Out-of-Region Keypoint Localization for 6D Pose Estimation

Out-of-Region Keypoint Localization for 6D Pose Estimation
复制标题

6D 姿态估计的区域外关键点定位

DOI:
10.1016/j.imavis.2019.103854
复制
发表时间:
2020-01
影响因子:
4.7
通讯作者:
Haopeng Zhang
Haopeng Zhang
中科院分区:
计算机科学3区
文献类型:
--
作者:
Xin Zhang;Zhiguo Jiang;Haopeng Zhang

文献摘要

参考文献

相似文献

本文讨论了从单个RGB图像的实例级6D姿态估计的问题。我们的方法同时检测对象和恢复构成预测对象的3D边界框顶点的2D图像位置。具体来说,我们专注于定位虚拟关键点的对象区域的建议之外的挑战,并提出了一个基于边界的关键点表示,它结合了分类和回归方案,以减少输出空间。此外,我们的方法预测本地化的信心,并通过投票过程来消除困难的关键点的影响。我们实现了基于二维检测流水线的方法,同时弥补了检测和姿态估计之间的特征鸿沟。我们的网络具有实时处理能力,在GTX 1080Ti GPU上运行30 fps。对于两个基准数据集上的单对象和多对象姿态估计,与最先进的基于RGB的姿态估计方法相比,我们的方法具有竞争力或上级性能。
This paper addresses the problem of instance level 6D pose estimation from a single RGB image. Our approach simultaneously detects objects and recovers poses by predicting the 2D image locations of the object's 3D bounding box vertices. Specifically, we focus on the challenge of locating virtual keypoints outside the object region proposals, and propose a boundary-based keypoint representation which incorporates classification and regression schemes to reduce output space. Moreover, our method predicts localization confidences and alleviates the influence of difficult keypoints by a voting process. We implement the proposed method based on 2D detection pipeline, meanwhile bridge the feature gap between detection and pose estimation. Our network has real-time processing capability, which runs 30 fps on a GTX 1080Ti GPU. For single object and multiple objects pose estimation on two benchmark datasets, our approach achieves competitive or superior performance compared with state-of-the-art RGB based pose estimation methods.
DOI: 10.1109/34.862199
发表时间: 2000-06-01
影响因子: 23.6
作者:
Lu, CP;Hager, GD;Mjolsness, E
通讯作者: Mjolsness, E
DOI: 10.24963/ijcai.2018/141
发表时间: 2018-07
期刊: --
影响因子: --
作者:
Zairan Wang;Weiming Li;Yueying Kao;Dongqing Zou;Qiang Wang;Minsu Ahn;Sunghoon Hong
通讯作者: Zairan Wang;Weiming Li;Yueying Kao;Dongqing Zou;Qiang Wang;Minsu Ahn;Sunghoon Hong
DOI: 10.1109/icra.2016.7487396
发表时间: 2016-05
期刊: 2016 IEEE International Conference on Robotics and Automation (ICRA)
影响因子: --
作者:
Zhe Cao;Yaser Sheikh;N. Banerjee
通讯作者: Zhe Cao;Yaser Sheikh;N. Banerjee
DOI: --
发表时间: 2018-09
期刊: ArXiv
影响因子: --
作者:
Jonathan Tremblay;Thang To;Balakumar Sundaralingam;Yu Xiang;D. Fox;Stan Birchfield
通讯作者: Jonathan Tremblay;Thang To;Balakumar Sundaralingam;Yu Xiang;D. Fox;Stan Birchfield
DOI: 10.1016/j.imavis.2019.06.013
发表时间: 2019-09
期刊: Image Vis. Comput.
影响因子: --
作者:
Xin Zhang;Zhi-guo Jiang;Haopeng Zhang
通讯作者: Xin Zhang;Zhi-guo Jiang;Haopeng Zhang