Computer Vision For Aimpoint Tracking In Biathlon
Master thesis
Permanent lenke
http://hdl.handle.net/11250/2560152Utgivelsesdato
2018Metadata
Vis full innførselSamlinger
Sammendrag
The purpose of this thesis was to look at the development of a computer vision systemfor aimpoint tracking in biathlon. It s desired to develop a system that tracks thePoint-of-Aim of the biathlete in order to give quantifiable feedback during and aftershooting practice to accelerate skill acquisition.This report covers the process of developing a prototype computer vision system,from the initial idea to a working prototype implementation and system evaluation. Itwas found that the usage of the Circular Hough Transform (CHT) algorithm gave high(sub-pixel) precision on a wide range of video resolutions and is suitable for futureimplementations. It came at the cost of expensive computation demands, and reachinghigh update frequencies were difficult. 13 FPS was seen on the desktop implementationwhen analyzing a 640x424 video, while 50 Hz were obtained on a 216MHz Cortex M7analyzing a 20x120 video source. Feature tracking based on establishing a region-ofinterestwithin the frame was proved to be successful. A successful aimpoint trackingoutput was obtained and is presented.Camera and processing power specifications are identified and presented for futureimplementations. The usage of Matlab as a development environment is discouragedfor further work on the project, and the switch to a OpenCV-based implementation isrecommended.