Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorBartolovic, Eduard
dc.contributor.authorHöfer, Tobias
dc.contributor.authorHage, Clemens
dc.contributor.authorNischwitz, Alfred
dc.contributor.editorSkala, Václav
dc.date.accessioned2024-07-29T18:33:32Z-
dc.date.available2024-07-29T18:33:32Z-
dc.date.issued2024
dc.identifier.citationWSCG 2024: full papers proceedings: 32. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 263-272.en
dc.identifier.issn2464–4625 (online)
dc.identifier.issn2464–4617 (print)
dc.identifier.urihttp://hdl.handle.net/11025/57398
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencyen
dc.rights© Václav Skala - UNION Agencyen
dc.subjectsyntetické generování datcs
dc.subjectaugmentace datcs
dc.subjectrandomizace doménycs
dc.subjectdetekce objektucs
dc.subjectYOLOv5cs
dc.subjectSegmentAnythingcs
dc.titleFrom Sources to Solutions: Enhancing Object Detection Models through Synthetic Dataen
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedObject detection, a fundamental task in computer vision, plays a crucial role in various applications such as au tonomous driving, surveillance, and robotics. However, training models for this task require vast amounts of high-quality data, often involving labor-intensive manual labeling. Synthetic data, a promising alternative, re mains an active area of research. This paper presents a comprehensive exploration of different object sources for the use of synthetic data in enhancing object detection models. We investigate various synthetic data gen eration techniques to implant objects into a scene, with a focus on enhancing training data diversity. These ob jects are either gathered from the training dataset itself using SegmentAnything as a new supervised self aug mentation technique or imported from external sources, including a photobox with a rotating table and web scraping of online shops. Moreover, our study delves into the development of a placement logic that gradu ally evolves from placing objects randomly to placing objects in physically correct orientations to mimic the real world data. We investigate the use of different blending techniques. The outcome of our study demon strates that synthetic images, when integrated with an existing real training set, substantially improve the ob ject recognition accuracy of the model without compromising inference time. Our code can be found at https://github.com/EduardBartolovic/synthetic-data-generationen
dc.subject.translatedsynthetic data generationen
dc.subject.translateddata augmentationen
dc.subject.translateddomain randomizationen
dc.subject.translatedobject detectionen
dc.subject.translatedYOLOv5en
dc.subject.translatedSegmentAnythingen
dc.identifier.doihttps://doi.org/10.24132/10.24132/CSRN.3401.27
dc.type.statusPeer revieweden
Vyskytuje se v kolekcích:WSCG 2024: Full Papers Proceedings

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
C59-2024.pdfPlný text3,65 MBAdobe PDFZobrazit/otevřít
Zobrazit minimální záznam Zobrazit statistiky


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/57398

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.

hledání
navigace
  1. DSpace at University of West Bohemia
  2. Publikace ZČU / UWB Publications
  3. Sborníky ZČU / UWB Proceedings
  4. WSCG: Full Papers
  5. WSCG 2024: Full Papers Proceedings