Приказ основних података о документу
Data Augmentation Methods for Semantic Segmentation-based Mobile Robot Perception System
dc.creator | Jokić, Aleksandar | |
dc.creator | Đokić, Lazar | |
dc.creator | Petrović, Milica | |
dc.creator | Miljković, Zoran | |
dc.date.accessioned | 2023-01-18T13:38:41Z | |
dc.date.available | 2023-01-18T13:38:41Z | |
dc.date.issued | 2022 | |
dc.identifier.issn | 1451-4869 | |
dc.identifier.uri | https://machinery.mas.bg.ac.rs/handle/123456789/3967 | |
dc.description.abstract | Data augmentation has become a standard technique for increasing deep learning models’ accuracy and robustness. Different pixel intensity modifications, image transformations, and noise additions represent the most utilized data augmentation methods. In this paper, a comprehensive evaluation of data augmentation techniques for mobile robot perception system is performed. The perception system based on a deep learning model for semantic segmentation is augmented by 17 techniques to obtain better generalization characteristics during the training process. The deep learning model is trained and tested on a custom dataset and utilized in real-time scenarios. The experimental results show the increment of 6.2 in mIoU (mean Intersection over Union) for the best combination of data augmentation strategies. | sr |
dc.language.iso | en | sr |
dc.relation | info:eu-repo/grantAgreement/MESTD/inst-2020/200105/RS// | |
dc.relation | info:eu-repo/grantAgreement/ScienceFundRS/AI/6523109/RS// | |
dc.rights | openAccess | sr |
dc.rights.uri | https://creativecommons.org/share-your-work/public-domain/cc0/ | |
dc.source | Serbian Journal of Electrical Engineering | sr |
dc.subject | Mobile robot perception system | sr |
dc.subject | Deep learning | sr |
dc.subject | Data augmentation | sr |
dc.subject | Semantic segmentation | sr |
dc.title | Data Augmentation Methods for Semantic Segmentation-based Mobile Robot Perception System | sr |
dc.type | article | sr |
dc.rights.license | BY-NC-ND | sr |
dc.citation.issue | 3 | |
dc.citation.rank | M52 | |
dc.citation.spage | 291-302 | |
dc.citation.volume | 19 | |
dc.identifier.doi | https://doi.org/10.2298/SJEE2203291J | |
dc.identifier.fulltext | http://machinery.mas.bg.ac.rs/bitstream/id/9158/bitstream_9158.pdf | |
dc.type.version | publishedVersion | sr |