Automated markerless extraction of walking people using deformable contour models
Computer Animation and Virtual WorldsPublished 16 June 2004
David K. Wagg, Mark Nixon
Citations33
SJR quartileQ3
SJR score0.32
SNIP0.62
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
The greedy snake formulation is extended to include temporal constraints and occlusion modelling, increasing the capability of this technique when dealing with cluttered and self‐occluding extraction targets.
Abstract
Abstract We develop a new automated markerless motion capture system for the analysis of walking people. We employ global evidence gathering techniques guided by biomechanical analysis to robustly extract articulated motion. This forms a basis for new deformable contour models, using local image cues to capture shape and motion at a more detailed level. We extend the greedy snake formulation to include temporal constraints and occlusion modelling, increasing the capability of this technique when dealing with cluttered and self‐occluding extraction targets. This approach is evaluated on a large database of indoor and outdoor video data, demonstrating fast and autonomous motion capture for walking people. Copyright © 2004 John Wiley & Sons, Ltd.
Keywords
Computer ScienceEngineering
Computer Vision and Image UnderstandingA Survey of Computer Vision-Based Human Motion Capture
1,755 Citations2001Thomas B. Moeslund, Erik Granum
A comprehensive survey of computer vision-based human motion capture literature from the past two decades is presented, with a general overview based on a taxonomy of system functionalities, broken down into four processes: initialization, tracking, pose estimation, and recognition.
CVGIP Image UnderstandingA Fast algorithm for active contours and curvature estimation
1,095 Citations1992Donna J. Williams, Mubarak Shah
A greedy algorithm is presented which retains the improvements of stability, flexibility, and inclusion of hard constraints introduced by dynamic programming but is more than an order of magnitude faster than that approach, being O(nm).
Pattern RecognitionRecent developments in human motion analysis
962 Citations2003Liang Wang, Weiming Hu +1 more
This paper provides a comprehensive survey of research on computer-vision-based human motion analysis, namely human detection, tracking and activity understanding, and various methods for each issue are discussed in order to examine the state of the art.
3-D model-based tracking of humans in action: a multi-view approach
702 Citations1996Dariu M. Gavrila, L.S. Davis
A vision system for the 3-D model-based tracking of unconstrained human movement and initial tracking results from a large new Humans-in-Action database containing more than 2500 frames in each of four orthogonal views are presented.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRobust real-time periodic motion detection, analysis, and applications
692 Citations2000Ross Cutler, L.S. Davis
New techniques to detect and analyze periodic motion as seen from both a static and a moving camera are described and the periodicity is analyzed robustly using the 2D lattice structures inherent in similarity matrices.
W/sup 4/: Who? When? Where? What? A real time system for detecting and tracking people
591 Citations2002I. Haritaoglu, David Harwood +1 more
W/sup 4/ is a real time visual surveillance system for detecting and tracking people and monitoring their activities in an outdoor environment that employs a combination of shape analysis and tracking to locate people and their parts and to create models of people's appearance so that they can be tracked through interactions such as occlusion.
Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion capture
333 Citations2003Kong Man Cheung, Simon Baker +1 more
An iterative algorithm is proposed to solve this simultaneous assignment and alignment problem of the shape and motion of a rigidly moving object over time to apply to dynamic articulated objects.
Stride and cadence as a biometric in automatic person identification and verification
252 Citations2003Chiraz BenAbdelkader, Ross Cutler +1 more
A correspondence-free method to automatically estimate the spatio-temporal parameters of gait (stride length and cadence) of a walking person from video, which works with low-resolution images of people and is robust to changes in lighting, clothing and tracking errors.
On a Large Sequence-Based Human Gait Database
250 Citations2004Jamie D. Shutler, Michael Grant +2 more
A large human gait database is designed and built, providing a large multi-purpose dataset enabling the investigation of gait as a biometric and is also a useful database for many still and sequence based vision applications.
On automated model-based extraction and analysis of gait
227 Citations2004David K. Wagg, Mark Nixon
A new model-based extraction process guided by biomechanical analysis for walking people, and analysis of the extracted gait parameters suggest that recognition capability is primarily gained from cadence and from static shape parameters, although gait is the cue by which these are derived.
Computer Vision and Image UnderstandingTracking Persons in Monocular Image Sequences
204 Citations1999Stefan Wachter, Hans-Hellmut Nagel
The person model is augmented by a simple motion model of constant velocity for all DOFs which is used in the prediction step of the IEKF and in the update step, both region and edge information are used.
IEEE Transactions on Pattern Analysis and Machine IntelligenceArticulated soft objects for multiview shape and motion capture
154 Citations2003R. Plankers, Pascal Fua
A formalism that incorporates the use of implicit surfaces into earlier robotics approaches that were designed to handle articulated structures is proposed, and its effectiveness for human body modeling from synchronized video sequences is demonstrated.
A fast algorithm for active contours
145 Citations2002D.J. Williams, Mazlina Muzafar Shah
A method of controlling snakes that combines speed, flexibility, and simplicity is presented, found to be comparable in final results, while being faster than dynamic programming and more stable and flexible for including hard constraints than the variational calculus approach.
Articulated soft objects for video-based body modeling
118 Citations2002R. Plankers, Pascal Fua
This work develops a framework for 3-D shape and motion recovery of articulated deformable objects that incorporates the use of implicit surfaces into earlier robotics approaches that were designed to handle articulated structures.
Human Movement ScienceThree-dimensional relationships between the movements of the pelvis and lumbar spine during normal gait
98 Citations1999Michael W. Whittle, David Levine
The three-dimensional motions of the pelvis and lumbar spine in walking were measured, in 20 normal adult males, using “Vicon” optoelectronic system, with reflective targets attached to lightweight rigs over the thoracolumbar junction and upper sacrum.
On the relationship of human walking and running: automatic person identification by gait
64 Citations2003Chew-Yean Yam, Mark Nixon +1 more
The mapping between these gait modes clusters better than the original signatures and can be used for recognition purposes alone, or to buttress both of the signatures.
EurographicsMarkerless Motion Capture of Complex Full-Body Movement for Character Animation
47 Citations2001Andrew J. Davison, J. Deutscher +1 more
The approach to searching through the high-dimensional model configuration space is an algorithm called annealed particle filtering which finds the best fit to image data via multiple-layer propagation of a stochastic particle set.
Articulated model based people tracking using motion models
21 Citations2003Huazhong Ning, Liang Wang +2 more
This paper focuses on acquisition of human motion data such as joint angles and velocity for applications of virtual reality, using both an articulated body model and a motion model in the CONDENSATION framework, and proposes a PEF (pose evaluation function) modeled with a radial term.
ePrints Soton (University of Southampton)Model-Based Gait Enrolment in Real-World Imagery
11 Citations2003David K. Wagg, Mark Nixon
A new approach to enrolment for gait recognition technologies is described, allowing reliable subject gait extraction in real-world imagery and showing that comparable performance is attained in outdoor conditions.