Advanced

Pictorial Human Spaces : A Computational Study on the Human Perception of 3D Articulated Poses

Marinoiu, Elisabeta; Papava, Dragos and Sminchisescu, Cristian LU (2016) In International Journal of Computer Vision p.1-22
Abstract

Human motion analysis in images and video, with its deeply inter-related 2D and 3D inference components, is a central computer vision problem. Yet, there are no studies that reveal how humans perceive other people in images and how accurate they are. In this paper we aim to unveil some of the processing—as well as the levels of accuracy—involved in the 3D perception of people from images by assessing the human performance. Moreover, we reveal the quantitative and qualitative differences between human and computer performance when presented with the same visual stimuli and show that metrics incorporating human perception can produce more meaningful results when integrated into automatic pose prediction algorithms. Our contributions are:... (More)

Human motion analysis in images and video, with its deeply inter-related 2D and 3D inference components, is a central computer vision problem. Yet, there are no studies that reveal how humans perceive other people in images and how accurate they are. In this paper we aim to unveil some of the processing—as well as the levels of accuracy—involved in the 3D perception of people from images by assessing the human performance. Moreover, we reveal the quantitative and qualitative differences between human and computer performance when presented with the same visual stimuli and show that metrics incorporating human perception can produce more meaningful results when integrated into automatic pose prediction algorithms. Our contributions are: (1) the construction of an experimental apparatus that relates perception and measurement, in particular the visual and kinematic performance with respect to 3D ground truth when the human subject is presented an image of a person in a given pose; (2) the creation of a dataset containing images, articulated 2D and 3D pose ground truth, as well as synchronized eye movement recordings of human subjects, shown a variety of human body configurations, both easy and difficult, as well as their ‘re-enacted’ 3D poses; (3) quantitative analysis revealing the human performance in 3D pose re-enactment tasks, the degree of stability in the visual fixation patterns of human subjects, and the way it correlates with different poses; (4) extensive analysis on the differences between human re-enactments and poses produced by an automatic system when presented with the same visual stimuli; (5) an approach to learning perceptual metrics that, when integrated into visual sensing systems, produces more stable and meaningful results.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
in press
keywords
Human eye movements, Human perception, Human pose estimation, Metric learning, Perceptual distance
in
International Journal of Computer Vision
pages
22 pages
publisher
Springer
external identifiers
  • Scopus:84962013919
ISSN
0920-5691
DOI
10.1007/s11263-016-0888-3
language
English
LU publication?
yes
id
718d409e-5bb8-4374-950c-dc7626bdbeb5
date added to LUP
2016-06-08 08:41:08
date last changed
2016-07-06 14:36:33
@misc{718d409e-5bb8-4374-950c-dc7626bdbeb5,
  abstract     = {<p>Human motion analysis in images and video, with its deeply inter-related 2D and 3D inference components, is a central computer vision problem. Yet, there are no studies that reveal how humans perceive other people in images and how accurate they are. In this paper we aim to unveil some of the processing—as well as the levels of accuracy—involved in the 3D perception of people from images by assessing the human performance. Moreover, we reveal the quantitative and qualitative differences between human and computer performance when presented with the same visual stimuli and show that metrics incorporating human perception can produce more meaningful results when integrated into automatic pose prediction algorithms. Our contributions are: (1) the construction of an experimental apparatus that relates perception and measurement, in particular the visual and kinematic performance with respect to 3D ground truth when the human subject is presented an image of a person in a given pose; (2) the creation of a dataset containing images, articulated 2D and 3D pose ground truth, as well as synchronized eye movement recordings of human subjects, shown a variety of human body configurations, both easy and difficult, as well as their ‘re-enacted’ 3D poses; (3) quantitative analysis revealing the human performance in 3D pose re-enactment tasks, the degree of stability in the visual fixation patterns of human subjects, and the way it correlates with different poses; (4) extensive analysis on the differences between human re-enactments and poses produced by an automatic system when presented with the same visual stimuli; (5) an approach to learning perceptual metrics that, when integrated into visual sensing systems, produces more stable and meaningful results.</p>},
  author       = {Marinoiu, Elisabeta and Papava, Dragos and Sminchisescu, Cristian},
  issn         = {0920-5691},
  keyword      = {Human eye movements,Human perception,Human pose estimation,Metric learning,Perceptual distance},
  language     = {eng},
  month        = {04},
  pages        = {1--22},
  publisher    = {ARRAY(0xc23cb58)},
  series       = {International Journal of Computer Vision},
  title        = {Pictorial Human Spaces : A Computational Study on the Human Perception of 3D Articulated Poses},
  url          = {http://dx.doi.org/10.1007/s11263-016-0888-3},
  year         = {2016},
}