Volker Krüger

Identification of humans using gait

We propose a view-based approach to recognize humans from their gait. Two different image features have been considered: the width of the outer contour of the binarized silhouette of the walking person and the entire binary silhouette itself. To obtain the observation vector from the image features, we employ two different methods. In the first method, referred to as the indirect approach, the high-dimensional image feature is transformed to a lower dimensional space by generating what we call the frame to exemplar (FED) distance. The FED vector captures both structural and dynamic traits of each individual. For compact and effective gait representation and recognition, the gait information in the FED vector sequences is captured in a hidden Markov model (HMM). In the second method, referred to as the direct approach, we work with the feature vector directly (as opposed to computing the FED) and train an HMM. We estimate the HMM parameters (specifically the observation probability B) based on the distance between the exemplars and the image features. In this way, we avoid learning high-dimensional probability density functions. The statistical nature of the HMM lends overall robustness to representation and recognition. The performance of the methods is illustrated using several databases.

Gait-based recognition of humans using continuous HMMs

Gait is a spatio-temporal phenomenon that typifies the motion characteristics of an individual. In this paper, we propose a view-based approach to recognize humans through gait. The width of the outer contour of the binarized silhouette of a walking person is chosen as the image feature. A set of stances or key frames that occur during the walk cycle of an individual is chosen. Euclidean distances of a given image from this stance set are computed and a lower-dimensional observation vector is generated. A continuous hidden Markov model (HMM) is trained using several such lower-dimensional vector sequences extracted from the video. This methodology serves to compactly capture structural and transitional features that are unique to an individual. The statistical nature of the HMM renders overall robustness to gait representation and recognition. The human identification performance of the proposed scheme is found to be quite good when tested in natural walking conditions.

The Meaning of Action: a review on action recognition and mapping

In this paper, we analyze the different approaches taken to date within the computer vision, robotics and artificial intelligence communities for the representation, recognition, synthesis and understanding of action. We deal with action at different levels of complexity and provide the reader with the necessary related literature references. We put the literature references further into context and outline a possible interpretation of action by taking into account the different aspects of action recognition, action synthesis and task-level planning.

Hierarchical wavelet networks for facial feature localization

We present a technique for facial feature localization using a two-level hierarchical wavelet network. The first level wavelet network is used for face matching, and yields an affine transformation used for a rough approximation of feature locations. Second level wavelet networks for each feature are then used to fine-tune the feature locations. Construction of a training database containing hierarchical wavelet networks of many faces allows features to be detected in most faces. Experiments show that facial feature localization benefits significantly from the hierarchical approach. Results compare favorably with existing techniques for feature localization.

Probabilistic recognition of human faces from video

Most present face recognition approaches recognize faces based on still images. We present a novel approach to recognize faces in video. In that scenario, the face gallery may consist of still images or may be derived from a videos. For evidence integration we use classical Bayesian propagation over time and compute the posterior distribution using sequential importance sampling. The probabilistic approach allows us to handle uncertainties in a systematic manner. Experimental results using videos collected by NIST/USF and CMU illustrate the effectiveness of this approach in both still-to-video and video-to-video scenarios with appropriate model choices.

Learning Actions from Observations

In the area of imitation learning, one of the important research problems is action representation. There has been a growing interest in expressing actions as a combination of meaningful subparts called action primitives. Action primitives could be thought of as elementary building blocks for action representation. In this article, we present a complete concept of learning action primitives to recognize and synthesize actions. One of the main novelties in this work is the detection of primitives in a unified framework, which takes into account objects and actions being applied to them. As the first major contribution, we propose an unsupervised learning approach for action primitives that make use of the human movements as well as object state changes. As the second major contribution, we propose using parametric hidden Markov models (PHMMs) for representing the discovered action primitives. PHMMs represent movement trajectories as a function of their desired effect on the object, and we will discuss 1) how these PHMMs can be trained in an unsupervised manner, 2) how they can be used for synthesizing movements to achieve a desired effect, and 3) how they can be used to recognize an action primitive and the effect from an observed acting human.

Gabor wavelet networks for efficient head pose estimation

In this paper, we first introduce the Gabor wavelet network (GWN) as a model-based approach for effective and efficient object representation. GWNs combine the advantages of the continuous wavelet transform with RBF networks. They have additional advantages such as invariance to some degree with respect to affine deformations. The use of Gabor filters enables the coding of geometrical and textural object features. Gabor filters as a model for local object features ensure considerable data reduction while at the same time allowing any desired precision of the object representation ranging from sparse to photo-realistic representation. As an application we present an approach for the estimation of head pose based on the GWNs. Feature information is encoded in the wavelet coefficients. An artificial neural network is then used to compute the head pose from the wavelet coefficients.

Visual Analysis of Humans

This unique text/reference provides a coherent and comprehensive overview of all aspects of video analysis of humans. Broad in coverage and accessible in style, the text presents original perspectives collected from preeminent researchers gathered from across the world. In addition to presenting state-of-the-art research, the book reviews the historical origins of the different existing methods, and predicts future trends and challenges. Features: with a Foreword by Professor Larry Davis; contains contributions from an international selection of leading authorities in the field; includes an extensive glossary; discusses the problems associated with detecting and tracking people through camera networks; examines topics related to determining the time-varying 3D pose of a person from video; investigates the representation and recognition of human and vehicular actions; reviews the most important applications of activity recognition, from biometrics and surveillance, to sports and driver assistance.

Single view motion tracking by depth and silhouette information

In this work1a combination of depth and silhouette information is presented to track the motion of a human from a single view. Depth data is acquired from a Photonic Mixer Device (PMD), which measures the time-of-flight of light. Correspondences between the silhouette of the projected model and the real image are established in a novel way, that can handle cluttered non-static backgrounds. Pose is estimated by Nonlinear Least Squares, which handles the underlying dynamics of the kinematic chain directly. Analytic Jacobians allow pose estimation with 5 FPS.

Exemplar-Based Face Recognition from Video

A new exemplar-based probabilistic approach for face recognition in video sequences is presented. The approach has two stages: First, Exemplars, which are selected representatives from the raw video, are automatically extracted from gallery videos. The exemplars are used to summarize the gallery video information. In the second part, exemplars are then used as centers for probabilistic mixture distributions for the tracking and recognition process. A particle method is used to compute the posteriori probabilities. Probabilistic methods are attractive in this context as they allow a systematic handling of uncertainty and an elegant way for fusing temporal information.Contrary to some previous video-based approaches, our approach is not limited to a certain image representation. It rather enhances known ones, such as the PCA, with temporal fusion and uncertainty handling. Experiments demonstrate the effectiveness of each of the two stages. We tested this approach on more than 100 training and testing sequences, with 25 different individuals.