Recovering Human Body Configurations Using Pairwise Constraints between Parts

Authors:
Xiaofeng Ren;Alexander C. Berg;Jitendra Malik
Affiliations:
University of California at Berkeley;University of California at Berkeley;University of California at Berkeley
Venue:
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Year:
2005

Citing 0
Cited 40

A survey of advances in vision-based human motion capture and analysis

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Vision-based human motion analysis: An overview

Computer Vision and Image Understanding
Learning Probabilistic Models for Contour Completion in Natural Images

International Journal of Computer Vision
Human skeleton proportions recovery from monocular data

ISPRA'06 Proceedings of the 5th WSEAS International Conference on Signal Processing, Robotics and Automation
Covered body analysis in application to patient monitoring

CSTST '08 Proceedings of the 5th international conference on Soft computing as transdisciplinary science and technology
Learning articulated appearance models for tracking humans: A spectral graph matching approach

Image Communication
Integration of Local Image Cues for Probabilistic 2D Pose Recovery

ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Recovery of upper body poses in static images based on joints detection

Pattern Recognition Letters
Contour Grouping Based on Contour-Skeleton Duality

International Journal of Computer Vision
Shape Based Detection and Top-Down Delineation Using Image Segments

International Journal of Computer Vision
Hierarchical Vibrations: A Structural Decomposition Approach for Image Analysis

EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Stable Structural Deformations

ICVS '09 Proceedings of the 7th International Conference on Computer Vision Systems: Computer Vision Systems
HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion

International Journal of Computer Vision
Coupled region-edge shape priors for simultaneous localization and figure-ground segmentation

Pattern Recognition
2D Articulated Pose Tracking Using Particle Filter with Partitioned Sampling and Model Constraints

Journal of Intelligent and Robotic Systems
Object detection combining recognition and segmentation

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Bottom-up recognition and parsing of the human body

EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Boosted multiple deformable trees for parsing human poses

Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Recognizing activities with multiple cues

Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Hierarchical vibrations for part-based recognition of complex objects

Pattern Recognition
Robust Pose Recognition of the Obscured Human Body

International Journal of Computer Vision
Visual affect recognition

Visual affect recognition
Detecting people using mutually consistent poselet activations

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Monocular human pose tracking using multi frame part dynamics

WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Efficient inference with multiple heterogeneous part detectors for human pose estimation

ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Fast multi-aspect 2D human detection

ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Integration of bottom-up/top-down approaches for 2D pose estimation using probabilistic Gaussian modelling

Computer Vision and Image Understanding
Dimensionality reduction using a Gaussian Process Annealed Particle Filter for tracking and classification of articulated body motions

Computer Vision and Image Understanding
Finding human poses in videos using concurrent matching and segmentation

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
Max Margin Learning of Hierarchical Configural Deformable Templates (HCDTs) for Efficient Object Parsing and Pose Estimation

International Journal of Computer Vision
Part-based localisation and segmentation of landmark-related auditory cortical regions

Pattern Recognition
Estimation of 3-D human body posture via co-registration of 3-D human model and sequential stereo information

Applied Intelligence
Learning of graphical models and efficient inference for object class recognition

DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Person de-identification in videos

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
Discriminative Appearance Models for Pictorial Structures

International Journal of Computer Vision
Evolutionary Hough Games for coherent object detection

Computer Vision and Image Understanding
Finding people using scale, rotation and articulation invariant matching

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Efficient human parsing based on sketch representation

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Discriminative hierarchical part-based models for human parsing and action recognition

The Journal of Machine Learning Research
Combination of annealing particle filter and belief propagation for 3D upper body tracking

Applied Bionics and Biomechanics - Personal Care Robotics

Quantified Score

Hi-index	0.00

Visualization

Abstract

The goal of this work is to recover human bodyconfigurations from static images. Without assuming a priori knowledge of scale, pose or appearance, this problem is extremely challenging and demands the use of all possible sources of information. We develop a framework which can incorporate arbitrary pairwise constraints between body parts, such as scale compatibility, relative position, symmetry of clothing and smooth contour connections between parts. We detect candidate body parts from bottom-up using parallelism, and use various pairwise configuration constraints to assemble them together into body configurations. To find the most probable configuration, we solve an Integer Quadratic Programming problem with a standard technique using linear approximations. Approximate IQP allows us to incorporate much more information than the traditional dynamic programming and remains computationally efficient. 15 hand-labeled images are used to train the low-level part detector and learn the pairwise constraints. We show test results on a variety of images.