prikaz prve stranice dokumenta Detekcija anomalnih sljedova poza osoba difuzijskim otklanjanjem šuma
  Download
PDF 2.06 MB
undergraduate thesis
Detekcija anomalnih sljedova poza osoba difuzijskim otklanjanjem šuma
2024. urn:nbn:hr:168:293902
Kukolj, Marko
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Kukolj, M. (2024). Detekcija anomalnih sljedova poza osoba difuzijskim otklanjanjem šuma (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:293902

Kukolj, Marko. "Detekcija anomalnih sljedova poza osoba difuzijskim otklanjanjem šuma." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:293902

Kukolj, Marko. "Detekcija anomalnih sljedova poza osoba difuzijskim otklanjanjem šuma." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:293902

Kukolj, M. (2024). 'Detekcija anomalnih sljedova poza osoba difuzijskim otklanjanjem šuma', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 14 March 2025, https://urn.nsk.hr/urn:nbn:hr:168:293902

Kukolj M. Detekcija anomalnih sljedova poza osoba difuzijskim otklanjanjem šuma [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2025 March 14] Available at: https://urn.nsk.hr/urn:nbn:hr:168:293902

M. Kukolj, "Detekcija anomalnih sljedova poza osoba difuzijskim otklanjanjem šuma", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:293902

Please login to the repository to save this object to your list.
Metadata
TitleDetekcija anomalnih sljedova poza osoba difuzijskim otklanjanjem šuma
Title (english)Detection of anomalous sequences of human poses by denoising diffusion
AuthorMarko Kukolj
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberAnja Delić (član povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2024-09-11, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Raspoznavanje kretnji osoba bitan je problem u području računalnog vida, koji nije praktično modelirati nadziranim učenjem. Ovaj rad promatra alternativni pristup utemeljen na detekciji anomalnih poza koristeći skupove sljedova za učenje. Model anomalne poze prepoznaje modeliranjem predviđanja stvarnih kretnji te odstupanjem predviđene kretnje od stvarne kretnje.
Abstract (english)
Recognizing movement of people is an important problem in the field of computer vision that is not practical to model with supervised learning. This work looks at an alternative approach based on the detection of anomalous poses using sets of sequences for learning. The model recognizes anomalous poses by modeling the prediction of real movement and using the deviation between the prediction and the actual movement.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:293902
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Public note
Created on2024-10-12 21:15:14