1 / 2

Efficient Tree-Based Joint Object and Pose Recognition System

This paper presents a scalable tree-based approach for simultaneously recognizing objects and estimating poses. The system utilizes a tree of classifiers for object recognition and pose estimation, leveraging state-of-the-art features extracted from RGB and depth images. With a near real-time performance of approximately one second, it achieves less than 30° pose estimation error on 300 everyday objects in the RGB-D Object Dataset. The research will be presented at the Twenty-Fifth Conference on Artificial Intelligence (AAAI) in August 2011.

odetta
Télécharger la présentation

Efficient Tree-Based Joint Object and Pose Recognition System

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. A Scalable Tree-based Approach for Joint Object and Pose Recognition Kevin Lai, Liefeng Bo, Xiaofeng Ren, and Dieter Fox

  2. A Scalable Tree-based Approach for Joint Object and Pose Recognition • Tree of classifiers for object recognition and pose estimation • State-of-the-art features (kernel descriptors) extracted from RGB and depth images • Near real-time performance (~1 second) • < 30° pose estimation error on 300 everyday objects(RGB-D Object Dataset) To appear in the Twenty-Fifth Conference on Artificial Intelligence (AAAI), August 2011

More Related