Dense Color Constraints based 6D object pose estimation from RGB-D images

被引：0
|
作者：
Wang, Zilun [1 ,2 ]
Liu, Yi [3 ,4 ]
Xu, Chi [1 ,2 ]
机构：
[1] China Univ Geosci, Sch Automat, Wuhan 430074, Peoples R China
[2] Hubei Key Lab Adv Control & Intelligent Automat C, Wuhan 430074, Peoples R China
[3] CRRC Zhuzhou Locomot Co Ltd, Zhuzhou, Peoples R China
[4] Natl Innovat Ctr Adv Rail Transit Equipment, Zhuzhou, Hunan, Peoples R China
来源：
2022 41ST CHINESE CONTROL CONFERENCE (CCC) | 2022年
基金：
中国国家自然科学基金;
关键词：
Computer Vision; Deep Learning; Pose Estimation;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
A key problem for 6D pose estimation based on RGB-D image input is how to make full use of these two different data sources. The previous work simply took the depth map as the input of the fourth channel of CNN, or carried out the fusion offeatures extracted from these two data sources with different methods. But their fusion did not impose the right constraints and lost some valuable information. In this work, we propose that DCC (Dense Color Constraints). 6D pose estimation performance can be improved effectively by using dense corresponding color constraints. Experiments show the most advanced end-to-end performance in LineMod datasets.
引用
下载
收藏
页码：6416 / 6420
页数：5
相关论文
共 50 条
  • [21] ConvPoseCNN: Dense Convolutional 6D Object Pose Estimation
    Capellen, Catherine
    Schwarz, Max
    Behnke, Sven
    PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 5: VISAPP, 2020, : 162 - 172
  • [22] HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects
    Kaskman, Roman
    Zakharov, Sergey
    Shugurov, Ivan
    Ilic, Slobodan
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 2767 - 2776
  • [23] 3D Model-Based 6D Object Pose Tracking on RGB Images
    Majcher, Mateusz
    Kwolek, Bogdan
    INTELLIGENT INFORMATION AND DATABASE SYSTEMS (ACIIDS 2020), PT I, 2020, 12033 : 271 - 282
  • [24] Attention-guided RGB-D Fusion Network for Category-level 6D Object Pose Estimation
    Wang, Hao
    Li, Weiming
    Kim, Jiyeon
    Wang, Qiang
    2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 10651 - 10658
  • [25] 6D Robotic Assembly Based on RGB-only Object Pose Estimation
    Fu, Bowen
    Leong, Sek Kun
    Lian, Xiaocong
    Ji, Xiangyang
    2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 4736 - 4742
  • [26] RGB-D object pose estimation in unstructured environments
    Choi, Changhyun
    Christensen, Henrik I.
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2016, 75 : 595 - 613
  • [27] DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
    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
  • [28] A 3D Object Detection and Pose Estimation Pipeline Using RGB-D Images
    He, Ruotao
    Rojas, Juan
    Guan, Yisheng
    2017 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (IEEE ROBIO 2017), 2017, : 1527 - 1532
  • [29] An efficient lightweight deep neural network for real-time object 6D pose estimation with RGB-D inputs
    Liang, Yu
    Chen, Fan
    Liang, Guoyuan
    Wu, Xinyu
    Feng, Wei
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [30] Model-Based Underwater 6D Pose Estimation From RGB
    Sapienza D.
    Govi E.
    Aldhaheri S.
    Bertogna M.
    Roura E.
    Pairet E.
    Verucchi M.
    Ardon P.
    IEEE Robotics and Automation Letters, 2023, 8 (11) : 7535 - 7542
12345