prikaz prve stranice dokumenta Izlučivanje kandidata u dvoprolaznim lokalizacijskim modelima
No public access
undergraduate thesis
Izlučivanje kandidata u dvoprolaznim lokalizacijskim modelima
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:408498
Pleše, Leo
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pleše, L. (2020). Izlučivanje kandidata u dvoprolaznim lokalizacijskim modelima (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:408498

Pleše, Leo. "Izlučivanje kandidata u dvoprolaznim lokalizacijskim modelima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:408498

Pleše, Leo. "Izlučivanje kandidata u dvoprolaznim lokalizacijskim modelima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:408498

Pleše, L. (2020). 'Izlučivanje kandidata u dvoprolaznim lokalizacijskim modelima', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:408498

Pleše L. Izlučivanje kandidata u dvoprolaznim lokalizacijskim modelima [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 November 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:408498

L. Pleše, "Izlučivanje kandidata u dvoprolaznim lokalizacijskim modelima", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:408498

Metadata
TitleIzlučivanje kandidata u dvoprolaznim lokalizacijskim modelima
Title (english)Candidate extraction in two-stage localization models
AuthorLeo Pleše
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMladen Karan (član povjerenstva)
Committee memberJosip Šarić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Postoje mnogi modeli lokalizacije objekata: mi smo odabrali RPN. RPN je dvoprolazni lokalizacijski model duboke konvolucijske neronske mreže koji paralelno predviđa klasu objekta u razred objekt/pozadina te položaj i dimenzije okvira objekata. Pritom se oslanja na model FPN koji radi i prolaz konvolucijskom mrežom u suprotnom smjeru čime izlučuje još značajki spojivši lateralnim vezama mape značajki tih prolaza – lokalne informacije iz prvog i semantički vrednija svojstva iz drugog. Za osnovu FPN-a odabrali smo arhitekturu ResNet-34 koja rješava problem degradacije točnosti na skupu za učenje uslijed prevelike dubine konvolucijske mreže. Proučili smo ove modele i implementirali RPN. Naučili smo model na više slika iz podatkovnog skupa PASCAL VOC 2012 pojedinačno i eksperimentalno metrikom AR1000 potvrdili da učinkovito označava interesne regije okvirima kao rezultat učenja pozicija i dimenzija okvira radi još bolje prilagodbe objektu. Na kraju smo algoritmom NMS uspješno odabrali okvire koji se prema IoU najbolje preklapaju s točnima.
Abstract (english)
There are many object localization objects: we have chosen RPN. RPN is a two-stage convolutional neural network localization model which in parallel predicts an object's class into object/background as well as position and dimension of its bounding boxes. Thereat it relies on FPN model, which does an additional pass through convolutional network in the opposite direction, which extracts more features by having lateral connections between the feature maps from the two passes – local information from the first and semantically more valuable features from the second one. As for the FPN groundwork we have chosen ResNet-34 architecture, which solves the training accuracy degradation problem appearing as a result of too large convolutional network depth. We have studied these models and implemented RPN. We have trained the model on multiple images from the PASCAL VOC 2012 dataset individually and by using AR1000 for the baseline experimentally confirmed it efficiently labels regions of interest with bounding boxes as a result of learning anchor positions and dimensions with aim of even better adjustment to the object. At the end, using NMS algorithm we have successfully selected the anchors which according to IoU have the largest overlap with the ground truth ones.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:408498
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 on2023-01-13 15:54:00