Realworld 3D Object Recognition Using a 3D Extension of the HOG Descriptor and a Depth Camera
3D object recognition is an generic task in robotics and autonomous vehicles. In this paper, we propose a 3D object recognition approach using a 3D extension of the histogram-of-gradients object descriptor with data captured with a depth camera. The presented method makes use of synthetic objects fo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/3/910 |
| _version_ | 1797406035830374400 |
|---|---|
| author | Cristian Vilar Silvia Krug Mattias O’Nils |
| author_facet | Cristian Vilar Silvia Krug Mattias O’Nils |
| author_sort | Cristian Vilar |
| collection | DOAJ |
| description | 3D object recognition is an generic task in robotics and autonomous vehicles. In this paper, we propose a 3D object recognition approach using a 3D extension of the histogram-of-gradients object descriptor with data captured with a depth camera. The presented method makes use of synthetic objects for training the object classifier, and classify real objects captured by the depth camera. The preprocessing methods include operations to achieve rotational invariance as well as to maximize the recognition accuracy while reducing the feature dimensionality at the same time. By studying different preprocessing options, we show challenges that need to be addressed when moving from synthetic to real data. The recognition performance was evaluated with a real dataset captured by a depth camera and the results show a maximum recognition accuracy of 81.5%. |
| first_indexed | 2024-03-09T03:18:54Z |
| format | Article |
| id | doaj.art-6b923cc292004c33badf6493057ba247 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T03:18:54Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6b923cc292004c33badf6493057ba2472023-12-03T15:13:12ZengMDPI AGSensors1424-82202021-01-0121391010.3390/s21030910Realworld 3D Object Recognition Using a 3D Extension of the HOG Descriptor and a Depth CameraCristian Vilar0Silvia Krug1Mattias O’Nils2Department of Electronics Design, Mid Sweden University, Holmgatan 10, 851 70 Sundsvall, SwedenDepartment of Electronics Design, Mid Sweden University, Holmgatan 10, 851 70 Sundsvall, SwedenDepartment of Electronics Design, Mid Sweden University, Holmgatan 10, 851 70 Sundsvall, Sweden3D object recognition is an generic task in robotics and autonomous vehicles. In this paper, we propose a 3D object recognition approach using a 3D extension of the histogram-of-gradients object descriptor with data captured with a depth camera. The presented method makes use of synthetic objects for training the object classifier, and classify real objects captured by the depth camera. The preprocessing methods include operations to achieve rotational invariance as well as to maximize the recognition accuracy while reducing the feature dimensionality at the same time. By studying different preprocessing options, we show challenges that need to be addressed when moving from synthetic to real data. The recognition performance was evaluated with a real dataset captured by a depth camera and the results show a maximum recognition accuracy of 81.5%.https://www.mdpi.com/1424-8220/21/3/9103D object recognition3DHOGhistogram-of-gradientsModelNet40ModelNet10feature descriptor |
| spellingShingle | Cristian Vilar Silvia Krug Mattias O’Nils Realworld 3D Object Recognition Using a 3D Extension of the HOG Descriptor and a Depth Camera Sensors 3D object recognition 3DHOG histogram-of-gradients ModelNet40 ModelNet10 feature descriptor |
| title | Realworld 3D Object Recognition Using a 3D Extension of the HOG Descriptor and a Depth Camera |
| title_full | Realworld 3D Object Recognition Using a 3D Extension of the HOG Descriptor and a Depth Camera |
| title_fullStr | Realworld 3D Object Recognition Using a 3D Extension of the HOG Descriptor and a Depth Camera |
| title_full_unstemmed | Realworld 3D Object Recognition Using a 3D Extension of the HOG Descriptor and a Depth Camera |
| title_short | Realworld 3D Object Recognition Using a 3D Extension of the HOG Descriptor and a Depth Camera |
| title_sort | realworld 3d object recognition using a 3d extension of the hog descriptor and a depth camera |
| topic | 3D object recognition 3DHOG histogram-of-gradients ModelNet40 ModelNet10 feature descriptor |
| url | https://www.mdpi.com/1424-8220/21/3/910 |
| work_keys_str_mv | AT cristianvilar realworld3dobjectrecognitionusinga3dextensionofthehogdescriptorandadepthcamera AT silviakrug realworld3dobjectrecognitionusinga3dextensionofthehogdescriptorandadepthcamera AT mattiasonils realworld3dobjectrecognitionusinga3dextensionofthehogdescriptorandadepthcamera |