From: 2024-05-24 10:15 to 11:00
Place: E:1144
Contact: birger [dot] swahn [at] cs [dot] lth [dot] se

One Computer Science MSc thesis to be presented on 24 May

Friday, 24 May there will be a master thesis presentation in Computer Science at Lund University, Faculty of Engineering.

The presentation will take place in E:1144.

Note to potential opponents: Register as an opponent to the presentation of your choice by sending an email to the examiner for that presentation (firstname.lastname@cs.lth.se). Do not forget to specify the presentation you register for! Note that the number of opponents may be limited (often to two), so you might be forced to choose another presentation if you register too late. Registrations are individual, just as the oppositions are! More instructions are found on this page.

10:15-11:00 in E:1144

Presenters: Amin Alian, Ludvig Gierup
Title: Analysis of seam algorithms in video stitching with static scenes and dynamic objects
Examiner: Per Andersson
Supervisors: Michael Doggett (LTH), Håkan Ardö (Spiideo AB)

The focus of this paper is video stitching with a dual camera setup, static sports scenes and dynamic objects, as Spiideo wants to explore solutions to frequently occurring optical issues. Video stitching is closely related to image stitching but poses a different range of challenges. To create a video without visual artifacts, one solution is to find a seam through each video frame image pair so that the pixels to the left of the seam are from the left image, and the pixels to the right of the seam originate from the right image. In this paper we adapt and improve an already existing seam algorithm with optimisations in both performance and visual quality. We have developed three different versions of the baseline seam algorithm that we call temporal, index, and segmented. The conclusion is that the segmented variant was preferred over other variants as it was the best performing while also minimising visual artifacts.

Link to popular science summary: To be uploaded