Detekcija klizišta na LiDAR snimkama pomoću dubokog učenja

master's thesis

• Title (english): Landslide Detection in LiDAR Images Using Deep Learning
• Author: Franko Car
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Tomislav Petković (član povjerenstva)
• Committee member: Krešimir Križanović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu uvedeni su osnovni koncepti dubokog učenja i neuronskih mreža, modeli EfficientDet i YOLOv5 te je opisana njihova primjena na detekciju klizišta. Osnovni oblik podataka su LiDAR snimke koje predstavljaju visinski model terena. Uz detekciju na osnovnim visinskim modelima, oba navedena modela učena su i na deriviranim kartama osjenčanog terena. Na kraju, predstavljene su korištene metrike i konačni rezultati nad skupom podataka za testiranje.

Abstract (english)

This thesis introduces the foundations of deep learning and neural networks, EfficientDet and YOLOv5 deep learning models and their application in landslide detection. Basic data format are LiDAR images representing digital terrain models. Besides detecting landslides on the basic terrain models, both models were trained using the derived hillshaded maps as well. Finally, metrics used and final results on the test dataset are presented.

• Keywords: duboko učenje; LiDAR; detekcija; visinske snimke; osjenčane karte; konvolucija; konvolucijske neuronske mreže; EfficientDet; YOLOv5; klizišta
• Keywords (english): deep learning; LiDAR; detection; aerial imagery; hillshaded maps; convolution; convolutional neural networks; EfficientDet; YOLOv5; landslides
• Language: croatian
• URN:NBN: urn:nbn:hr:168:255816
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 11:56:40