6D Object Pose Estimation Based on the Attention Mechanism

被引：0
作者：
Zhou, Guanyu [1 ]
机构：
[1] Univ Jinan, Sch Informat Sci & Engn, Jinan 250024, Shandong, Peoples R China
来源：
INTERNATIONAL CONFERENCE ON ALGORITHMS, HIGH PERFORMANCE COMPUTING, AND ARTIFICIAL INTELLIGENCE (AHPCAI 2021) | 2021年 / 12156卷
关键词：
object pose estimation; attention mechanism; point cloud;
D O I：
10.1117/12.2626757
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Estimating a 6D object pose is an important and longstanding computer vision task. Though existing deep learning -based approaches have achieved inspiring results, there is still much room for improvement. In this paper, we present to introduce attention mechanism into object pose estimation method, which enables the network extract more distinguishing features on the objects to further get accurate object 6D pose. We verify the proposed method on the LINEMOD dataset, and the results show that our method achieves state-of-the-art performance.
引用
收藏
页数：6
相关论文
共 12 条
[1]   Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis [J].
Dai, Angela ;
Qi, Charles Ruizhongtai ;
Niessner, Matthias .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :6545-6554
[2]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[3]  
He Y., 2020, P IEEE CVF C COMP VI, P641
[4]  
Hinterstoisser S., 2013, ACCV, V7724, P548, DOI [DOI 10.1007/978-3-642-37331-242, 10.1007/978- 3- 642-37331-2_42]
[5]   EPnP: An Accurate O(n) Solution to the PnP Problem [J].
Lepetit, Vincent ;
Moreno-Noguer, Francesc ;
Fua, Pascal .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2009, 81 (02) :155-166
[6]   CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation [J].
Li, Zhigang ;
Wang, Gu ;
Ji, Xiangyang .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :7677-7686
[7]   Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation [J].
Park, Kiru ;
Patten, Timothy ;
Vincze, Markus .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :7667-7676
[8]   PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation [J].
Peng, Sida ;
Liu, Yuan ;
Huang, Qixing ;
Zhou, Xiaowei ;
Bao, Hujun .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :4556-4565
[9]  
Rublee E, 2011, IEEE I CONF COMP VIS, P2564, DOI 10.1109/ICCV.2011.6126544
[10]   DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion [J].
Wang, Chen ;
Xu, Danfei ;
Zhu, Yuke ;
Martin-Martin, Roberto ;
Lu, Cewu ;
Li Fei-Fei ;
Savarese, Silvio .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :3338-3347
12