Huazhong Ning

Silhouette analysis-based gait recognition for human identification

Human identification at a distance has recently gained growing interest from computer vision researchers. Gait recognition aims essentially to address this problem by identifying people based on the way they walk. In this paper, a simple but efficient gait recognition algorithm using spatial-temporal silhouette analysis is proposed. For each image sequence, a background subtraction algorithm and a simple correspondence procedure are first used to segment and track the moving silhouettes of a walking figure. Then, eigenspace transformation based on principal component analysis (PCA) is applied to time-varying distance signals derived from a sequence of silhouette images to reduce the dimensionality of the input feature space. Supervised pattern classification techniques are finally performed in the lower-dimensional eigenspace for recognition. This method implicitly captures the structural and transitional characteristics of gait. Extensive experimental results on outdoor image sequences demonstrate that the proposed algorithm has an encouraging recognition performance with relatively low computational cost.

Fusion of static and dynamic body biometrics for gait recognition

Vision-based human identification at a distance has recently gained growing interest from computer vision researchers. This paper describes a human recognition algorithm by combining static and dynamic body biometrics. For each sequence involving a walker, temporal pose changes of the segmented moving silhouettes are represented as an associated sequence of complex vector configurations and are then analyzed using the Procrustes shape analysis method to obtain a compact appearance representation, called static information of body. In addition, a model-based approach is presented under a Condensation framework to track the walker and to further recover joint-angle trajectories of lower limbs, called dynamic information of gait. Both static and dynamic cues obtained from walking video may be independently used for recognition using the nearest exemplar classifier. They are fused on the decision level using different combinations of rules to improve the performance of both identification and verification. Experimental results of a dataset including 20 subjects demonstrate the feasibility of the proposed algorithm.

Automatic gait recognition based on statistical shape analysis

Gait recognition has recently gained significant attention from computer vision researchers. This interest is strongly motivated by the need for automated person identification systems at a distance in visual surveillance and monitoring applications. The paper proposes a simple and efficient automatic gait recognition algorithm using statistical shape analysis. For each image sequence, an improved background subtraction procedure is used to extract moving silhouettes of a walking figure from the background. Temporal changes of the detected silhouettes are then represented as an associated sequence of complex vector configurations in a common coordinate frame, and are further analyzed using the Procrustes shape analysis method to obtain mean shape as gait signature. Supervised pattern classification techniques, based on the full Procrustes distance measure, are adopted for recognition. This method does not directly analyze the dynamics of gait, but implicitly uses the action of walking to capture the structural characteristics of gait, especially the shape cues of body biometrics. The algorithm is tested on a database consisting of 240 sequences from 20 different subjects walking at 3 viewing angles in an outdoor environment. Experimental results are included to demonstrate the encouraging performance of the proposed algorithm.

Incremental spectral clustering by efficiently updating the eigen-system

In recent years, the spectral clustering method has gained attentions because of its superior performance. To the best of our knowledge, the existing spectral clustering algorithms cannot incrementally update the clustering results given a small change of the data set. However, the capability of incrementally updating is essential to some applications such as websphere or blogsphere. Unlike the traditional stream data, these applications require incremental algorithms to handle not only insertion/deletion of data points but also similarity changes between existing points. In this paper, we extend the standard spectral clustering to such evolving data, by introducing the incidence vector/matrix to represent two kinds of dynamics in the same framework and by incrementally updating the eigen-system. Our incremental algorithm, initialized by a standard spectral clustering, continuously and efficiently updates the eigenvalue system and generates instant cluster labels, as the data set is evolving. The algorithm is applied to a blog data set. Compared with recomputation of the solution by the standard spectral clustering, it achieves similar accuracy but with much lower computational cost. It can discover not only the stable blog communities but also the evolution of the individual multi-topic blogs. The core technique of incrementally updating the eigenvalue system is a general algorithm and has a wide range of applications-as well as incremental spectral clustering-where dynamic graphs are involved. This demonstrates the wide applicability of our incremental algorithm.

Kinematics-based tracking of human walking in monocular video sequences

Human tracking is currently one of the most active research topics in computer vision. This paper proposed a kinematics-based approach to recovering motion parameters of people walking from monocular video sequences using robust image matching and hierarchical search. Tracking a human with unconstrained movements in monocular image sequences is extremely challenging. To reduce the search space, we design a hierarchical search strategy in a divide-and-conquer fashion according to the tree-like structure of the human body model. Then a kinematics-based algorithm is proposed to recursively refine the joint angles. To measure the matching error, we present a pose evaluation function combining both boundary and region information. We also address the issue of initialization by matching the first frame to six key poses acquired by clustering and the pose having minimal matching error is chosen as the initial pose. Experimental results in both indoor and outdoor scenes demonstrate that our approach performs well

Discriminative learning of visual words for 3D human pose estimation

This paper addresses the problem of recovering 3D human pose from a single monocular image, using a discriminative bag-of-words approach. In previous work, the visual words are learned by unsupervised clustering algorithms. They capture the most common patterns and are good features for coarse-grain recognition tasks like object classification. But for those tasks which deal with subtle differences such as pose estimation, such representation may lack the needed discriminative power. In this paper, we propose to jointly learn the visual words and the pose regressors in a supervised manner. More specifically, we learn an individual distance metric for each visual word to optimize the pose estimation performance. The learned metrics rescale the visual words to suppress unimportant dimensions such as those corresponding to background. Another contribution is that we design an appearance and position context (APC) local descriptor that achieves both selectivity and invariance while requiring no background subtraction. We test our approach on both a quasi-synthetic dataset and a real dataset (HumanEva) to verify its effectiveness. Our approach also achieves fast computational speed thanks to the integral histograms used in APC descriptor extraction and fast inference of pose regressors.

Gait recognition based on Procrustes shape analysis

Gait recognition has recently attracted increasing attention, especially in vision-based human identification-at-a-distance in visual surveillance. The paper proposes a simple but efficient gait recognition algorithm, based on statistical shape analysis. For each gait sequence, a background subtraction procedure is used to segment spatial silhouettes of the walking figures from the background. Static pose changes of these silhouettes over time are represented as a sequence of associated complex configurations in a common coordinate, and are then analyzed using the Procrustes shape analysis method to obtain a gait signature. The k-nearest neighbor classifier and the nearest exemplar classifier based on the full Procrustes distance measure are adopted for recognition. Experimental results demonstrate that the proposed algorithm has an encouraging recognition performance.

Hierarchical Space-Time Model Enabling Efficient Search for Human Actions

We propose a five-layer hierarchical space-time model (HSTM) for representing and searching human actions in videos. From a features point of view, both invariance and selectivity are desirable characteristics, which seem to contradict each other. To make these characteristics coexist, we introduce a coarse-to-fine search and verification scheme for action searching, based on the HSTM model. Because going through layers of the hierarchy corresponds to progressively turning the knob between invariance and selectivity, this strategy enables search for human actions ranging from rapid movements of sports to subtle motions of facial expressions. The introduction of the Histogram of Gabor Orientations feature makes the searching for actions go smoothly across the hierarchical layers of the HSTM model. The efficient matching is achieved by applying integral histograms to compute the features in the top two layers. The HSTM model was tested on three selected challenging video sequences and on the KTH human action database. And it achieved improvement over other state-of-the-art algorithms. These promising results validate that the HSTM model is both selective and robust for searching human actions.

People tracking based on motion model and motion constraints with automatic initialization

Human motion analysis is currently one of the most active research topics in computer vision. This paper presents a model-based approach to recovering motion parameters of walking people from monocular image sequences in a CONDENSATION framework. From the semi-automatically acquired training data, we learn a motion model represented as Gaussian distributions, and explore motion constraints by considering the dependency of motion parameters and represent them as conditional distributions. Then both of them are integrated into a dynamic model to concentrate factored sampling in the areas of the state-space with most posterior information. To measure the observation density with accuracy and robustness, a pose evaluation function (PEF) combining both boundary and region information is proposed. The function is modeled with a radial term to improve the efficiency of the factored sampling. We also address the issue of automatic acquisition of initial model pose and recovery from severe failures. A large number of experiments carried out in both indoor and outdoor scenes demonstrate that the proposed approach works well (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

Latent Pose Estimator for Continuous Action Recognition

Recently, models based on conditional random fields (CRF) have produced promising results on labeling sequential data in several scientific fields. However, in the vision task of continuous action recognition, the observations of visual features have dimensions as high as hundreds or even thousands. This might pose severe difficulties on parameter estimation and even degrade the performance. To bridge the gap between the high dimensional observations and the random fields, we propose a novel model that replace the observation layer of a traditional random fields model with a latent pose estimator. In training stage, the human pose is not observed in the action data, and the latent pose estimator is learned under the supervision of the labeled action data, instead of image-to-pose data. The advantage of this model is twofold. First, it learns to convert the high dimensional observations into more compact and informative representations. Second, it enables transfer learning to fully utilize the existing knowledge and data on image-to-pose relationship. The parameters of the latent pose estimator and the random fields are jointly optimized through a gradient ascent algorithm. Our approach is tested on HumanEva [1] --- a publicly available dataset. The experiments show that our approach can improve recognition accuracy over standard CRF model and its variations. The performance can be further significantly improved by using additional image-to-pose data for training. Our experiments also show that the model trained on HumanEva can generalize to different environment and human subjects.