Detekcija položaja pikado puščic s pomočjo računalniškega vida

Dimc, Simon (author), Solina, Franc (mentor)

Računalniški vid se uspešno uporablja v športu za namene, kot so sledenje igralcev in predmetov, pomoč pri sojenju in izboljšanje prenosa športa. Kjer pa se do sedaj še ne uporablja, je pri jekleni različici športa pikado. Detekcija položaja pikado puščic bi omogočala samodejno štetje in beleženje statistike metov. V diplomskem delu izdelamo dva prototipa za detekcijo in računanje položaja puščic. Oba prototipa uporabljata sistem treh kamer, ki so usmerjene proti pikado tarči. Pri obeh prototipih namesto zaznavanja puščic, zaznavamo barvni trup puščic. Zaznanim trupom izračunamo orientacijsko premico, ki določa usmerjenost puščice. Prvi prototip uporablja odstranjevanje ozadja in homografijo. Na ospredju, ki predstavlja puščice, iščemo stik puščice s tarčo na orientacijski premici trupa. Lokacijo stika s pomočjo homografije preslikamo na ciljno ravnino, ki predstavlja lokacijo puščice. Pri drugem prototipu lokacijo računamo s 3D rekonstrukcijo. Iščemo presek premice, ki jo tvori orientacija trupa in ravnino, ki jo tvori pikado tarča. Oba prototipa testiramo na pravih metih puščic v primerih, ko puščice v tarčo, ena do druge, priletijo skupaj in narazen.

• Language: Slovenian
• Keywords: računalniški vid, pikado, šport, OpenCV
• Work type: Bachelor thesis/paper
• Organization: FRI - Faculty of Computer and Information Science
• Year: 2019
• PID: 20.500.12556/RUL-109517
• COBISS.SI-ID: 1538321859
• Publication date in RUL: 04.09.2019

DIMC, Simon, 2019, Detekcija položaja pikado puščic s pomočjo računalniškega vida [online]. Bachelor’s thesis. [Accessed 27 March 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=109517

Secondary language

• Language: English
• Title: Detection of dart positions with computer vision

Abstract

Computer vision is successfully used in sport for purposes of player and object tracking, referee assistance and improved sports broadcasting. But it is not used yet in the steel version of sport darts. Detection of dart locations could be used for automatic point counting and statistic making. In this thesis we developed two prototypes for detecting and calculating darts locations. Both prototypes use a system of three cameras, which are pointed to the dartboard. In both prototypes we are detecting the colored dart shafts, instead of whole darts. Orientation line is then calculated for each detected shaft. The first prototype uses background subtraction and homography. On the foreground, which represents darts, we search along the orientation line for the location where the dart meets the dartboard. Then, we map the location to the target plane with homography, which gives us the location on the dartboard. The second prototype uses 3D reconstruction. The dart location is found by intersecting the dart orientation line with the plane which represents the dartboard. Both prototypes are tested with real dart throws. We test the situations where the darts are close and apart, to one another.

• Keywords: computer vision, darts, sport, OpenCV