Detekcija klizišta na LiDAR terenskim snimkama

undergraduate thesis

• Title (english): Landslide Detection in LiDAR Terrain Images
• Author: Toni Krešo
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Denis Milošević (član povjerenstva)
• Committee member: Karlo Koščević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Detekcija objekata danas pronalazi razne primjene u svrhu napretka znanosti i
ljudskog života. Što se više koristi, što više podataka nastaje, to će neuronske mreže
biti bolje u rješavanju zadataka. U sklopu ovog rada dan je uvod u neuronske mreže
i računalni vid te je istreniran model za detekciju klizišta na LiDAR snimkama.
Detekcija objekata na LiDAR snimkama je doprinijela znanosti na način da
znanstvenicima dopušta da rade posao koji pronalazi nove načine rješavanja
problema i da prikupljaju nove podatke, a model za detekciju olakšava posao
pronalaženja klizišta tako da znanstvenicima pokaže gdje bi klizište moglo biti. Na
ovaj način se štedi cijenjeno vrijeme znanstvenika.

Abstract (english)

Object detection today finds various applications for the purpose of advancing
science and human life. The more it is used, the more data is generated, the better
the neural networks will be in solving tasks. As part of this paper, an introduction
to neural networks and computer vision was given, and a model for landslide
detection on LiDAR images was trained. Detection of objects on LiDAR images
has contributed to science by allowing scientists to do work that finds new ways to
solve problems and collect new data, and the detection model facilitates the job of
finding landslides by showing scientists where a landslide might be. This saves
scientists’ valuable time.

• Keywords: neuronska mreža; neuron; konvolucija; računalni vid; detekcija objekata
• Keywords (english): neural network; neuron; convolution; computer vision; object detection
• Language: croatian
• URN:NBN: urn:nbn:hr:168:649593
• 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: 2023-01-15 10:36:01