Javascript must be enabled for the correct page display

Counting people in videos

schoonen, twan (2018) Counting people in videos. Bachelor's Thesis, Computing Science.

[img]
Preview
Text
thesis.pdf

Download (4MB) | Preview
[img] Text
toestemming.pdf
Restricted to Registered users only

Download (98kB)

Abstract

In a more and more media filled world, automation is needed for analyzing media sources. In this thesis we focus on counting people in video collections. These videos collection are to large to watch manually and have a low resolution. We compare 2 different face detection techniques and 4 different image comparison techniques. With the optimal setting we achieve a reduction rate of 95.36% on average.

Item Type: Thesis (Bachelor's Thesis)
Supervisor name: Sobiecki, A. and Telea, A.C.
Degree programme: Computing Science
Thesis type: Bachelor's Thesis
Language: English
Date Deposited: 17 Jul 2018
Last Modified: 17 Jul 2018 14:30
URI: https://fse.studenttheses.ub.rug.nl/id/eprint/17900

Actions (login required)

View Item View Item