Volumetric Object Recognition Using 3-D CNNs on Depth Data
Recognizing 3-D objects has a wide range of application areas from autonomous robots to self-driving vehicles. The popularity of low-cost RGB-D sensors has enabled a rapid progress in 3-D object recognition in the recent years. Most of the existing studies use depth data as an additional channel to...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8328829/ |
| _version_ | 1818331726492991488 |
|---|---|
| author | Ali Caglayan Ahmet Burak Can |
| author_facet | Ali Caglayan Ahmet Burak Can |
| author_sort | Ali Caglayan |
| collection | DOAJ |
| description | Recognizing 3-D objects has a wide range of application areas from autonomous robots to self-driving vehicles. The popularity of low-cost RGB-D sensors has enabled a rapid progress in 3-D object recognition in the recent years. Most of the existing studies use depth data as an additional channel to the RGB channels. Instead of this approach, we propose two volumetric representations to reveal rich 3-D structural information hidden in depth images. We present a 3-D convolutional neural network (CNN)-based object recognition approach, which utilizes these volumetric representations and single and multi-rotational depth images. The 3-D CNN architecture trained to recognize single depth images produces competitive results with the state-of-the-art methods on two publicly available datasets. However, recognition accuracy increases further when the multiple rotations of objects are brought together. Our multirotational 3-D CNN combines information from multiple views of objects to provide rotational invariance and improves the accuracy significantly comparing with the single-rotational approach. The results show that utilizing multiple views of objects can be highly informative for the 3-D CNN-based object recognition. |
| first_indexed | 2024-12-13T13:24:26Z |
| format | Article |
| id | doaj.art-a4ec6b3659ec41b7aeb057644f9583eb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T13:24:26Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a4ec6b3659ec41b7aeb057644f9583eb2022-12-21T23:44:20ZengIEEEIEEE Access2169-35362018-01-016200582006610.1109/ACCESS.2018.28208408328829Volumetric Object Recognition Using 3-D CNNs on Depth DataAli Caglayan0Ahmet Burak Can1https://orcid.org/0000-0002-0101-6878Department of Computer Engineering, Hacettepe University, Beytepe Campus, Ankara, TurkeyDepartment of Computer Engineering, Hacettepe University, Beytepe Campus, Ankara, TurkeyRecognizing 3-D objects has a wide range of application areas from autonomous robots to self-driving vehicles. The popularity of low-cost RGB-D sensors has enabled a rapid progress in 3-D object recognition in the recent years. Most of the existing studies use depth data as an additional channel to the RGB channels. Instead of this approach, we propose two volumetric representations to reveal rich 3-D structural information hidden in depth images. We present a 3-D convolutional neural network (CNN)-based object recognition approach, which utilizes these volumetric representations and single and multi-rotational depth images. The 3-D CNN architecture trained to recognize single depth images produces competitive results with the state-of-the-art methods on two publicly available datasets. However, recognition accuracy increases further when the multiple rotations of objects are brought together. Our multirotational 3-D CNN combines information from multiple views of objects to provide rotational invariance and improves the accuracy significantly comparing with the single-rotational approach. The results show that utilizing multiple views of objects can be highly informative for the 3-D CNN-based object recognition.https://ieeexplore.ieee.org/document/8328829/3-D object recognitionconvolutional neural networksvolumetric representations |
| spellingShingle | Ali Caglayan Ahmet Burak Can Volumetric Object Recognition Using 3-D CNNs on Depth Data IEEE Access 3-D object recognition convolutional neural networks volumetric representations |
| title | Volumetric Object Recognition Using 3-D CNNs on Depth Data |
| title_full | Volumetric Object Recognition Using 3-D CNNs on Depth Data |
| title_fullStr | Volumetric Object Recognition Using 3-D CNNs on Depth Data |
| title_full_unstemmed | Volumetric Object Recognition Using 3-D CNNs on Depth Data |
| title_short | Volumetric Object Recognition Using 3-D CNNs on Depth Data |
| title_sort | volumetric object recognition using 3 d cnns on depth data |
| topic | 3-D object recognition convolutional neural networks volumetric representations |
| url | https://ieeexplore.ieee.org/document/8328829/ |
| work_keys_str_mv | AT alicaglayan volumetricobjectrecognitionusing3dcnnsondepthdata AT ahmetburakcan volumetricobjectrecognitionusing3dcnnsondepthdata |