Real-Time Object Pose Estimation with Pose Interpreter Networks

被引：0

作者：

Wu, Jimmy ^{[1
]}

Zhou, Bolei ^{[1
]}

RusseLL, Rebecca ^{[2
]}

Kee, Vincent ^{[2
]}

Wagner, Syler ^{[3
]}

Hebert, Mitchell ^{[2
]}

Torralba, Antonio ^{[1
]}

Johnson, David M. S. ^{[3
]}

机构：

[1] MIT, Comp Sci & Artificial Intelligence Lab, 77 Massachusetts Ave, Cambridge, MA 02139 USA

[2] Charles Stark Draper Lab, Cambridge, MA USA

[3] Dexai Robot, Boston, MA 02110 USA

来源：

2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2018年

关键词：

RECOGNITION;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this work, we introduce pose interpreter networks for 6-DoF object pose estimation. In contrast to other CNN-based approaches to pose estimation that require expensively annotated object pose data, our pose interpreter network is trained entirely on synthetic pose data. We use object masks as an intermediate representation to bridge real and synthetic. We show that when combined with a segmentation model trained on RGB images, our synthetically trained pose interpreter network is able to generalize to real data. Our end-to-end system for object pose estimation runs in real-time (20 Hz) on live RGB data, without using depth information or ICP refinement.

引用

页码：6798 / 6805

页数：8

共 50 条

[1] Real-Time Pose Estimation Piggybacked on Object Detection
Juranek, Roman
Herout, Adam
Dubska, Marketa
Zemcik, Pavel
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 2381 - 2389
[2] Real-time face pose estimation
McKenna, SJ
Gong, S
REAL-TIME IMAGING, 1998, 4 (05) : 333 - 347
[3] Real-time Human Pose Estimation with Convolutional Neural Networks
Linna, Marko
Kannala, Juho
Rahtu, Esa
PROCEEDINGS OF THE 13TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2018), VOL 5: VISAPP, 2018, : 335 - 342
[4] Towards Real-time Object Recognition and Pose Estimation in Point Clouds
Marcon, Marlon
Pereira Bellon, Olga Regina
Silva, Luciano
VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 5: VISAPP, 2021, : 164 - 174
[5] Real-Time 6D Object Pose Estimation on CPU
Konishi, Yoshinori
Hattori, Kosuke
Hashimoto, Manabu
2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2019, : 3451 - 3458
[6] Real-time tracking and estimation of plane pose
Buenaposada, M
Baumela, L
16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL II, PROCEEDINGS, 2002, : 697 - 700
[7] Research on Real-time Estimation for Human Pose
Li, Beibei
Zhao, Zhihong
2013 3RD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT), 2013, : 301 - 305
[8] Depth-assisted rectification for real-time object detection and pose estimation
João Paulo Silva do Monte Lima
Francisco Paulo Magalhães Simões
Hideaki Uchiyama
Veronica Teichrieb
Eric Marchand
Machine Vision and Applications, 2016, 27 : 193 - 219
[9] Depth-assisted rectification for real-time object detection and pose estimation
Silva do Monte Lima, Joao Paulo
Magalhaes Simoes, Francisco Paulo
Uchiyama, Hideaki
Teichrieb, Veronica
Marchand, Eric
MACHINE VISION AND APPLICATIONS, 2016, 27 (02) : 193 - 219
[10] Joint real-time object detection and pose estimation using probabilistic boosting network
Zhang, Jingdan
Zhou, Shaohua Kevin
McMillan, Leonard
Comaniciu, Dorin
2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8, 2007, : 2342 - +

← 1 2 3 4 5 →