International Journal of Computer Vision

, Volume 118, Issue 1, pp 49–64

Poselet-Based Contextual Rescoring for Human Pose Estimation via Pictorial Structures

  • Antonio Hernández-Vela
  • Stan Sclaroff
  • Sergio Escalera
Article

DOI: 10.1007/s11263-015-0869-y

Cite this article as:
Hernández-Vela, A., Sclaroff, S. & Escalera, S. Int J Comput Vis (2016) 118: 49. doi:10.1007/s11263-015-0869-y
  • 352 Downloads

Abstract

In this paper we propose a contextual rescoring method for predicting the position of body parts in a human pose estimation framework. A set of poselets is incorporated in the model, and their detections are used to extract spatial and score-related features relative to other body part hypotheses. A method is proposed for the automatic discovery of a compact subset of poselets that covers the different poses in a set of validation images while maximizing precision. A rescoring mechanism is defined as a set-based boosting classifier that computes a new score for each body joint detection, given its relationship to detections of other body joints and mid-level parts in the image. This new score is incorporated in the pictorial structure model as an additional unary potential, following the recent work of Pishchulin et al. Experiments on two benchmarks show comparable results to Pishchulin et al. while reducing the size of the mid-level representation by an order of magnitude, reducing the execution time by \(68~\%\) accordingly.

Keywords

Contextual rescoring Poselets Human pose estimation 

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Antonio Hernández-Vela
    • 1
    • 3
  • Stan Sclaroff
    • 2
  • Sergio Escalera
    • 1
    • 3
  1. 1.Department of Applied Mathematics and AnalysisUniversitat de BarcelonaBarcelonaSpain
  2. 2.Department of Computer ScienceBoston UniversityBostonUSA
  3. 3.Computer Vision CenterBarcelonaSpain

Personalised recommendations