Paper Info
Title
Fast Single Shot Detection and Pose Estimation
Abstract
For applications in navigation and robotics, estimating the 3D pose of objects is as important as detection. Many approaches to pose estimation rely on detecting or tracking parts or keypoints [11, 21]. In this paper we build on a recent state-of-the-art convolutional network for sliding-window detection [10] to provide detection and rough pose estimation in a single shot, without intermediate stages of detecting parts or initial bounding boxes. While not the first system to treat pose estimation as a categorization problem, this is the first attempt to combine detection and pose estimation at the same level using a deep learning approach. The key to the architecture is a deep convolutional network where scores for the presence of an object category, the offset for its location, and the approximate pose are all estimated on a regular grid of locations in the image. The resulting system is as accurate as recent work on pose estimation (42.4% 8 View mAVP on Pascal 3D+ [21] ) and significantly faster (46 frames per second (FPS) on a TITAN X GPU). This approach to detection and rough pose estimation is fast and accurate enough to be widely applied as a pre-processing step for tasks including high-accuracy pose estimation, object tracking and localization, and vSLAM.
Year
DOI
Venue
2016
10.1109/3DV.2016.78
2016 Fourth International Conference on 3D Vision (3DV)
Keywords
DocType
Volume
fast single shot detection,pose estimation,sliding-window detection,categorization problem,deep learning approach,deep convolutional network,TITAN X GPU,object tracking,object localization,vSLAM
Conference
abs/1609.05590
ISSN
ISBN
Citations 
2378-3826
978-1-5090-5408-4
13
PageRank 
References 
Authors
0.60
14
6
Name
Order
Citations
PageRank
Patrick Poirson1291.20
Phil Ammirato2130.93
Cheng-Yang Fu31386.57
Wei Liu41519103.13
Jana Kosecká51523129.85
Alexander C. Berg610554630.24