Detekcija i klasifikacija otpada na slici s kamere

undergraduate thesis

• Title (english): Waste Detection and Classification in Camera Image
• Author: Tin Ogrizek
• Mentor: Tamara Petrović (mentor)
• Committee member: Tamara Petrović (član povjerenstva)
• Committee member: Marijana Peti (član povjerenstva)
• Committee member: Robert Milijaš (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Detection and classification of waste is a very important step in addressing many environmental issues. This paper studies this problem with the aim of training a custom image detection and classification model. The concept of convolutional neural networks, their structure and how they work are explained in this thesis. Also, the thesis reviews the most well-known algorithms for object detection, as well as the metrics used for evaluating trained models. It described the TACO dataset and describes the software requirements used for training an object detection model. The YOLO algorithm is used to train the models, and training is performed on two different datasets with the same intent. At the end of the thesis, the achieved results are described and analyzed.

Abstract (english)

Detection and classification of waste is a very important step in addressing many environmental issues. This paper studies this problem with the aim of training a custom image detection and classification model. The concept of convolutional neural networks, their structure and how they work are explained in this thesis. Also, the thesis reviews the most well-known algorithms for object detection, as well as the metrics used for evaluating trained models. It described the TACO dataset and describes the software requirements used for training an object detection model. The YOLO algorithm is used to train the models, and training is performed on two different datasets with the same intent. At the end of the thesis, the achieved results are described and analyzed

• Keywords: Detekcija objekata; klasifikacija objekata; računalni vid; konvolucijske neuronske mreže; YOLO; TACO skup podataka
• Keywords (english): Object detection; object classification; computer vision; convolutional neural networks; YOLO; TACO dataset
• Language: croatian
• URN:NBN: urn:nbn:hr:168:344744
• 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: 2024-10-12 21:42:56