Return to search

Measuring the Speed of a Floorball Shot Using Trajectory Detection and Distance Estimation With a Smartphone Camera : Using OpenCV and Computer Vision on an iPhone to Detect the Speed of a Floorball Shot / Mätning av hastigheten på ett innebandyskott genom detektering av projektilbana och avståndsbedömning med kameran i en smartphone

This thesis describes the possibilities of using smartphones and their cameras in combination with modern computer vision algorithms to track and measure the speed of a floorball. Previous research within the area is described and an explanation is given as to why an implementation using three-frame temporal differencing to detect objects in motion works best to detect and track the ball. 100 floorball shots were recorded and measured using a speedometer radar and two different smartphones, one running the application and the other recording each shot. The video recording for each shot was then used to manually create a baseline for speed comparison. A second experiment was later conducted to analyse the sensitivity and effect on the determined ball size in the floorball shot analysis. The results from the first experiment show that the speedometer radar results in average deviate by 12% from the speed baseline. The speedshooting application however has results that, on average, deviate from the speed baseline by 6%. Furthermore, the results show that a faulty ball size detection is the major cause of error in the speedshooting application. The main conclusion that can be drawn from this is that it is possible to use a smartphone and computer vision methodologies to determine the speed of a floorball shot. In fact, it is even possible to do so with greater accuracy than the radar used in the experiments in this thesis. However, to prove the accuracy of the application for normal use, further testing needs to be conducted in new experiment conditions, for example by recording shots at higher speeds than those recorded in the experiments in this thesis.

Identiferoai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kth-190823
Date January 2016
CreatorsSchmidt, Eric
PublisherKTH, Skolan för datavetenskap och kommunikation (CSC)
Source SetsDiVA Archive at Upsalla University
LanguageEnglish
Detected LanguageEnglish
TypeStudent thesis, info:eu-repo/semantics/bachelorThesis, text
Formatapplication/pdf
Rightsinfo:eu-repo/semantics/openAccess

Page generated in 0.0027 seconds