Human body pose estimation with particle swarm optimisation

Špela Ivekovič, Emanuele Trucco, Yvan R. Petillot

Research output: Contribution to journalArticlepeer-review

32 Citations (Scopus)

Abstract

In this paper we address the problem of human body pose estimation from still images. A multi-view set of images of a person sitting at a table is acquired and the pose estimated. Reliable and efficient pose estimation from still images represents an important part of more complex algorithms, such as tracking human body pose in a video sequence, where it can be used to automatically initialise the tracker on the first frame. The quality of the initialisation influences the performance of the tracker in the subsequent frames. We formulate the body pose estimation as an analysis-by-synthesis optimisation algorithm, where a generic 3D human body model is used to illustrate the pose and the silhouettes extracted from the images are used as constraints. A simple test with gradient descent optimisation run from randomly selected initial positions in the search space shows that a more powerful optimisation method is required. We investigate the suitability of the Particle Swarm Optimisation (PSO) for solving this problem and compare its performance with an equivalent algorithm using Simulated Annealing (SA). Our tests show that the PSO outperforms the SA in terms of accuracy and consistency of the results, as well as speed of convergence. © 2008 by the Massachusetts Institute of Technology.

Original languageEnglish
Pages (from-to)509-528
Number of pages20
JournalEvolutionary Computation
Volume16
Issue number4
DOIs
Publication statusPublished - Dec 2008

Keywords

  • Articulated human body pose estimation
  • PSO
  • Still multi-view images

Fingerprint

Dive into the research topics of 'Human body pose estimation with particle swarm optimisation'. Together they form a unique fingerprint.

Cite this