Human Pose Estimation with Fields of Parts

Kiefel, Martin; Gehler, Peter

doi:10.1007/978-3-319-10602-1_22

Local TagsRelease HistoryDetailsSummary

Human Pose Estimation with Fields of Parts

Kiefel, M., & Gehler, P. (2014). Human Pose Estimation with Fields of Parts. In D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars (Eds.), Computer Vision - ECCV 2014. Proceedings, Part 5 (pp. 331-346). Cham et al.: Springer International Publishing.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-C6FF-3 Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0028-7AE4-C

Genre: Conference Paper

Files

show Files

Locators

show

Creators

show

hide

Creators:
Kiefel, Martin¹, Author
Gehler, Peter², Author

Affiliations:
1Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647
2Dept. Perceiving Systems, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497642

Content

show

hide

Free keywords: Abt. Black; Abt. Schölkopf

Abstract: 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 percent in terms of Average Precision of Keypoints (APK).

Details

show

hide

Language(s): eng - English

Dates: Date issued: 2014-09

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: DOI: 10.1007/978-3-319-10602-1_22
BibTex Citekey: kiefel14eccv

Degree: -

Event

show

hide

Title: ECCV 2014 - 13th European Conference on Computer Vision

Place of Event: Zürich

Start-/End Date: 2014-09-06 - 2014-09-12

Legal Case

show

Project information

show

Source 1

show

hide

Title: Computer Vision - ECCV 2014. Proceedings, Part 5

Source Genre: Proceedings

Creator(s):
Fleet, David, Editor
Pajdla, Tomas, Editor
Schiele, Bernt, Editor
Tuytelaars, Tinne, Editor

Affiliations:
-

Publ. Info: Cham et al. : Springer International Publishing

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 331 - 346 Identifier: ISBN: 978-3-319-10601-4
ISBN: 978-3-319-10602-1

Source 2

show

hide

Title: Lecture Notes in Computer Science

Source Genre: Series

Creator(s):

Affiliations:

Publ. Info: -

Pages: - Volume / Issue: 8693 Sequence Number: - Start / End Page: - Identifier: -