Hybrid Dynamical Models of Human Motion for the Recognition of Human Gaits

Bissacco, Alessandro; Soatto, Stefano

doi:10.1007/s11263-009-0248-7

Cited by 28 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The descriptors are modeled by the Interval-based Hybrid Dynamical System (IHDS) method [23], [24] to describe the dynamics of block-based HOOF features. The IHDS scheme is extended from switching LDSs [28], [29] and hybrid dynamical systems [30], which have been demonstrated in human action recognition. Aside from finite state transitions represented in general switching LDSs (e.g., transitions between walking and jogging in [29]), the IHDS method models a temporal interval at each finite state.…”

Section: Dictionary Of Motion Primitives (Domp)mentioning

confidence: 99%

Natural Facial and Head Behavior Recognition using Dictionary of Motion Primitives

Shi

Ukita

Yang

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper proposes a natural facial and head behavior recognition method using hybrid dynamical systems. Most existing facial and head behavior recognition methods focus on analyzing deliberately displayed prototypical emotion patterns rather than complex and spontaneous facial and head behaviors in natural conversation environments. We first capture spatio-temporal features on important facial parts via dense feature extraction. Next, we cluster the spatio-temporal features using hybrid dynamical systems, and construct a dictionary of motion primitives to cover all possible elemental motion dynamics accounting for facial and head behaviors. With this dictionary, the facial and head behavior can be interpreted into a distribution of motion primitives. This interpretation is robust against different rhythms of dynamic patterns in complex and spontaneous facial and head behaviors. We evaluate the proposed approach under natural tele-communication scenarios, and achieve promising results. Furthermore, the proposed method also performs favorably against the state-ofthe-art methods on three benchmark databases.

show abstract

Section: Dictionary Of Motion Primitives (Domp)mentioning

confidence: 99%

Natural Facial and Head Behavior Recognition using Dictionary of Motion Primitives

Shi

Ukita

Yang

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…If it is assumed that every examinee can be modeled by the virtual physical model precisely, the joint trajectories generated by the model can replace the true examinee ideally. The generated data can be used to estimate different AR models by certain measurement (e.g., Wasserstein distance) [21]. However, in practical security applications, it is hard to measure all the examinees' physical parameters and to establish precise physical models.…”

Section: The Dynamics Of Virtual Passive Walking Modelmentioning

confidence: 99%

Velocity-Robust Gait Analysis for Human Identification through Constrained Learning of Stochastic Switched Auto-Regressive Model

Zhang

Inagaki

Suzuki

2013

SICE Journal of Control, Measurement, and System Integration

View full text Add to dashboard Cite

: Gait recognition is a promising non-intrusive biometric method. A robust and compact gait model is desirable in many security applications from public facilities to personal devices. Shape cues are chosen in most current researches except a few adopting dynamical features exclusively. And most of these systems are velocity-dependent. In order to explore more features of gait and to fit the varying environments of different applications, a new gait recognition model which synthesizes dynamic model and statistical one is designed. A kind of dynamical features, angular variables with respect to ankle joint, are adopted as the model's input. The proposed model has a circular structure consisted of 2 pairs of correlated states. A constrained learning algorithm is proposed under the model's special structure configured according to a 2-link virtual passive walking model which plays an important role both in the initialization and in the updating step. By evaluating the recognition rates of different models, the velocity-robust characteristics of the new model and its low computational load compared with conventional HMM are verified.

show abstract

“…State of the art in gait recognition is found in Bissacco and Soatto (2009), they proposed a hybrid dynamical model of human motion and developed a classification algorithm for the purpose of analysis and recognition. Motivated by the successes of the two-dimensional LDA, Tao et al (2007), developed a general tensor discriminant analysis (GTDA) as a preprocessing step for LDA and used human gait recognition to validate their proposed GTDA.…”

Section: Automatic Recognition Using Biometricsmentioning

confidence: 99%

Landmark Localisation in 3D Face Data

Romero

Pears

2009

2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance

View full text Add to dashboard Cite

Accurate landmark localisation is an essential precursor to many 3D face processing algorithms but, as yet, there is a lack of convincing solutions that work well over a wide range of head poses.In this thesis, an investigation to localise facial landmarks from 3D images is presented, without using any assumption concerning facial pose. In particular, this research devises new surface descriptors, which are derived from either unstructured face data, or a radial basis function (RBF) model of the facial surface.A ground-truth of eleven facial landmarks is collected over well-registered facial images in the Face Recognition Grand Challenge (FRGC) database. Then, a range of feature descriptors of varying complexity are investigated to illustrate repeatability and accuracy when computed for the full set of eleven facial landmarks. At this stage, the nose-tip and two inner-eye corners are observed as the most distinctive facial landmarks as a tradeoff among repeatability, accuracy, and complexity. Thus, this investigation focuses on the localisation of these three facial landmarks, which is the minimum number of landmarks necessary for pose normalisation.Two new families of descriptors are introduced, namely point-pair and point-triplet descriptors, which require two and three vertices respectively for their computation. Also, two facial landmark localisation methods are investigated; in the first, a binary decision tree is used to implement a cascade filter, in the second, graph matching is implemented via relaxation by elimination. Then, using all of these descriptors and algorithms, a number of systems are designed to localise the nose-tip and two inner-eye corners. Above all, 99.92% of nose-tip landmarks within an accuracy of 12 mm is the best localisation performance, which is achieved by one cascade filter system. Finally, landmark localisation performance is reported by using a novel cumulative error curve. Localisation results are gathered by computing errors of estimated landmark locations against respective ground-truth data.2

show abstract

Hybrid Dynamical Models of Human Motion for the Recognition of Human Gaits

Cited by 28 publications

References 33 publications

Natural Facial and Head Behavior Recognition using Dictionary of Motion Primitives

Natural Facial and Head Behavior Recognition using Dictionary of Motion Primitives

Velocity-Robust Gait Analysis for Human Identification through Constrained Learning of Stochastic Switched Auto-Regressive Model

Landmark Localisation in 3D Face Data

Contact Info

Product

Resources

About