prikaz prve stranice dokumenta Detekcija i brojanje ljudi u nizu slika
No public access
master's thesis
Detekcija i brojanje ljudi u nizu slika
2018. urn:nbn:hr:168:830584
Karužić, Katarina
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Karužić, K. (2018). Detekcija i brojanje ljudi u nizu slika (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:830584

Karužić, Katarina. "Detekcija i brojanje ljudi u nizu slika." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:830584

Karužić, Katarina. "Detekcija i brojanje ljudi u nizu slika." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:830584

Karužić, K. (2018). 'Detekcija i brojanje ljudi u nizu slika', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 11 April 2024, https://urn.nsk.hr/urn:nbn:hr:168:830584

Karužić K. Detekcija i brojanje ljudi u nizu slika [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 April 11] Available at: https://urn.nsk.hr/urn:nbn:hr:168:830584

K. Karužić, "Detekcija i brojanje ljudi u nizu slika", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:830584

Please login to the repository to save this object to your list.
Metadata
TitleDetekcija i brojanje ljudi u nizu slika
Title (english)Detection and Counting of People in Image Sequences
AuthorKatarina Karužić
MentorSven Lončarić (mentor)
Committee memberSven Lončarić (predsjednik povjerenstva)
Committee memberMarko Subašić (član povjerenstva)
Committee memberTomislav Petković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-03, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U sklopu ovog rada proučeni su algoritmi za detekciju lica, te metode za praćenje, odnosno spajanje detekcija u nizu slika. Odabrana su tri algoritma za detekciju lica: Viola-Jones, MTCNN i TinyFace, koji su opisani u radu. Također je opisana i metoda za kreiranje trajektorija na temelju detekcija u nizu slika koja koristi Jaccardov indeks sličnosti i rješenje problema dodjeljivanja za uparivanje detekcija između dvije slike. Brojanje je provedeno pomoću ručno unesene linije za brojanje ili automatski izračunate na temelju dominantnog smjera trajektorija.
Abstract (english)
This paper examines algorithms for face detection, methods for object tracking and connecting detected faces in series of pictures. Three algorithms are chosen and described in this paper: Viola-Jones algorithm, MTCNN and TinyFace. Also is described method for creating trajectories based on detections in series of pictures, which uses Jaccard similarity index and assignment problem to connect detections between to images. Counting is done with manually inserted counting line or with automatically calculated line based on dominant direction of trajectories.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:830584
Study programmeTitle: Information and Communication Technology
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-13 21:27:08