Abstract
In this paper we show how segmentation as preprocessing paradigm can be used to improve the efficiency and accuracy of model search in an image. We operationalize this idea using an over-segmentation of an image into superpixels. The problem domain we explore is human body pose estimation from still images. The superpixels prove useful in two ways. First, we restrict the joint positions in our human body model to lie at centers of superpixels, which reduces the size of the model search space. In addition, accurate support masks for computing features on half-limbs of the body model are obtained by using agglomerations of superpixels as half limb segments. We present results on a challenging dataset of people in sports news images
Keywords
Computer scienceArtificial intelligenceSegmentationPreprocessorImage segmentationComputer visionScale-space segmentationDomain (mathematical analysis)Image (mathematics)Pattern recognition (psychology)Joint (building)Segmentation-based object categorizationMathematicsEngineering
Affiliated Institutions
Related Publications
Superpixel lattices
Unsupervised over-segmentation of an image into superpixels is a common preprocessing step for image parsing algorithms. Ideally, every pixel within each superpixel region will ...
End-to-End Recovery of Human Shape and Pose
We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods tha...
Composite Statistical Inference for Semantic Segmentation
In this paper we present an inference procedure for the semantic segmentation of images. Different from many CRF approaches that rely on dependencies modeled with unary and pair...
Model-Based Interpretation of 3D Medical Images
The automatic segmentation and labelling of anatomical structures in 3D medical images is a challenging task of practical importance. We describe a model-based approach which al...
Discovering objects and their location in images
We seek to discover the object categories depicted in a set of unlabelled images. We achieve this using a model developed in the statistical text literature: probabilistic Laten...
Publication Info
- Year
- 2005
- Type
- article
- Pages
- 1417-1423 Vol. 2
- Citations
- 298
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
298
OpenAlex
Cite This
Giulio Mori
(2005).
Guiding model search using segmentation.
, 1417-1423 Vol. 2.
https://doi.org/10.1109/iccv.2005.112
Identifiers
- DOI
- 10.1109/iccv.2005.112