real-world database of handwritten Chinese characters and demonstrates that it can achieve high classification accuracy and is robust in the presence of noise.     

Invariant pattern recognition using multiple filter image representations

In this paper we develop a 4-dimensional representation for patterns based on image decompositions via orientation- and size-specific filters. By retaining image positional information, this encoding scheme reduces pattern rotations, translations, and scale changes to shifts in the filter outputs. The appropriate correlation processes for matching are discussed and the recognition system is illustrated by a number of examples.     

Pattern recognition in image processing using interpixel correlation

When within-object interpixel correlation varies appreciably from object to object, it may be important for the classifier to utilize this correlation, as well as the mean and variance of pixel intensities. In this correspondence interpixel correlation is brought into the classification scheme by means of a two-dimensional Markov model.