Parsing Occluded People
- 1 June 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2401-2408
- https://doi.org/10.1109/cvpr.2014.308
Abstract
Occlusion poses a significant difficulty for object recognition due to the combinatorial diversity of possible occlusion patterns. We take a strongly supervised, non-parametric approach to modeling occlusion by learning deformable models with many local part mixture templates using large quantities of synthetically generated training data. This allows the model to learn the appearance of different occlusion patterns including figure-ground cues such as the shapes of occluding contours as well as the co-occurrence statistics of occlusion between neighboring parts. The underlying part mixture-structure also allows the model to capture coherence of object support masks between neighboring parts and make compelling predictions of figure-ground-occluder segmentations. We test the resulting model on human pose estimation under heavy occlusion and find it produces improved localization accuracy.Keywords
This publication has 20 references indexed in Scilit:
- Single-Pedestrian Detection Aided by Multi-pedestrian DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Occlusion reasoning for object detection under arbitrary viewpointPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Articulated people detection and pose estimation: Reshaping the futurePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Detection and Tracking of Occluded PeoplePublished by British Machine Vision Association and Society for Pattern Recognition ,2012
- A segmentation-aware object detection model with occlusion handlingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Recognition using visual phrasesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- An HOG-LBP human detector with partial occlusion handlingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Learning methods for generic object recognition with invariance to pose and lightingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Fast pose estimation with parameter-sensitive hashingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Towards automatic discovery of object categoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002