master's thesis
Vision Based Object Following Using a Mobile Phone

Antonio Lončar (2015)
Metadata
TitleSlijeđenje objekta mobilnim robotom upravljanim pomoću mobilnog telefona
AuthorAntonio Lončar
Mentor(s)Robert Cupec (thesis advisor)
Abstract
Zadatak diplomskoga rada je napraviti robotska kolica koja autonomno prate odabrani objekt primjenom računalnog vida. Sklopovlje robotskih kolica je realizirano pomoću Arduino uno platforme i pametnoga telefona, dok je komunikacija između njih omogućena HC-05 bluetooth modulom. Algoritam za praćenje objekta na pametnom telefonu pisan je u Java programskom jeziku pomoću biblioteke Opencv4Android. Dok je kod za Arduino uno pisan u C++ programskom jeziku. Algoritam za praćenje objekta na pametnome telefonu temelji se na praćenju boje zadanog objekta, dodirom na ekran mobitela pohrani se informacija o boji objekta te se obradom svake sljedeće slike koju kamera snimi određuje kontura odabranog objekta i njegov centroid. Ovisno o položaju objekta na slici pametni telefon šalje poruke Arduinu. U porukama koje prima Arduino uno nalaze se podaci o smjeru kretanja robotskih kolica, brzini kretanja i koliko dugo će se kretati. Na Arduinu je isprogramiran program koji služi za parsiranje primljenih poruke te pomicanje robotskih kolica.
Keywordsmobile robot Arduino uno smartphone color based tracking opencv4android
Parallel title (English)Vision Based Object Following Using a Mobile Phone
Committee MembersRobert Cupec (committee chairperson)
Alfonzo Baumgartner (committee member)
Damir Filko (committee member)
GranterSveučilište Josipa Jurja Strossmayera u Osijeku
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek
Lower level organizational unitsZavod za računalno inženjerstvo i automatiku
Katedra za automatiku i robotiku
PlaceOsijek
StateCroatia
Scientific field, discipline, subdisciplineTECHNICAL SCIENCES
Computing
Process Computing
Study programme typeuniversity
Study levelgraduate
Study programmeGraduate University Study Programme in Computer Engineering
Academic title abbreviationmag.ing.comp.
Genremaster's thesis
Language Croatian
Defense date2015-10-05
Parallel abstract (English)
The task of this thesis is to build a robotic car which follows an object autonomously using computer vision. The hardware of the robotic car is realised with an Arduino uno platform and a smartphone which comunicate via HC-05 bluetooth modul. The program for object tracking using a smartphone is written in Java programming language with library Opencv4Android while the code for Arduino is written in C++ programming language. The object tracking algorithm is color based. The information about the color of the object is stored with a touch on the mobile phone screen. The program processes every next image that the camera records finds the contour and compute the centroid of the object. The smartphone sends a messages to Arduino depending on the location of the tracked object. The messages that Arduino recieves contain information about the direction of motion of the robotic car, speed of motion and how long the motion should be performed. There is a program on Arduino which serves for parsing the recieved messages and for moving the robotic car.
Parallel keywords (Croatian)mobilni robot Arduino uno pametni telefon praćenje objekta bazirano na boji opencv4android.
Resource typetext
Access conditionOpen access
Terms of usehttp://rightsstatements.org/vocab/InC/1.0/
URN:NBNhttps://urn.nsk.hr/urn:nbn:hr:200:053721
CommitterAnka Ovničević