Pose estimation for category specific multiview object localization
- 1 June 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 778-785
- https://doi.org/10.1109/cvpr.2009.5206633
Abstract
We propose an approach to overcome the two main challenges of 3D multiview object detection and localization: The variation of object features due to changes in the viewpoint and the variation in the size and aspect ratio of the object. Our approach proceeds in three steps. Given an initial bounding box of fixed size, we first refine its aspect ratio and size. We can then predict the viewing angle, under the hypothesis that the bounding box actually contains an object instance. Finally, a classifier tuned to this particular viewpoint checks the existence of an instance. As a result, we can find the object instances and estimate their poses, without having to search over all window sizes and potential orientations. We train and evaluate our method on a new object database specifically tailored for this task, containing real-world objects imaged over a wide range of smoothly varying viewpoints and significant lighting changes. We show that the successive estimations of the bounding box and the viewpoint lead to better localization results.Keywords
This publication has 13 references indexed in Scilit:
- A fast local descriptor for dense matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Multiplicative kernels: Object detection, segmentation and pose estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Joint Real-time Object Detection and Pose Estimation Using Probabilistic Boosting NetworkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- POP: Patchwork of Parts Models for Object RecognitionInternational Journal of Computer Vision, 2007
- 3D generic object categorization, localization and pose estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Multiclass Object Recognition with Sparse, Localized FeaturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene CategoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Towards Multi-View Object Class DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- A performance evaluation of local descriptorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004