Finding people by sampling

Sergey Ioffe, David Forsyth

Research output: Contribution to conferencePaperpeer-review


We show how to use a sampling method to find sparsely clad people in static images. People are modeled as an assembly of nine cylindrical segments. Segments are found using an EM algorithm, and then assembled into hypotheses incrementally, using a learned likelihood model. Each assembly step passes on a set of samples of its likelihood to the next; this yields effective pruning of the space of hypotheses. The collection of available nine-segment hypotheses is then represented by a set of equivalence classes, which yield an efficient pruning process. The posterior for the number of people is obtained from the class representatives. People are counted quite accurately in images of real scenes using an MAP estimate. We show the method allows top-down as well as bottom up reasoning. While the method can be overwhelmed by very large numbers of segments, we show that this problem can be avoided by quite simple pruning steps.

Original languageEnglish (US)
Number of pages6
StatePublished - Jan 1 1999
Externally publishedYes
EventProceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99) - Kerkyra, Greece
Duration: Sep 20 1999Sep 27 1999


OtherProceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99)
CityKerkyra, Greece

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Finding people by sampling'. Together they form a unique fingerprint.

Cite this