An Algorithm for Extracting Human Motion Signatures

We review methods for kinematic tracking of the human body in video. The review is part of a projected book that is intended to cross-fertilize ideas about motion representation between the animation and computer vision communities. The review confines itself to the earlier stages of motion, focusing on tracking and motion synthesis; future material will cover activity representation and motion generation. In general, we take the position that tracking does not necessarily involve (as is usually thought) complex multimodal inference problems. Instead, there are two key problems, both easy to state. The first is lifting, where one must infer the configuration of the body in three dimensions from image data. Ambiguities in lifting can result in multimodal inference problem, and we review what little is known about the extent to which a lift is ambiguous. The second is data association, where one must determine which pixels in an image

Behavior Research Methods

Human locomotion is a fundamental class of events, and manners of locomotion (e.g., how the limbs are used to achieve a change of location) are commonly encoded in language and gesture. To our knowledge, there is no openly accessible database containing normed human locomotion stimuli. Therefore, we introduce the GestuRe and ACtion Exemplar (GRACE) video database, which contains 676 videos of actors performing novel manners of human locomotion (i.e., moving from one location to another in an unusual manner) and videos of a female actor producing iconic gestures that represent these actions. The usefulness of the database was demonstrated across four norming experiments. First, our database contains clear matches and mismatches between iconic gesture videos and action videos. Second, the male actors and female actors whose action videos matched the gestures in the best possible way, perform the same actions in very similar manners and different actions in highly distinct manners.

This paper presents a framework for audio-driven human body motion analysis and synthesis. We address the problem in the context of a dance performance, where gestures and movements of the dancer are mainly driven by a musical piece and characterized by the repetition of a set of dance !gures. The system is trained in a supervised manner using the multiview video recordings of the dancer. The human body posture is extracted from multiview video information without any human intervention using a novel marker-based algorithm based on annealing particle !ltering. Audio is analyzed to extract beat and tempo information. The joint analysis of audio and motion features provides a correlation model that is then used to animate a dancing avatar when driven with any musical piece of the same genre. Results are provided showing the effectiveness of the proposed algorithm.

1998

Abstract This paper is concerned with the extraction of spatio-temporal patterns in video sequences with focus on trajectories of gestural motions associated with American Sign Language. An algorithm is described to extract the motion trajectories of salient features such as human palms from an image sequence. First, motion segmentation of the image sequence is generated based on a multiscale segmentation of the frames and attributed graph matching of regions across frames.

2008

A new method for extraction and temporal segmentation of multiple motion trajectories in human motion is presented. The proposed method extracts motion trajectories generated by body parts without any initialization or any assumption on color distribution. Motion trajectories are very compact and representative features for activity recognition.

Lecture Notes in Computer Science, 2002

We present a method for the synthesis of sequences of realistically looking human movements from learned example patterns. We apply this technique for the synthesis of dynamic facial expressions. Sequences of facial movements are decomposed into individual movement elements which are modeled by linear combinations of learned examples. The weights of the linear combinations define an abstract pattern space that

Lecture Notes in Computer Science, 2006

An appraisal of human motions and particular motion phases is essential for a good interaction between a human and a humanoid robot. We present a new method for the analysis of human motions and the classification of motion phases. The method allows an automatic composition of a motion model for a complex motion from several elementary models. The elementary models can be retrieved from a motion catalogue according to the requirements of a current motion processing task. The method is based on the analysis of the hidden states in a complex HMM and considers the context of all elementary phases in an entire motion sequence. The analysis of motion phases with the new model is computationally more efficient and yields better recognition rates than conventional motion analysis with HMMs and winner-takes-all strategy.

Computer Graphics Forum, 2004

While powerful, the simplest version of this approach is not particularly well suited to modeling the specific style of an individual whose motion had not yet been recorded when building the database: it would take an expert to adjust the PCA weights to obtain a motion style that is indistinguishable from his. Consequently, when realism is required, the current practice is to perform a full motion capture session each time a new person must be considered. In this paper, we extend the PCA approach so that this requirement can be drastically reduced: for whole classes of cyclic and noncyclic motions such as walking, running or jumping, it is enough to observe the newcomer moving only once at a particular speed or jumping a particular distance using either an optical motion capture system or a simple pair of synchronized video cameras. This one observation is used to compute a set of principal component weights that best approximates the motion and to extrapolate in real-time realistic animations of the same person walking or running at different speeds, and jumping a different distance.

ACM Transactions on Graphics, 2005

Style translation is the process of transforming an input motion into a new style while preserving its original content. This problem is motivated by the needs of interactive applications, which require rapid processing of captured performances. Our solution learns to translate by analyzing differences between performances of the same content in input and output styles. It relies on a novel correspondence algorithm to align motions, and a linear time-invariant model to represent stylistic differences. Once the model is estimated with system identification, our system is capable of translating streaming input with simple linear operations at each frame.

PLOS ONE

We present a novel framework for the automatic discovery and recognition of motion primitives in videos of human activities. Given the 3D pose of a human in a video, human motion primitives are discovered by optimizing the 'motion flux', a quantity which captures the motion variation of a group of skeletal joints. A normalization of the primitives is proposed in order to make them invariant with respect to a subject anatomical variations and data sampling rate. The discovered primitives are unknown and unlabeled and are unsupervisedly collected into classes via a hierarchical non-parametric Bayes mixture model. Once classes are determined and labeled they are further analyzed for establishing models for recognizing discovered primitives. Each primitive model is defined by a set of learned parameters. Given new video data and given the estimated pose of the subject appearing on the video, the motion is segmented into primitives, which are recognized with a probability given according to the parameters of the learned models. Using our framework we build a publicly available dataset of human motion primitives, using sequences taken from well-known motion capture datasets. We expect that our framework, by providing an objective way for discovering and categorizing human motion, will be a useful tool in numerous research fields including video analysis, human inspired motion generation, learning by demonstration, intuitive humanrobot interaction, and human behavior analysis.