Performance analysis for automated gait extraction and recognition in multi-camera surveillance

Many studies have confirmed that gait analysis can be used as a new biometrics. In this research, gait analysis is deployed for people identification in multi-camera surveillance scenarios. We present a new method for viewpoint independent markerless gait analysis that does not require camera calibration and works with a wide range of walking directions. These properties make the proposed method particularly suitable for gait identification in real surveillance scenarios where people and their behaviour need to be tracked across a set of cameras. Tests on 300 synthetic and real video sequences, with subjects walking freely along different walking directions, have been performed. Since the choice of the cameras’ characteristics is a key-point for the development of a smart surveillance system, the performance of the proposed approach is measured with respect to different video properties: spatial resolution, frame-rate, data compression and image quality. The obtained results show that markerless gait analysis can be achieved without any knowledge of camera’s position and subject’s pose. The extracted gait parameters allow recognition of people walking from different views with a mean recognition rate of 92.2% and confirm that gait can be effectively used for subjects’ identification in a multi-camera surveillance scenario.     

基于步态特征提取的ELM身份识别方法

利用步态信息进行身份识别是一种新兴的生物识别技术.相较于其他的生物识别技术,其具有不易伪装、可在远距离情况下进行身份识别的优点.现有模型的识别方法计算量大、模型难以准确建立;现有的分类方法普遍存在训练时间长、分类准确率不高的问题.针对以上问题,对步态视频进行分帧处理,将分帧后的图像进行运动目标检测、形态学处理和图像归一...     

Integrating face and gait for human recognition at a distance in video.

This paper introduces a new video-based recognition method to recognize noncooperating individuals at a distance in video who expose side views to the camera. Information from two biometrics sources, side face and gait, is utilized and integrated for recognition. For side face, an enhanced side-face image (ESFI), a higher resolution image compared with the image directly obtained from a single video frame, is constructed, which integrates face information from multiple video frames. For gait, the gait energy image (GEI), a spatio-temporal compact representation of gait in video, is used to characterize human-walking properties. The features of face and gait are obtained separately using the principal component analysis and multiple discriminant analysis combined method from ESFI and GEI, respectively. They are then integrated at the match score level by using different fusion strategies. The approach is tested on a database of video sequences, corresponding to 45 people, which are collected over seven months. The different fusion methods are compared and analyzed. The experimental results show that: 1) the idea of constructing ESFI from multiple frames is promising for human recognition in video, and better face features are extracted from ESFI compared to those from the original side-face images (OSFIs); 2) the synchronization of face and gait is not necessary for face template ESFI and gait template GEI; the synthetic match scores combine information from them; and 3) an integrated information from side face and gait is effective for human recognition in video.     

一种基于人体轮廓宽度特征的步态识别方法

步态识别是一种新的生物识别技术,它通过人行走的姿势来实现对人身份的鉴别。提出了一种新的基于人体轮廓宽度特征的步态识别方法,将视频序列中检测出的步态轮廓提取三种宽度特征并计算步态序列中宽度的变化特征,从而构成描述步态序列的特征向量。实验表明提出的方法具有较好的识别性能,是一种有效的步态识别方法。     

Performing content-based retrieval of humans using gait biometrics

In order to analyse surveillance video, we need to efficiently explore large datasets containing videos of walking humans. Effective analysis of such data relies on retrieval of video data which has been enriched using semantic annotations. A manual annotation process is time-consuming and prone to error due to subject bias however, at surveillance-image resolution, the human walk (their gait) can be analysed automatically. We explore the content-based retrieval of videos containing walking subjects, using semantic queries. We evaluate current research in gait biometrics, unique in its effectiveness at recognising people at a distance. We introduce a set of semantic traits discernible by humans at a distance, outlining their psychological validity. Working under the premise that similarity of the chosen gait signature implies similarity of certain semantic traits we perform a set of semantic retrieval experiments using popular Latent Semantic Analysis techniques. We perform experiments on a dataset of 2000 videos of people walking in laboratory conditions and achieve promising retrieval results for features such as Sex (mAP  =  14% above random), Age (mAP  =  10% above random) and Ethnicity (mAP  =  9% above random).     

一种基于多区域不变矩的步态识别方法

步态识别是一种新的生物识别技术，它通过人行走的姿势来实现对人身份的鉴别。本文提出了一种基于多区域不变矩的步态识别方法，将视频序列中检测出的步态侧影分为五个子区域，提取每个子区域的不变矩特征并计算步态序列中不变矩的变化特征，从而构成描述步态序列的特征向量。最后的实验表明，提出的方法具有较好的识别性能，是一种有效的步态识别方法。     

步态识别研究进展

近年来步态识别技术已经成为生物特征识别领域一个新的研究热点。该技术是唯一可在远距离非接触状态下识别生物特征的技术,因此引起了各国学术科研机构的重视。对步态识别系统的一般处理过程进行了综述,重点分析和跟踪了步态特征提取技术的最新研究进展,讨论了各种方法中典型技术的优缺点和步态识别技术所面临的挑战,并概括介绍了常用的步态评测数据库和实验结果,最后展望了步态识别技术未来的发展方向和趋势。     

基于步态的人身份识别技术综述

由于不同的人在身体结构和运动行为方面存在广泛的不同性,步态为人的身份识别提供了独特的线索。对于近年来日益受到普遍重视的基于步态生物特征的人身份识别专题进行了较为详尽的综述,分析了目前所取得的主要成果及其特点,并指出了存在的难题和未来的发展趋势。     

Towards automated visual surveillance using gait for identity recognition and tracking across multiple non-intersecting cameras

Despite the fact that personal privacy has become a major concern, surveillance technology is now becoming ubiquitous in modern society. This is mainly due to the increasing number of crimes as well as the essential necessity to provide secure and safer environment. Recent research studies have confirmed now the possibility of recognizing people by the way they walk i.e. gait. The aim of this research study is to investigate the use of gait for people detection as well as identification across different cameras. We present a new approach for people tracking and identification between different non-intersecting un-calibrated stationary cameras based on gait analysis. A vision-based markerless extraction method is being deployed for the derivation of gait kinematics as well as anthropometric measurements in order to produce a gait signature. The novelty of our approach is motivated by the recent research in biometrics and forensic analysis using gait. The experimental results affirmed the robustness of our approach to successfully detect walking people as well as its potency to extract gait features for different camera viewpoints achieving an identity recognition rate of 73.6 % processed for 2270 video sequences. Furthermore, experimental results confirmed the potential of the proposed method for identity tracking in real surveillance systems to recognize walking individuals across different views with an average recognition rate of 92.5 % for cross-camera matching for two different non-overlapping views.     

步态表征和步态融合方法新进展

作为可远距离感知的生物特征识别技术之一,步态识别受到越来越多的关注.有效的步态表征方法是步态识别的关键,信息融合是提高步态识别性能的重要手段.从步态表征方法和信息融合方法两方面总结了步态识别技术的最新进展;对步态表征方法做了详细的总结;从多特征融合、多视角融合和多模态生物特征融合3个方面归纳了融合在步态识别方面的发展.在此基础上,分析了步态识别的发展趋势.     

Gait-based person identification using 3D LiDAR and long short-term memory deep networks

Gait recognition is one measure of biometrics, which also includes facial, fingerprint, and retina recognition. Although most biometric methods require direct contact between a device and a subject, gait recognition has unique characteristics whereby interaction with the subjects is not required and can be performed from a distance. Cameras are commonly used for gait recognition, and a number of researchers have used depth information obtained using an RGB-D camera, such as the Microsoft Kinect. Although depth-based gait recognition has advantages, such as robustness against light conditions or appearance variations, there are also limitations. For instance, the RGB-D camera cannot be used outdoors and the measurement distance is limited to approximately 10 meters. The present paper describes a long short-term memory-based method for gait recognition using a real-time multi-line LiDAR. Very few studies have dealt with LiDAR-based gait recognition, and the present study is the first attempt that combines LiDAR data and long short-term memory for gait recognition and focuses on dealing with different appearances. We collect the first gait recognition dataset that consists of time-series range data for 30 people with clothing variations and show the effectiveness of the proposed approach.     

基于LBP统计特征的低分辨率安全帽识别

针对工地进出口的视频监控录像,考虑远距离低分辨率安全帽识别问题,探讨了低分辨率安全帽识别方法,分析了提取不同的特征和应用不同的分类器与识别率的关系.首先截取视频中的人头,获得大小为22*22的图像,然后分别提取图像的统计特征、局部二进制模式特征、快速主成分分析特征,再利用分类器和反向人工神经网络进行分类预测,最后计算测试样本的识别率.实验结果表明,提取图像的二进制模式统计特征,再结合反向人工神经网络的识别率效果最佳,识别率可达87.27%.     

视频人脸识别进展综述

人脸识别是生物特征识别领域的一项关键技术,长期以来得到研究者的广泛关注。视频人脸识别任务特指从一段视频中提取出人脸的关键信息,从而完成身份识别。相较于基于图像的人脸识别任务来说,视频数据中的人脸变化模式更为多样且视频帧之间存在较大差异,如何从冗长而复杂的视频中抽取到人脸的关键特征成为当前的研究重点。以视频人脸识别技术为研究对象,首先介绍了该技术的研究价值和存在的挑战;接着对当前研究工作的发展脉络进行了系统的梳理,依据建模方式将传统基于图像集合建模的方法分为线性子空间建模、仿射子空间建模、非线性流形建模、统计建模四大类,同时对深度学习背景下基于图像融合的方法进行了介绍;另外对现有视频人脸识别数据集进行分类整理并简要介绍了常用的评价指标;最后分别采用灰度特征和深度特征在YTC数据集及IJB-A数据集上对代表性工作进行评测。实验结果表明:神经网络可以从大规模数据中提取到鲁棒的视频帧特征,从而带来识别性能的大幅提升,而有效的视频数据建模能够挖掘出人脸潜在的变化模式,从视频序列包含的大量样本中找到更具判别力的关键信息,排除噪声样本的干扰,因此基于视频的人脸识别具有广泛的通用性和实用价值。     

基于脸部和步态特征融合的身份识别

提出了一种将脸部和步态特征相结合,应用于智能监控系统进行远距离视频流中身份识别的新方法.该方法首先分别采用隐马尔可夫模型(HMM)和Fisherfaces方法进行步态和脸部的识别,之后将这两个分类器得到的结果进行匹配级的融合.对从不同方向采集的31个人的视频序列进行分析实验,结果表明将脸部和步态特征相结合进行身份识别具有很好的鲁棒性,其识别性能也优于只采用脸部或步态单一特征的识别方法.     

Feature fusion of side face and gait for video-based human identification

Video-based human recognition at a distance remains a challenging problem for the fusion of multimodal biometrics. As compared to the approach based on match score level fusion, in this paper, we present a new approach that utilizes and integrates information from side face and gait at the feature level. The features of face and gait are obtained separately using principal component analysis (PCA) from enhanced side face image (ESFI) and gait energy image (GEI), respectively. Multiple discriminant analysis (MDA) is employed on the concatenated features of face and gait to obtain discriminating synthetic features. This process allows the generation of better features and reduces the curse of dimensionality. The proposed scheme is tested using two comparative data sets to show the effect of changing clothes and face changing over time. Moreover, the proposed feature level fusion is compared with the match score level fusion and another feature level fusion scheme. The experimental results demonstrate that the synthetic features, encoding both side face and gait information, carry more discriminating power than the individual biometrics features, and the proposed feature level fusion scheme outperforms the match score level and another feature level fusion scheme. The performance of different fusion schemes is also shown as cumulative match characteristic (CMC) curves. They further demonstrate the strength of the proposed fusion scheme.     

动静态信息融合及动态贝叶斯网络的步态识别

步态是远距离视频监控领域最具潜力的生物特征。目前对步态的识别研究大都是考虑单一条件下步态的识别率,但在穿外套、背包等混合条件下识别率较低,通过分析人体行走时步态的时序特征,提出一种基于动静态信息相结合的多信息融合的动态贝叶斯网络(DSIF-DBN)。模型含有3层状态,模型中每个时间片都为静态信息和动态信息的融合。此模型能很好地表达步态的时序特性,即步态行走时人体姿态,运动幅度等特征的节奏性变化。实验结果表明该方法有较高的识别率,能有机地融合步态的静态信息及动态信息,并且在有噪声及信息缺失的情况下有较好的鲁棒性,大大降低了外套及背包对步态识别的影响。     

基于视频残差神经网络的深度步态识别

步态识别是根据人体的行走方式进行身份识别. 目前, 大多数步态识别方法通过浅层神经网络进行特征提取, 在室内步态数据集表现良好, 然而在近年新公布的室外步态数据集中性能表现不佳. 为了解决室外步态数据集带来的严峻挑战, 提出了一种基于视频残差神经网络的深度步态识别模型. 在特征提取阶段, 基于提出的视频残差块构建深层3D卷积神经网络(3D CNN), 提取整个步态序列的时空动力学特征; 然后, 引入时序池化和水平金字塔映射降低采样特征分辨率并提取局部步态特征; 使用联合损失函数驱动训练过程, 最后通过BNNeck平衡损失函数并调整特征空间. 实验分别在公开的室内 (CASIA-B)、室外(GREW、Gait3D)这3个步态数据集上进行. 实验结果表明, 该模型在室外步态数据集中的准确率以及收敛速度优于其他模型.     

基于生成对抗网络的跨视角步态特征提取

步态是一种能够在远距离、非侵犯的条件下识别身份的生物特征,但在实际场景中,步态很容易受到拍摄视角、行走环境、物体遮挡、着装等因素的影响.在跨视角识别问题上,现有方法只注重将多种视角的步态模板转化到固定视角下,且视角跨度的增大加深了错误的累积.为了提取有效的步态特征用于跨视角步态识别,本文提出了一种基于生成对抗网络的跨视角步态特征提取方法,该方法只需训练一个模型即可将步态模板转换到任意视角下的正常行走状态,并最大化地保留原本的身份特征信息,从而提高步态识别的准确率.在CASIA-B和OUMVLP数据集上的实验结果表明,该方法在解决跨视角步态识别问题上具有一定的鲁棒性和可行性.     

Cancellable biometrics and annotations on BioHash

Lately, the once powerful one-factor authentication which is based solely on either password, token or biometric approach, appears to be insufficient in addressing the challenges of identity frauds. For example, the sole biometric approach suffers from the privacy invasion and non-revocable issues. Passwords and tokens are easily forgotten and lost. To address these issues, the notion of cancellable biometrics was introduced to denote biometric templates that can be cancelled and replaced with the inclusion of another independent authentication factor. BioHash is a form of cancellable biometrics which mixes a set of user-specific random vectors with biometric features. In verification setting, BioHash is able to deliver extremely low error rates as compared to the sole biometric approach when a genuine token is used. However, this raises the possibility of two identity theft scenarios: (i) stolen-biometrics, in which an impostor possesses intercepted biometric data of sufficient high quality to be considered genuine and (ii) stolen-token, in which an impostor has access to the genuine token and used by the impostor to claim as the genuine user. We found that the recognition rate for the latter case is poorer. In this paper, the quantised random projection ensemble based on the Johnson–Lindenstrauss Lemma is used to establish the mathematical foundation of BioHash. Based on this model, we elucidate the characteristics of BioHash in pattern recognition as well as security view points and propose new methods to rectify the stolen-token problem.     

Robust Gait Recognition by Learning and Exploiting Sub-gait Characteristics

Gait recognition algorithms often perform poorly because of low resolution video sequences, subjective human motion and challenging outdoor scenarios. Despite these challenges, gait recognition research is gaining momentum due to increasing demand and more possibilities for deployment by the surveillance industry. Therefore every research contribution which significantly improves this new biometric is a milestone. We propose a probabilistic sub-gait interpretation model to recognize gaits. A sub-gait is defined by us as part of the silhouette of a moving body. Binary silhouettes of gait video sequences form the basic input of our approach. A novel modular training scheme has been introduced in this research to efficiently learn subtle sub-gait characteristics from the gait domain. For a given gait sequence, we get useful information from the sub-gaits by identifying and exploiting intrinsic relationships using Bayesian networks. Finally, by incorporating efficient inference strategies, robust decisions are made for recognizing gaits. Our results show that the proposed model tackles well the uncertainties imposed by typical covariate factors and shows significant recognition performance.