Paper
12 June 2020 Object 6D pose estimation with non-local attention
Jianhan Mei, Henghui Ding, Xudong Jiang
Author Affiliations +
Proceedings Volume 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020); 115191H (2020) https://doi.org/10.1117/12.2573051
Event: Twelfth International Conference on Digital Image Processing, 2020, Osaka, Japan
Abstract
In this paper, we address the challenging task of estimating 6D object poses from a single RGB image. Motivated by the deep learning-based object detection methods, we propose a concise and efficient network that integrates 6D object pose parameter estimation into the object detection framework. Furthermore, for more robust estimation to occlusion, a nonlocal self-attention module is introduced. The experimental results show that the proposed method reaches the state-ofthe-art performance on the YCB-video and the Linemod datasets.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jianhan Mei, Henghui Ding, and Xudong Jiang "Object 6D pose estimation with non-local attention", Proc. SPIE 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020), 115191H (12 June 2020); https://doi.org/10.1117/12.2573051
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Cameras

RGB color model

3D modeling

3D image processing

Neural networks

Feature extraction

3D acquisition

RELATED CONTENT

Optimal target recognition method using accumulated evidence
Proceedings of SPIE (September 15 1998)
3D object registration in image sequences
Proceedings of SPIE (April 06 1998)

Back to Top