6DoF Pose Estimation of Transparent Object from a Single RGB-D Image
6DoF object pose estimation is a foundation for many important applications, such as robotic grasping, automatic driving, and so on. However, it is very challenging to estimate 6DoF pose of transparent object which is commonly seen in our daily life, because the optical characteristics of transparen...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/23/6790 |
| _version_ | 1797546442564304896 |
|---|---|
| author | Chi Xu Jiale Chen Mengyang Yao Jun Zhou Lijun Zhang Yi Liu |
| author_facet | Chi Xu Jiale Chen Mengyang Yao Jun Zhou Lijun Zhang Yi Liu |
| author_sort | Chi Xu |
| collection | DOAJ |
| description | 6DoF object pose estimation is a foundation for many important applications, such as robotic grasping, automatic driving, and so on. However, it is very challenging to estimate 6DoF pose of transparent object which is commonly seen in our daily life, because the optical characteristics of transparent material lead to significant depth error which results in false estimation. To solve this problem, a two-stage approach is proposed to estimate 6DoF pose of transparent object from a single RGB-D image. In the first stage, the influence of the depth error is eliminated by transparent segmentation, surface normal recovering, and RANSAC plane estimation. In the second stage, an extended point-cloud representation is presented to accurately and efficiently estimate object pose. As far as we know, it is the first deep learning based approach which focuses on 6DoF pose estimation of transparent objects from a single RGB-D image. Experimental results show that the proposed approach can effectively estimate 6DoF pose of transparent object, and it out-performs the state-of-the-art baselines by a large margin. |
| first_indexed | 2024-03-10T14:30:14Z |
| format | Article |
| id | doaj.art-1d6709166f0e4c79a907373cb5b8040f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T14:30:14Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1d6709166f0e4c79a907373cb5b8040f2023-11-20T22:39:35ZengMDPI AGSensors1424-82202020-11-012023679010.3390/s202367906DoF Pose Estimation of Transparent Object from a Single RGB-D ImageChi Xu0Jiale Chen1Mengyang Yao2Jun Zhou3Lijun Zhang4Yi Liu5School of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaSchool of Automation, China University of Geosciences, Wuhan 430074, ChinaCRRC Zhuzhou Electric Locomotive Co., Ltd. 1 TianXin Road; Zhuzhou 412000, China6DoF object pose estimation is a foundation for many important applications, such as robotic grasping, automatic driving, and so on. However, it is very challenging to estimate 6DoF pose of transparent object which is commonly seen in our daily life, because the optical characteristics of transparent material lead to significant depth error which results in false estimation. To solve this problem, a two-stage approach is proposed to estimate 6DoF pose of transparent object from a single RGB-D image. In the first stage, the influence of the depth error is eliminated by transparent segmentation, surface normal recovering, and RANSAC plane estimation. In the second stage, an extended point-cloud representation is presented to accurately and efficiently estimate object pose. As far as we know, it is the first deep learning based approach which focuses on 6DoF pose estimation of transparent objects from a single RGB-D image. Experimental results show that the proposed approach can effectively estimate 6DoF pose of transparent object, and it out-performs the state-of-the-art baselines by a large margin.https://www.mdpi.com/1424-8220/20/23/67906Dof pose estimationtransparent objecthuman-computer interaction |
| spellingShingle | Chi Xu Jiale Chen Mengyang Yao Jun Zhou Lijun Zhang Yi Liu 6DoF Pose Estimation of Transparent Object from a Single RGB-D Image Sensors 6Dof pose estimation transparent object human-computer interaction |
| title | 6DoF Pose Estimation of Transparent Object from a Single RGB-D Image |
| title_full | 6DoF Pose Estimation of Transparent Object from a Single RGB-D Image |
| title_fullStr | 6DoF Pose Estimation of Transparent Object from a Single RGB-D Image |
| title_full_unstemmed | 6DoF Pose Estimation of Transparent Object from a Single RGB-D Image |
| title_short | 6DoF Pose Estimation of Transparent Object from a Single RGB-D Image |
| title_sort | 6dof pose estimation of transparent object from a single rgb d image |
| topic | 6Dof pose estimation transparent object human-computer interaction |
| url | https://www.mdpi.com/1424-8220/20/23/6790 |
| work_keys_str_mv | AT chixu 6dofposeestimationoftransparentobjectfromasinglergbdimage AT jialechen 6dofposeestimationoftransparentobjectfromasinglergbdimage AT mengyangyao 6dofposeestimationoftransparentobjectfromasinglergbdimage AT junzhou 6dofposeestimationoftransparentobjectfromasinglergbdimage AT lijunzhang 6dofposeestimationoftransparentobjectfromasinglergbdimage AT yiliu 6dofposeestimationoftransparentobjectfromasinglergbdimage |