|
|
|
|
| LEADER |
04242na a2200241 4500 |
| 003 |
HR-ZaFER |
| 005 |
20160714123504.0 |
| 008 |
160221s2015 ci ||||| m||| 00| 0 hr d |
| 035 |
|
|
|a (HR-ZaFER)ferid2618
|
| 040 |
|
|
|a HR-ZaFER
|b hrv
|c HR-ZaFER
|e ppiak
|
| 100 |
1 |
|
|a Soldo, Antonio
|9 37557
|
| 245 |
1 |
0 |
|a Sustav za geometrijsku transformaciju i povezivanje dijelova slika :
|b diplomski rad /
|c Antonio Soldo ; [mentor Damir Seršić].
|
| 246 |
1 |
|
|a System for geometric transformation and image stitching
|i Naslov na engleskom:
|
| 260 |
|
|
|a Zagreb,
|b A. Soldo,
|c 2015.
|
| 300 |
|
|
|a 40 str. ;
|c 30 cm +
|e CD-ROM
|
| 502 |
|
|
|b diplomski studij
|c Fakultet elektrotehnike i računarstva u Zagrebu
|g smjer: Obradba informacija, šifra smjera: 51, datum predaje: 2015-06-30, datum završetka: 2015-07-07
|
| 520 |
3 |
|
|a Sažetak na hrvatskom: Tržište računalne i mobilne industrije danas je tržište najbržeg rasta i razvoja, a u zadnjih nekoliko godina rapidno raste interes za uređaje koji imaju mogućnost potpunog uranjanja u virtualni svijet. Iako se tehnologija najviše povezuje uz videoigrice, platforma nudi nove mogućnosti za video, internet oglašavanje i još mnogo više. Jedna od mogućnosti koje ta tehnologija može omogućiti je i ostvarivanje virtualnog razgovora, s tim da osoba s kojom razgovaramo bude animirani lik po želji. Trenutno to nije moguće jer je pola lica prekriveno HMD uređajem. Iako se taj problem može vrlo lako riješiti, ostaje još jedan problem. Naime, nijedan današnji program za praćenje lica nema mogućnost praćenja samo donje polovice lica. Ovaj rad zaobilazi navedenu problematiku tako što pretpostavlja jednu kameru na HMD uređaju koja snima donji dio lica, a onda takvu sliku spaja s unaprijed određenim ljudskim licem pazeći da to preklapanje bude što prirodnije. Prije nego što se uopće počnu obrađivati slikovni okviri kamere, kamera se kalibrira uz pretpostavku radijalne i tangencijalne distorzije. Zatim se na svakom okviru odvija poništenje distorzije koeficijentima dobivenim u procesu kalibracije. Nakon toga slijedi operacija modeliranja histograma prema histogramu pozadine kako bi varijacije u kontrastu i osvjetljenju bile što sličnije pozadini. Konačno se takva slika spaja u jednu cjelinu pomoću binarne maske zaglađene Gaussovim filtrom. Predloženo rješenje ne ovisi o specifičnom HMD uređaju niti o nekoj posebnoj kameri.
|
| 520 |
3 |
|
|a Sažetak na engleskom: Today, market with one of the highest growth and development is computer and mobile industry market, and in last few years there is rapid interest in devices that have the possibility of total immersion into a virtual world. Although this technology is usually linked with video games, platform provides new possibilites for video, e-advertising and many more. One of the possibilities that this technology offers is also virtual chatting, where the person we are talking to can be animated character as desired. That is not currently possible, because half of the face is covered with HMD. Although that problem can be easily overcomed, we still have one problem to solve. Namely, none of todays softwares for facial tracking have the ability to track only lower part of human face. This paper bypasses stated problems by assuming one camera mounted on HMD that records only lower part of human face, and then it joins that picture with predefined image of human face ensuring that given overlay looks as natural as possible. Before any frame is processed, camera is calibrated with assumption of radial and tangential distortion. After that, every frame is undistorted by coefficients calculated in calibration process. Afterwards, histogram of every frame is modelled towards histogram of background so the contrast and brightness would be more similar to the background. Finally, processed image is merged into a whole using binary mask that is filtered with Gaussian kernel. Given solution is independent of specific HMD or special sort of camera.
|
| 653 |
|
1 |
|a kalibracija kamere
|a modeliranje histograma
|a zaglađivanje
|a Gaussov filtar
|
| 653 |
|
1 |
|a camera calibration, histogram specification, smoothing, Gaussian kernel
|
| 700 |
1 |
|
|a Seršić, Damir
|4 ths
|9 37558
|
| 942 |
|
|
|c Y
|2 udc
|
| 999 |
|
|
|c 46493
|d 46493
|