prikaz prve stranice dokumenta Duboki modeli za semantičku segmentaciju i detekciju anomalija
No public access
undergraduate thesis
Duboki modeli za semantičku segmentaciju i detekciju anomalija
2023. urn:nbn:hr:168:202303
Čengić, Marko
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Čengić, M. (2023). Duboki modeli za semantičku segmentaciju i detekciju anomalija (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:202303

Čengić, Marko. "Duboki modeli za semantičku segmentaciju i detekciju anomalija." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:202303

Čengić, Marko. "Duboki modeli za semantičku segmentaciju i detekciju anomalija." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:202303

Čengić, M. (2023). 'Duboki modeli za semantičku segmentaciju i detekciju anomalija', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 13 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:202303

Čengić M. Duboki modeli za semantičku segmentaciju i detekciju anomalija [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 November 13] Available at: https://urn.nsk.hr/urn:nbn:hr:168:202303

M. Čengić, "Duboki modeli za semantičku segmentaciju i detekciju anomalija", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:202303

Please login to the repository to save this object to your list.
Metadata
TitleDuboki modeli za semantičku segmentaciju i detekciju anomalija
Title (english)Deep models for semantic segmentation and anomaly detection
AuthorMarko Čengić
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarin Kačan (član povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-06, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu primijenjene su metode dubokog učenja za segmentaciju anomalija. Specifično je korišten model arhitekture Swiftnet sa s ljestvičastim naduzorkovanjem. Nadodane su na njega tri metode detekcije anomalija: maksimalni softmax, maksimalni logit i entropija Takav je model onda korišten za detekciju anomalija na cesti.
Abstract (english)
In this work, deep learning methods were applied for anomaly segmentation. The Swiftnet architecture model with ladder oversampling was specifically used. Three anomaly detection methods were added to it: max-softmax, max-logit and entropy. Such a model was then used to detect anomalies on the road.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:202303
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 conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-07-13 09:59:47