Finding people by sampling
Sergey Ioffe, David Alexander Forsyth · IEEE International Conference on Computer Vision (ICCV) · 1999
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.
Cited by 42 works. doi:10.1109/iccv.1999.790398
Authors
References
- Markov Chain Monte Carlo in Practice
- Model-Based Recognition and Localization from Sparse Range or Tactile Data
- Model-based image analysis of human motion using constraint propagation
- Human Face Detection in Visual Scenes
- Pedestrian detection using wavelet templates
- Description and recognition of curved objects☆
- Representation and Description of Curved Objects
- Finding naked people
- Active Contours: The Application of Techniques from Graphics, Vision, Control Theory and Statistics to Visual Tracking of Shapes in Motion
- Finding human faces with a Gaussian mixture distribution-based face model