Detekcija objekata u zračnim snimkama

undergraduate thesis

• Title (english): Object Detection in Aerial Images
• Author: Marin Tokić
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Darijan Marčetić (član povjerenstva)
• Committee member: Ivan Krešo (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Polje računalnog vida je doživjelo značajan razvoj u posljednim godinama. Interes za poljem je porasao kada se ispostavilo da efektivno može riješavati kompleksne probleme detekcije i klasifikacije. Dok se dijelovi računalnog vida koji su povezani sa prometom i autonomnim vozilima brzo razvijaju, dijelovi poput detekcija u zračnim i satelitskim snimkama kasne za ostalim područjima. U radu razlažemo probleme detekcija objekata u zračnim snimkama. Predlažemo pristup riješavanju problema primjenom HOG deskriptora i SVM-a. Opisujemo postupak treniranja, detekcije i evaluacije detekcija na konkretnom primjeru. Konačno, analiziramo performanse pristupa za različite vrste objekata.

Abstract (english)

The field of computer vision has undergone significant development in recent years. The interest in the field grew when it turned out to be effective in solving complex detection and classification problems. While computer vision-related parts, that are related to traffic and autonomous vehicles, are rapidly evolving, parts such as object detection in aerial and satellite images are lagging behind other areas. The paper discusses the problems of detecting objects in aerial images. We propose a solution to the problem by using the HOG descriptor and SVM. We describe the training, detection and evaluation on a concrete example. Finally, we analyze the performance of the method on different types of objects.

• Keywords: računalno učenje; SVM; HOG; racunalni vid; zračne snimke; detekcija objekata
• Keywords (english): machine learing; SVM; HOG; computer vision; aerial images; object detection
• Language: croatian
• URN:NBN: urn:nbn:hr:168:637370
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-14 01:33:19