Human Pose Estimation with Fields of Parts

2014

Conference Paper

ei

ps


This paper proposes a new formulation of the human pose estimation problem. We present the Fields of Parts model, a binary Conditional Random Field model designed to detect human body parts of articulated people in single images. The Fields of Parts model is inspired by the idea of Pictorial Structures, it models local appearance and joint spatial configuration of the human body. However the underlying graph structure is entirely different. The idea is simple: we model the presence and absence of a body part at every possible position, orientation, and scale in an image with a binary random variable. This results into a vast number of random variables, however, we show that approximate inference in this model is efficient. Moreover we can encode the very same appearance and spatial structure as in Pictorial Structures models. This approach allows us to combine ideas from segmentation and pose estimation into a single model. The Fields of Parts model can use evidence from the background, include local color information, and it is connected more densely than a kinematic chain structure. On the challenging Leeds Sports Poses dataset we improve over the Pictorial Structures counterpart by 5.5% in terms of Average Precision of Keypoints (APK).

Author(s): Kiefel, Martin and Gehler, Peter
Book Title: Computer Vision – ECCV 2014
Volume: LNCS 8693
Pages: 331-346
Year: 2014
Month: September

Series: Lecture Notes in Computer Science
Editors: Fleet, David and Pajdla, Tomas and Schiele, Bernt and Tuytelaars, Tinne
Publisher: Springer

Department(s): Empirical Inference, Perceiving Systems
Research Project(s): 2D Pose from Images
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1007/978-3-319-10602-1_22
Event Name: 13th European Conference on Computer Vision
Event Place: Zürich, Switzerland

Links: website
Attachments: pdf

BibTex

@inproceedings{kiefel14eccv,
  title = {Human Pose Estimation with Fields of Parts},
  author = {Kiefel, Martin and Gehler, Peter},
  booktitle = {Computer Vision -- ECCV 2014},
  volume = {LNCS 8693},
  pages = {331-346},
  series = {Lecture Notes in Computer Science},
  editors = {Fleet, David and Pajdla, Tomas and Schiele, Bernt and Tuytelaars, Tinne},
  publisher = {Springer},
  month = sep,
  year = {2014},
  month_numeric = {9}
}