Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/148471
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCarbó Mestre, Pol-
dc.contributor.otherVentura, Carles-
dc.coverage.spatialBarcelona, ESP-
dc.date.accessioned2023-07-21T07:40:01Z-
dc.date.available2023-07-21T07:40:01Z-
dc.date.issued2023-06-20-
dc.identifier.urihttp://hdl.handle.net/10609/148471-
dc.description.abstractFisheries management has traditionally relied on catch quotas and manual reporting methods. However, the depletion of fish stocks has required the adoption of electronic reporting systems such as the Vessel Monitoring System (VMS) and Automatic Identification System (AIS), with its own limitations in preventing overexploitation. To address this, advancements in Synthetic Aperture Radar (SAR) satellite imagery analysis, coupled with Machine Learning (ML) techniques, have emerged as promising tools for monitoring fishing activities. These advancements are revolutionizing marine industry monitoring, closing the data gaps from traditional techniques, and enhancing transparency. This project focuses on vessel detection, employing computer vision methods. Convolutional Neural Networks (CNN), specifically Faster Region-Based CNN (Faster-RCNN), exhibit promising results with reduced detection time and computational costs. We evaluated the model's performance of these models and implemented various image pre-processing techniques to improve them. Furthermore, to demonstrate the potential of this approach in fisheries management, we tested the model using real-world Sentinel-1 images in a case study on Chilean fisheries and developed an interactive report presenting the results. The integration of SAR-based satellite imagery analysis and ML techniques holds significant promise for enhancing fisheries management. The evaluation of Faster-RCNN for vessel detection, along with the comparative analysis of pre-processing techniques, provides valuable insights into the effectiveness of this method. Furthermore, it also revealed some limitations of these techniques, underscoring the need for further advancements and emphasizing the reliance on combined approaches for effective fisheries management.en
dc.description.abstractTradicionalmente, la gestión pesquera se ha basado en el establecimiento de cuotas y la recolección manual de datos. Sin embargo, el constante deterioro de las poblaciones pesqueras ha requerido la adopción de sistemas de control electrónicos como el Sistema de Monitoreo de Embarcaciones (VMS) y el Sistema de Identificación Automática (AIS), cuyas limitaciones, sin embargo, siguen sin prevenir la sobreexplotación pesquera. Debido a esto, en los últimos años, varios avances en el análisis de imágenes satelitales de Radar de Apertura Sintética (SAR) con técnicas de Aprendizaje Automático (ML) han destacado como prometedoras herramientas para gestionar las actividades pesqueras. Estos avances están revolucionando el control de la industria marina, reduciendo las limitaciones de las técnicas tradicionales. Este trabajo se centra en la detección de embarcaciones, utilizando métodos de "computer vision", específicamente Redes Neuronales Convolucionales (CNN) del tipo Faster Region-Based (Faster-RCNN). En este proyecto, hemos evaluado el rendimiento de estos modelos, incluyendo la implementación de diversas técnicas de preprocesamiento de imágenes. Además, para demostrar el potencial de este enfoque en la gestión pesquera, hemos aplicado el modelo en imágenes del satélite Sentinel-1 a través de un caso de estudio sobre las pesquerías chilenas y desarrollado un informe interactivo para presentar los resultados.es
dc.format.mimetypeapplication/pdfca
dc.language.isoengca
dc.publisherUniversitat Oberta de Catalunya (UOC)ca
dc.rightsCC BY-NC-SA*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/es/-
dc.subjectmachine learningen
dc.subjectfisheries managementen
dc.subjectSynthetic Aperture Radaren
dc.subject.lcshBioinformatics -- TFMen
dc.titleVessel detection in Synthetic Aperture Radar images using Faster R-CNN models: Advanced monitoring techniques to improve fisheries managementca
dc.typeinfo:eu-repo/semantics/masterThesisca
dc.audience.educationlevelEstudis de Màsterca
dc.audience.educationlevelEstudios de Másteres
dc.audience.educationlevelMaster's degreesen
dc.subject.lemacBioinformàtica -- TFMca
dc.contributor.tutorRebrij, Romina-
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess-
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
UOC_MemoriaFinal_pcarbomestre.pdfTFM report1,8 MBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

This item is licensed under aCreative Commons License Creative Commons