Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/35821
Title: | Real-time Detection of 2D Tool Landmarks with Synthetic Training Data | Authors: | VANHERLE, Bram PUT, Jeroen MICHIELS, Nick VAN REETH, Frank |
Issue Date: | 2021 | Publisher: | Scitepress | Source: | Galambos, Péter; Kayacan, Erdal (Ed.). Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems, Scitepress, p. 40 -47 (Art N° 4) | Abstract: | In this paper a deep learning architecture is presented that can, in real time, detect the 2D locations of certain landmarks of physical tools, such as a hammer or screwdriver. To avoid the labor of manual labeling, the network is trained on synthetically generated data. Training computer vision models on computer generated images, while still achieving good accuracy on real images, is a challenge due to the difference in domain. The proposed method uses an advanced rendering method in combination with transfer learning and an intermediate supervision architecture to address this problem. It is shown that the model presented in this paper, named Intermediate Heatmap Model (IHM), generalizes to real images when trained on synthetic data. To avoid the need for an exact textured 3D model of the tool in question, it is shown that the model will generalize to an unseen tool when trained on a set of different 3D models of the same type of tool. IHM is compared to two existing approaches to keypoint detection and it is shown that it outperforms those at detecting tool landmarks, trained on synthetic data. | Keywords: | Object Keypoint Detection;Deep Learning;Synthetic Data Generation | Document URI: | http://hdl.handle.net/1942/35821 | ISBN: | 978-989-758-537-1 | DOI: | 10.5220/0010689900003061 | ISI #: | 000795862700004 | Rights: | CC BY-NC-ND 4.0 | Category: | C1 | Type: | Proceedings Paper | Validations: | ecoom 2023 |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
106899.pdf | Published version | 4.95 MB | Adobe PDF | View/Open |
WEB OF SCIENCETM
Citations
1
checked on Aug 6, 2024
Page view(s)
176
checked on May 24, 2022
Download(s)
42
checked on May 24, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.