prikaz prve stranice dokumenta Stereo vizualna lokalizacija mete u 3D prostoru
No public access
undergraduate thesis
Stereo vizualna lokalizacija mete u 3D prostoru
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:350230
Stracenski, Danijel
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Stracenski, D. (2020). Stereo vizualna lokalizacija mete u 3D prostoru (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:350230

Stracenski, Danijel. "Stereo vizualna lokalizacija mete u 3D prostoru." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:350230

Stracenski, Danijel. "Stereo vizualna lokalizacija mete u 3D prostoru." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:350230

Stracenski, D. (2020). 'Stereo vizualna lokalizacija mete u 3D prostoru', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:350230

Stracenski D. Stereo vizualna lokalizacija mete u 3D prostoru [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:168:350230

D. Stracenski, "Stereo vizualna lokalizacija mete u 3D prostoru", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:350230

Metadata
TitleStereo vizualna lokalizacija mete u 3D prostoru
Title (english)Stereo visual target localization in 3D space
AuthorDanijel Stracenski
MentorMarija Seder (mentor)
Committee memberMarija Seder (predsjednik povjerenstva)
Committee memberGoran Popović (član povjerenstva)
Committee memberAntea Hadviger (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Cilj ovoga rada je riješiti problem lokalizacije predmeta u prostoru pomoću stereo računarskog vida. Kao implementacija rješenja ovoga problema odabrana je autonomna navigacija robota do pokretnog cilja. U okviru rada, najprije je pojašnjena funkcionalnost RealSense D435 stereo kamere te komunikacija programa za navigaciju s robotom Turtlebot3 Waffle pomoću ROS-a. Nakon toga je objašnjen princip dobivanja udaljenosti predmeta iz slike dispariteta dobivene stereo kamerom. Kako bi dobili lokaciju predmeta u trodimenzionalnom prostoru, potrebno je poznavati njegovu lokaciju na slici što ostvarujemo praćenjem. Implementirano je dvostruko praćenje putem vizualnih svojstava predmeta i pomoću apriltag oznaka. Iz sada poznatih lokacija objekata na slici prijelazi se na samu lokalizaciju smještavanjem objekata u metrični koordinatni sustav kamere. Nadalje se iz pozicija robota i cilja dobiva vektor pomaka koji svojom orijentacijom i duljinom pokazuje ima li potrebe bilo za rotacijom ili za translacijom. Ovim postupkom robot je spreman na moguće nenadane kretnje cilja te u konačnici dolazi do odredišta.
Abstract (english)
The main goal of this paper is to solve the problem of target localization with stereo imaging. The solution is implemented on the autonomous navigation of the robot to the moving target. Firstly, this paper explains the functionality of the RealSense D435 stereo camera and shows the basic structure of ROS aided communication between the robot and the main navigation program. This is followed by the principle of getting distance from a disparity image. To be able to localize objects in three-dimensional space we first have to know its location on the image which is done with the object tracking. Double tracking is implemented for the sake of accuracy, with visual attributes tracking and primary apriltag tracking. From known image positions of objects, we can now localize them in the metric coordinate system of the camera. Secondly, from the location of the robot and target, we are calculating the displacement vector whose orientation and length give needed rotation and transition. This way the robot is ready for possible unexpected movement from the target and in the end it arrives at the target destination.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:350230
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 21:42:15