prikaz prve stranice dokumenta Aplikacija za kontinuiranu detekciju osoba u videosignalu
No public access
undergraduate thesis
Aplikacija za kontinuiranu detekciju osoba u videosignalu
2021. urn:nbn:hr:168:982466
Jelečević, Ljudevit
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Jelečević, Lj. (2021). Aplikacija za kontinuiranu detekciju osoba u videosignalu (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:982466

Jelečević, Ljudevit. "Aplikacija za kontinuiranu detekciju osoba u videosignalu." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:982466

Jelečević, Ljudevit. "Aplikacija za kontinuiranu detekciju osoba u videosignalu." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:982466

Jelečević, Lj. (2021). 'Aplikacija za kontinuiranu detekciju osoba u videosignalu', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 04 February 2025, https://urn.nsk.hr/urn:nbn:hr:168:982466

Jelečević Lj. Aplikacija za kontinuiranu detekciju osoba u videosignalu [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2025 February 04] Available at: https://urn.nsk.hr/urn:nbn:hr:168:982466

Lj. Jelečević, "Aplikacija za kontinuiranu detekciju osoba u videosignalu", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:982466

Please login to the repository to save this object to your list.
Metadata
TitleAplikacija za kontinuiranu detekciju osoba u videosignalu
Title (english)Application for continuous person detection in the video signal
AuthorLjudevit Jelečević
MentorMarko Horvat (mentor)
Committee memberMarko Horvat (predsjednik povjerenstva)
Committee memberVedran Mornar (član povjerenstva)
Committee memberMelita Fertalj (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-09-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Aplikacija za kontinuiranu detekciju ljudi u videosignalu koja koristi konvolucij- ske neuronske mreže Yolov3 i CSRNet kako bi detektirala lokaciju i broj ljudi na vi- deosignalu. Podaci prikupljeni obradom videosignala prikazuju se unutar grafičkom korisničkog sučelja i spremaju u lokalnu SQLite bazu podataka. Aplikacija je evalu- irana pomoću WIDER Attribute i Shanghai Tech datasetova te novog dataseta nastalog kombinacijom izmed̄u WIDER Attribute i Shanghai Tech datasetova kako bi aplikacija mogla biti evaluirana u većem skupu okolnostima u kojima se može naći i kako bi se korištene konvolucijske neuronske mreže mogle bolje usporediti.
Abstract (english)
Real-time video people detection application which uses convolutional neural networks Yolov3 and CSRNet for people detection and people counting in video. Data yielded by convolutional neural networks is displayed inside graphical user interface and stored inside a local SQLite database. Application is evaluated using Wider Attribute, Shanghai tech datasets and a new dataset created by combining WIDER Attribute i Shanghai Tech datasets so that application could be evaluated in wider range of situations and the two convolutional neural networks could be better compared.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:982466
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 on2023-01-14 20:40:21