Motion History Volumes for Free Viewpoint Action Recognition
HAL (Le Centre pour la Communication Scientifique Directe)Published 15 October 2005Open access
Daniel Weinland, Rémi Ronfard, Edmond Boyer
Citations47
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Preliminary results indicate that this MHV representation can be used to learn and recognize basic human action classes, independently of gender, body size and viewpoint.
Abstract
International audience
Keywords
Computer Science
IRE Transactions on Information TheoryVisual pattern recognition by moment invariants
7,528 Citations1962Ming-Kuei Hu
It is shown that recognition of geometrical patterns and alphabetical characters independently of position, size and orientation can be accomplished and it is indicated that generalization is possible to include invariance with parallel projection.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe recognition of human movement using temporal templates
2,784 Citations2001Aaron Bobick, James W. Davis
A view-based approach to the representation and recognition of human movement is presented, and a recognition method matching temporal templates against stored instances of views of known actions is developed.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe visual hull concept for silhouette-based image understanding
1,438 Citations1994Aldo Laurentini
This paper addresses the problem of finding which parts of a nonconvex object are relevant for silhouette-based image understanding and introduces the geometric concept of visual hull of a 3-D object, which is the maximal object silhouette-equivalent to S.
Recognizing action at a distance
1,240 Citations2003Alexei A. Efros, Berg +2 more
A novel motion descriptor based on optical flow measurements in a spatiotemporal volume for each stabilized human figure is introduced, and an associated similarity measure to be used in a nearest-neighbor framework is introduced.
Rotation invariant spherical harmonic representation of 3D shape descriptors
1,232 Citations2003Michael Kazhdan, Thomas Funkhouser +1 more
IEEE Transactions on Pattern Analysis and Machine IntelligenceRecognition of visual activities and interactions by stochastic parsing
648 Citations2000Yuri Ivanov, Aaron Bobick
A probabilistic syntactic approach to the detection and recognition of temporally extended activities and interactions between multiple agents and how the system correctly interprets activities of multiple interacting objects is demonstrated.
Actions Sketch: A Novel Action Representation
420 Citations2005Alper Yılmaz, Mubarak Shah
This paper proposes to model an action based on both the shape and the motion of the performing object, and generates STV by solving the point correspondence problem between consecutive frames using a two-step graph theoretical approach.
CognitionOn beyond Zebra: The relation of linguistic and visual information
407 Citations1987Ray Jackendoff
It is shown that there are substantial points of correspondence through which the encoding of physical objects and their locations and motions can be coordinated between these two levels of representation, and that both of these levels are deeply involved in visual as well as linguistic understanding.
International Journal of Computer VisionNatural Language Description of Human Activities from Video Images Based on Concept Hierarchy of Actions
356 Citations2002Atsuhiro Kojima, Takeshi Tamura +1 more
A method for describing human activities from video images based on concept hierarchies of actions based on semantic primitives, which demonstrates the performance of the proposed method by several experiments.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThree-Dimensional Moment Invariants
343 Citations1980Firooz A. Sadjadi, Ernest L. Hall
A set of three-dimensional moment invariants which are invariant under size, orientation, and position change is proposed which is highly significant in compressing the data which are needed in three- dimensional object recognition.
Recognizing Action at a Distance
338 Citations2003Alexei A. Efros, Alexander C. Berg +2 more
Pattern RecognitionDiscriminative wavelet shape descriptors for recognition of 2-D patterns
246 Citations1999Dinggang Shen, Horace H. S. Ip
The theoretical and experimental analyses prove that the proposed method has the ability to classify many types of image objects, and is particularly suitable for classifying seemingly similar objects with subtle di⁄erences.
IEEE Transactions on Pattern Analysis and Machine IntelligenceImage Normalization by Complex Moments
233 Citations1985Yaser S. Abu‐Mostafa, Demetri Psaltis
The role of moments in image normalization and invariant pattern recognition is addressed, and the relationship between moment-based normalization, moment invariants, and circular harmonics is established.
Proceedings of the Royal Society of London. Series B, Biological sciencesRepresentation and recognition of the movements of shapes
183 Citations1982David Marr, Lucia M. Vaina
A representation is proposed for the movements of shapes that lie within the scope of the Marr & Nishihara (1978) 3-D model representation of static shapes, called the state─motion─state (SMS) moving shape representation, and several examples of its application are given.
Hierarchical motion history images for recognizing human motion
168 Citations2002James W. Davis
A hierarchical extension to the original MHI framework to compute dense (local) motion flow directly from the MHI to address previous problems related to global analysis and limited recognition.
Recognizing action events from multiple viewpoints
92 Citations2002Tanveer Syeda-Mahmood, Andrei Vasilescu +1 more
This paper addresses the recognition of actions by taking a novel approach that models actions as special types of 3D objects, and observes that any action can be represented as a generalized cylinder, called the action cylinder.
Vision ResearchThe role of complex cells in object recognition
52 Citations2002Ladan Shams, Christoph von der Malsburg
Modeling complex cells as Gabor wavelet magnitudes shows that in spite of phase insensitivity of individual complex cell responses, population responses contain sufficient information to capture the perceptual essence of images.
IEEE Transactions on Circuits and Systems for Video TechnologyQuantifying and Recognizing Human Movement Patterns From Monocular Video Images—Part II: Applications to Biometrics
47 Citations2004R.D. Green, Ling Guan
The results suggest that the CHMR system enabled successful biometric authentication of anthropometric data, gait signatures, human activities, and movement disorders.
Pattern Recognition LettersA comparison between Fourier-Mellin descriptors and moment based features for invariant object recognition using neural networks
46 Citations1991Amelia Grace, M. Spann
Two algorithms for invariant object recognition are compared using a neural network and two statistical classifiers as classifiers for features taken from noiseless and noisy images and it is found that Fourier-Mellin descriptors perform as well as moment based features for noisy images but perform significantly better when noise is added.
A rotation invariant pattern signature
37 Citations2002Eero P. Simoncelli
A "signature" for rotation-invariant representation of local image structure is proposed, a complex-valued vector constructed analytically from the projections of the image onto a set of oriented basis kernels to avoid instabilities associated with previously developed algebraic invariants.
Lecture notes in computer scienceCombining Features for Content-Based Sketch Retrieval — A Comparative Evaluation of Retrieval Performance
22 Citations2002Daniel Heesch, Stefan Rüger
It is shown that the use of a combination of different shape representations may lead to a significant improvement of retrieval performance and an optimal combination is identified that proves robust across different data sets and queries.
Animated Heads: From 3D Motion Fields to Action Descriptions
6 Citations2001Jan Neumann, Cornelia Fermüller +1 more
The ability to estimate 3D motion fields points to a new framework for the study of action, which can serve as an intermediate representation which can be analyzed using geometrical and statisti cal tools for the purpose of extracting representations of generic human actions.