3D Object Detection and Annotation
| dc.contributor.author | Stamatoudis, Ioannis | en |
| dc.date.accessioned | 2021-07-01T09:24:56Z | |
| dc.date.available | 2021-07-01T09:24:56Z | |
| dc.date.issued | 2021-07-01 | |
| dc.identifier.uri | https://repository.ihu.edu.gr//xmlui/handle/11544/29712 | |
| dc.rights | Default License | |
| dc.subject | 3D object detection | en |
| dc.subject | 3D object annotation | en |
| dc.title | 3D Object Detection and Annotation | en |
| heal.abstract | The area of deep learning with 3d data is underexplored due to the fact that only lately 3d datasets become available. One type of 3d data is point clouds that usually are created by lidar sensors. There is intensive research, in the recent years, on the field of object detection and annotation with 3d data and many different state-of-the-art methods have been presented. The purpose behind this thesis, is to try to improve one of these methods, by combining it with parts of different methods or use it in parallel with another method. The motivation behind this thesis, is to research if it is possible to get better results by modifying a method. An application of this research is that there could be created a guideline for improving an already successful method. The selected method in 3d object detection and annotation to be modified was Pointpillars. One part of the exploration was to substitute part of this method with parts from different methods and test its performance. The selected parts to be added were residual networks and inception networks, that were successful in 2d object recognition. Pointpillars, first creates a pseudo-image from 3d data and then uses 2d convolutions to recognize patterns, and at this stage the above parts can be introduced. The other part of the exploration is to train parallelly with another method. The selected method was Complex YOLO, and the recognized features of each method were combined and then it was performed detection of objects. The goal is to check if the two parallel methods can outperform the original Pointpillars method. The results of the experiments showed that there was not improvement in the results both with the modifications and the parallel training. Except that, some of the modified models were more computationally expensive and inefficient compared to the original method. | en |
| heal.academicPublisher | IHU | en |
| heal.academicPublisherID | ihu | en_US |
| heal.access | free | en_US |
| heal.advisorName | Diamantaras, Konstantinos | en |
| heal.committeeMemberName | Karapiperis | en |
| heal.committeeMemberName | Akritidis | en |
| heal.dateAvailable | 2021-05-11 | |
| heal.language | en | en_US |
| heal.license | http://creativecommons.org/licenses/by-nc/4.0 | en_US |
| heal.publicationDate | 2021-05-11 | |
| heal.recordProvider | School of Science and Technology, MSc in Data Science | en_US |
| heal.type | masterThesis | en_US |
Αρχεία
Πρωτότυπος φάκελος/πακέτο
1 - 1 από 1
Φόρτωση...
- Ονομα:
- i.stamatoudis_datasc_10_5_2021.pdf
- Μέγεθος:
- 2.43 MB
- Μορφότυπο:
- Adobe Portable Document Format
- Περιγραφή:
Φάκελος/Πακέτο αδειών
1 - 1 από 1
Δεν υπάρχει διαθέσιμη μικρογραφία
- Ονομα:
- license.txt
- Μέγεθος:
- 5.55 KB
- Μορφότυπο:
- Item-specific license agreed upon to submission
- Περιγραφή: