Abstract
We investigate the task of 2D articulated human pose estimation in unconstrained still images. This is extremely challenging because of variation in pose, anatomy, clothing, and imaging conditions. Current methods use simple models of body part appearance and plausible configurations due to limitations of available training data and constraints on computational expense. We show that such models severely limit accuracy. Building on the successful pictorial structure model (PSM) we propose richer models of both appearance and pose, using state-of-the-art discriminative classifiers without introducing unacceptable computational expense. We introduce a new annotated database of challenging consumer images, an order of magnitude larger than currently available datasets, and demonstrate over 50% relative improvement in pose estimation accuracy over a stateof-the-art method.
Keywords
PoseComputer scienceArtificial intelligenceNonlinear systemEstimationComputer vision3D pose estimationPattern recognition (psychology)Engineering
Affiliated Institutions
Related Publications
Articulated Human Detection with Flexible Mixtures of Parts
We describe a method for articulated human detection and human pose estimation in static images based on a new representation of deformable part models. Rather than modeling art...
Pictorial structures revisited: People detection and articulated pose estimation
Non-rigid object detection and articulated pose estimation are two related and challenging problems in computer vision. Numerous models have been proposed over the years and oft...
Articulated people detection and pose estimation: Reshaping the future
State-of-the-art methods for human detection and pose estimation require many training samples for best performance. While large, manually collected datasets exist, the captured...
Poselet Conditioned Pictorial Structures
In this paper we consider the challenging problem of articulated human pose estimation in still images. We observe that despite high variability of the body articulations, human...
DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
This paper considers the task of articulated human pose estimation of multiple people in real world images. We propose an approach that jointly solves the tasks of detection and...
Publication Info
- Year
- 2010
- Type
- article
- Pages
- 12.1-12.11
- Citations
- 875
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
875
OpenAlex
Cite This
P. Sam Johnson,
Mark Everingham
(2010).
Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation.
, 12.1-12.11.
https://doi.org/10.5244/c.24.12
Identifiers
- DOI
- 10.5244/c.24.12