Reconstruction of articulated objects from point correspondences in a single uncalibrated image
Published 7 November 2002
Catherine Taylor
Citations156
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
This paper investigates the problem of recovering information about the configuration of an articulated object, such as a human figure, from point correspondences in a single-image by considering the foreshortening of the segments of the model in the image.
Abstract
This paper investigates the problem of recovering information about the configuration of an articulated object, such as a human figure, from point correspondences in a single-image. Unlike previous approaches, the proposed reconstruction method does not assume that the imagery was acquired with a calibrated camera. An analysis is presented which demonstrates that there are a family of solutions to this reconstruction problem parameterized by a single variable. A simple and effective algorithm is proposed for recovering the entire set of solutions by considering the foreshortening of the segments of the model in the image. Results obtained by applying this algorithm to real images are presented.
Keywords
Computer ScienceEngineering
IEEE Transactions on Pattern Analysis and Machine IntelligencePfinder: real-time tracking of the human body
4,147 Citations1997Christopher R. Wren, A. Azarbayejani +2 more
Tracking people with twists and exponential maps
732 Citations2002Christoph Bregler, Jitendra Malik
This paper demonstrates a new visual motion estimation technique that is able to recover high degree-of-freedom articulated human body configurations in complex video sequences, and is the first computer vision based system able to process such challenging footage and recover complex motions with such high accuracy.
Lecture notes in computer scienceVisual tracking of high DOF articulated structures: An application to human hand tracking
450 Citations1994James M. Rehg, Takeo Kanade
A model-based hand tracking system, called DigitEyes, that can recover the state of a 27 DOF hand model from ordinary gray scale images at speeds of up to 10 Hz is described.
Lecture notes in computer scienceFinding naked people
443 Citations1996Margaret M. Fleck, David Forsyth +1 more
A content-based retrieval strategy that can tell whether there are naked people present in an image and an effective mask for skin regions is demonstrated, which introduces a new view of object recognition.
IEEE Transactions on Pattern Analysis and Machine IntelligenceModel-based image analysis of human motion using constraint propagation
426 Citations1980Joseph O’Rourke, Norman I. Badler
A system capable of analyzing image sequences of human motion is described, structured as a feedback loop between high and low levels: predictions are made at the semantic level and verifications are sought at the image level.
CVGIP Image UnderstandingTowards Model-Based Recognition of Human Movements in Image Sequences
378 Citations1994Karl Rohr
A model-based approach for the recognition of pedestrians is introduced and the human body is represented by a 3D-model consisting of cylinders, whereas for modelling the movement of walking the authors use data from medical motion studies.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRecovery of nonrigid motion and structure
357 Citations1991Alex Pentland, B. Horowitz
Monocular tracking of the human arm in 3D
203 Citations2002Lídia Gonçalves, Enrico Bernardo +2 more
This work proposes to use a recursive estimator for arm position, and to provide the estimator with error signals obtained by comparing the projected estimated arm position with that of the actual arm in the image.
Computer Vision Graphics and Image ProcessingDetermination of 3D human body postures from a single view
202 Citations1985Hsi-Jian Lee, Zen Chen
A method is proposed to recover and interpret the 3D body structures of a person from a single view, provided that at least six feature points on the head and a set of body joints are available on the image plane, and the geometry of head and lengths of body segments formed by joints are known.
IEEE Transactions on Pattern Analysis and Machine IntelligenceTowards a system for the interpretation of moving light displays
139 Citations1980Richard F. Rashid
An algorithm is presented which segments the points of an MLD of a wire-frame man into body parts, and the relationship of this algorithm to previous theories of MLD perception and actual human performance is discussed.
Singularity analysis for articulated object tracking
129 Citations2002Daniel Morris, James M. Rehg
This work describes a novel 2-D Scaled Prismatic Model (SPM) for figure registration that has fewer singularity problems and does not require detailed knowledge of the 3-D kinematics.
A survey of motion analysis from moving light displays
58 Citations1994Cedras, Shah
This paper provides a review of recent developments in motion-based recognition and finds an appropriate representation for the objects or motions from the motion cues of the sequence, and then organize them into useful representations.
Model-based Recognition of Human Posture using Single Synthetic Images
14 Citations1989C. I. Attwood, G. D. Sullivan +1 more
This research shows that accurate 3D structure can be recovered without such knowledge, and that descriptions of a human figure's behaviour can be obtained in terms of static posture descriptions such as; "sitting", "kneeling", "standing".
National Conference on Artificial IntelligenceStatic analysis of moving jointed objects
12 Citations1980Jon A. Webb
An algorithm is presented for calculating the rigid part lengths and motion of the jointed objects just from the positions of the joints and some depth information and the algorithm is proved correct.
ScholarlyCommons (University of Pennsylvania)Moving posture reconstruction from perspective projections of jointed figure motion
8 Citations1993Jianmin Zhao, Norman I. Badler
This work tried to recover the original 3D postures through an accurate human figure model and the continuity requirement (temporal coherence) in the sequence to reproduce a human figure's motion with a computer simulated human figure.