Sökning: onr:"swepub:oai:lup.lub.lu.se:1c75c100-5dc0-465a-85c3-d076f7b584a1" >
A Shared Pose Regre...
A Shared Pose Regression Network for Pose Estimation of Objects from RGB Images
-
- Hein Bengtson, Stefan (författare)
- Aalborg University
-
- Åström, Hampus (författare)
- Lund University,Lunds universitet,Robotik och Semantiska System,Institutionen för datavetenskap,Institutioner vid LTH,Lunds Tekniska Högskola,Robotics and Semantic Systems,Department of Computer Science,Departments at LTH,Faculty of Engineering, LTH
-
- Moeslund, Thomas B. (författare)
- Aalborg University
-
visa fler...
-
- Topp, Elin A. (författare)
- Lund University,Lunds universitet,Robotik och Semantiska System,Institutionen för datavetenskap,Institutioner vid LTH,Lunds Tekniska Högskola,Robotics and Semantic Systems,Department of Computer Science,Departments at LTH,Faculty of Engineering, LTH
-
- Krueger, Volker (författare)
- Lund University,Lunds universitet,Institutionen för datavetenskap,Institutioner vid LTH,Lunds Tekniska Högskola,Department of Computer Science,Departments at LTH,Faculty of Engineering, LTH
-
visa färre...
-
(creator_code:org_t)
- 2022
- 2022
- Engelska 8 s.
-
Ingår i: IEEE/RSJ International Conference on Signal Image Technology & Internet Based Systems (SITIS). - 9781665464963 - 9781665464956
- Relaterad länk:
-
http://dx.doi.org/10...
-
visa fler...
-
https://lup.lub.lu.s...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- In this paper we propose a shared regression network to jointly estimate the pose of multiple objects, replacing multiple object-specific solutions. We demonstrate that this shared network can outperform other similar approaches that rely on multiple object-specific models by evaluating it on the TLESS dataset using the VSD (Visible Surface Discrepancy). Our approach offers a less complex solution, with fewer parameters, lower memory consumption and less training required. Furthermore, it inherently handles symmetric objects by using a depth-based loss during training and can predict in real-time. Finally, we show how our proposed pipeline can be used for fine-tuning a feature extractor jointly on all objects while training the shared pose regression network. This fine-tuning process improves the pose estimation performance.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Training
- Measurement
- Solid modeling
- image resolution
- Pose estimation
- neural networks
- memory management
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas