prikaz prve stranice dokumenta Prepoznavanje objekata i njihovih dijelova na složenim scenama
  Download
PDF 6.53 MB
master's thesis
Prepoznavanje objekata i njihovih dijelova na složenim scenama
2021. urn:nbn:hr:200:937325
Varga, Hrvoje
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Cite this document

Varga, H. (2021). Prepoznavanje objekata i njihovih dijelova na složenim scenama (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:937325

Varga, Hrvoje. "Prepoznavanje objekata i njihovih dijelova na složenim scenama." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:937325

Varga, Hrvoje. "Prepoznavanje objekata i njihovih dijelova na složenim scenama." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:937325

Varga, H. (2021). 'Prepoznavanje objekata i njihovih dijelova na složenim scenama', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 27 January 2025, https://urn.nsk.hr/urn:nbn:hr:200:937325

Varga H. Prepoznavanje objekata i njihovih dijelova na složenim scenama [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2021 [cited 2025 January 27] Available at: https://urn.nsk.hr/urn:nbn:hr:200:937325

H. Varga, "Prepoznavanje objekata i njihovih dijelova na složenim scenama", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:200:937325

Please login to the repository to save this object to your list.
Metadata
TitlePrepoznavanje objekata i njihovih dijelova na složenim scenama
Title (english)Recognition of Objects and Their Parts on Complex Scenes
AuthorHrvoje Varga
MentorRobert Cupec (mentor)
Committee memberRobert Cupec (predsjednik povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
Committee memberEmmanuel Karlo Nyarko (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Computer Engineering and Automation)
(Chair of Automation and Robotics)
Osijek
Defense date and country2021-09-30, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovom diplomskom radu opisan je sustav za detekciju i klasifikaciju objekata na RGB-D slikama snimljenim 3D kamerom, te određivanje mjesta na površini objekta prikladnih za hvatanje objekta od strane robota u svrhu robotske manipulacije. YOLO mreža koja detektira objekte na slikama integrirana je s VolumeNet algoritmom koji uz klasifikaciju objekata predlaže prikladan položaj dohvaćanja određenog objekta sa slike. YOLO mreža vraća kao izlaz granični okvir objekata zadanih klasa. Postavljeni su uvjeti za odabir odgovarajućeg graničnog okvira u slučaju da mreža na jednoj slici pronađe više objekta, tako da vraća samo jedan objekt očekivane veličine koja se nalazi blizu središta slike. Podatak o poziciji ciljnog objekta na slici dobiven YOLO mrežom predstavlja ulaz u VolumeNet.
Abstract (english)
This thesis describes a system for detecting and classifying objects on RGB-D images captured by a 3D camera and determining places on the surface of the object suitable for grasping the object by robots for robotic manipulation. The YOLO network that detects objects in images is integrated with the VolumeNet algorithm, which, along with object classification, returns an appropriate position for grasping a target object. The YOLO network returns the bounding box of instances of given classes as output. In the cases where the network detects more than one object, only one object of the expected size that is close to the centre of the image is considered. The position data of the target object in the image obtained by the YOLO network represents the input to the VolumeNet.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:937325
Study programmeTitle: UNIVERSITY STUDY AUTOMOBILE COMPUTER AND COMMUNICATION
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka automobilskog računarstva i komunikacija (magistar/magistra inženjer/inženjerka automobilskog računarstva i komunikacija)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2021-11-24 12:29:17