Finding people by sampling
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1092-1097 vol.2
- https://doi.org/10.1109/iccv.1999.790398
Abstract
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 a 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.Keywords
This publication has 6 references indexed in Scilit:
- Pedestrian detection using wavelet templatesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Finding human faces with a Gaussian mixture distribution-based face modelPublished by Springer Nature ,1996
- Model-Based Recognition and Localization from Sparse Range or Tactile DataThe International Journal of Robotics Research, 1984
- Model-based image analysis of human motion using constraint propagationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1980
- Description and recognition of curved objects☆Artificial Intelligence, 1977
- Representation and Description of Curved ObjectsPublished by Defense Technical Information Center (DTIC) ,1972