No description available.

Queimadas ocorrem por todo mundo com impactos locais e/ou globais, e, para mitigar seus efeitos danosos diversas iniciativas são utilizadas. Atualmente, utiliza-se imagens provenientes do sensoriamento remoto por meio de satélites nos quais é possível um reconhecimento de focos de queimadas. Dentre os principais métodos de identificação dos focos encontra-se o método de Limites Fixos, o qual determina quais são os limites do canal de infravermelho médio para que um foco possa ser identificado. Partindo-se da premissa de que estes limites foram determinados por meio de análises empíricas sobre os dados, essa tese se propõe à elaboração de um método para identificar focos de queimadas por meio de uma lógica computacional a qual o conhecimento do especialista possa ser inserido de modo a melhorar a definição dos limites utilizados para a identificação de queimadas. Como estudo de caso, foram utilizadas imagens do satélite NOAA, o qual é o principal satélite utilizado atualmente para este propósito devido à sua resolução espaço-temporal. Os limites são definidos a partir dos dados do canal de infravermelho médio do satélite, possibilitando que a identificação dos focos possa ser aplicada em ambientes embarcados de tempo real. Os resultados mostraram que a Lógica Fuzzy em comparação com a quantidade de focos de queimadas identificados pelo algoritmo de Setzer, apresentou resultados coerentes com o esperado. / Fire spots occurs throughout the world with local and / or global impacts, and to mitigate its harmful effects several initiatives are used. Currently, images from remote sensing via satellites are used in which it is possible the recognition of fire outbreaks. Among the main methods of identification of outbreaks is the Fixed Limits or Thresholding method, which determines the limits of the mid-infrared channel so that a focus can be identified. Starting from the premise that these limits are determined based on empirical analysis of the data, this thesis proposes the development of a method to identify fire outbreaks through a computational logic in which the knowledge of the expert may be inserted so as to enhance definition of the limits used for the identification of fire. As a case study, it is used images from the NOAA satellite, which is the main satellite currently used for this purpose because of its spatial and temporal resolution. The limits are defined from the raw satellite data, enabling that the identification of fire spots can be applied in embedded real-time environments systems. Results showed that the fuzzy logic, when compared to the amount of pixel fire identified by Setzer algorithm, showed consistent results, as expected.

Queimadas ocorrem por todo mundo com impactos locais e/ou globais, e, para mitigar seus efeitos danosos diversas iniciativas são utilizadas. Atualmente, utiliza-se imagens provenientes do sensoriamento remoto por meio de satélites nos quais é possível um reconhecimento de focos de queimadas. Dentre os principais métodos de identificação dos focos encontra-se o método de Limites Fixos, o qual determina quais são os limites do canal de infravermelho médio para que um foco possa ser identificado. Partindo-se da premissa de que estes limites foram determinados por meio de análises empíricas sobre os dados, essa tese se propõe à elaboração de um método para identificar focos de queimadas por meio de uma lógica computacional a qual o conhecimento do especialista possa ser inserido de modo a melhorar a definição dos limites utilizados para a identificação de queimadas. Como estudo de caso, foram utilizadas imagens do satélite NOAA, o qual é o principal satélite utilizado atualmente para este propósito devido à sua resolução espaço-temporal. Os limites são definidos a partir dos dados do canal de infravermelho médio do satélite, possibilitando que a identificação dos focos possa ser aplicada em ambientes embarcados de tempo real. Os resultados mostraram que a Lógica Fuzzy em comparação com a quantidade de focos de queimadas identificados pelo algoritmo de Setzer, apresentou resultados coerentes com o esperado. / Fire spots occurs throughout the world with local and / or global impacts, and to mitigate its harmful effects several initiatives are used. Currently, images from remote sensing via satellites are used in which it is possible the recognition of fire outbreaks. Among the main methods of identification of outbreaks is the Fixed Limits or Thresholding method, which determines the limits of the mid-infrared channel so that a focus can be identified. Starting from the premise that these limits are determined based on empirical analysis of the data, this thesis proposes the development of a method to identify fire outbreaks through a computational logic in which the knowledge of the expert may be inserted so as to enhance definition of the limits used for the identification of fire. As a case study, it is used images from the NOAA satellite, which is the main satellite currently used for this purpose because of its spatial and temporal resolution. The limits are defined from the raw satellite data, enabling that the identification of fire spots can be applied in embedded real-time environments systems. Results showed that the fuzzy logic, when compared to the amount of pixel fire identified by Setzer algorithm, showed consistent results, as expected.

Submitted by Bruna Rodrigues (bruna92rodrigues@yahoo.com.br) on 2016-10-21T11:57:46Z No. of bitstreams: 1 DissFTG.pdf: 1925700 bytes, checksum: c5c22c9a6d910a7762416dd81f13cd82 (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-11-08T18:52:33Z (GMT) No. of bitstreams: 1 DissFTG.pdf: 1925700 bytes, checksum: c5c22c9a6d910a7762416dd81f13cd82 (MD5) / Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-11-08T18:52:39Z (GMT) No. of bitstreams: 1 DissFTG.pdf: 1925700 bytes, checksum: c5c22c9a6d910a7762416dd81f13cd82 (MD5) / Made available in DSpace on 2016-11-08T18:52:45Z (GMT). No. of bitstreams: 1 DissFTG.pdf: 1925700 bytes, checksum: c5c22c9a6d910a7762416dd81f13cd82 (MD5) Previous issue date: 2016-08-30 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / The wildfires caused by human occupation is one of the factors that most contributes to deforestation of conservation areas, resulting in a number of issues for ecological systems. Premature fire detection lead to the elimination or minimize the damage that will be caused by a fire incident. Wireless Sensor Networks (WSNs) has been shown to be a good alternative for environmental monitoring applications, as they can collect and send the information in real-time, such as humidity, wind and temperature of various parts of the forest. Due to problems such as power limitation, communication failure and loss of nodes, the network topology is constantly changing, requiring mechanisms to achieve self-organization and fault tolerance. This paper proposes the development of a model and application in selforganizing and fault-tolerant WSNs for fire detection in conservation areas. To achieve self-organization and fault tolerance is encouraged local interactions between neighboring nodes that monitor the same region and the coordination of tasks, through a supervisor node, equipped with a framework for developing fault-tolerant applications based on components. Using a component redundancy technique with adaptive approach, the fire detection solution was implemented. Each component, ie, different implementations of the same specification, it is loaded and unloaded from runtime memory while the node assumes the role of coordinator. The results are stored and after execution of all components is achieved a consensus. For analysis and validation of the model and the application was simulated to 60 events in the sensor network in a real scenario, using the Sinalgo simulator. The results were classified as True (partial or absolute) or False (partial or absolute). In 45% of consensus identified a possible fault in the application and in only 35% there was absolute consensus. / Os incêndios causados pela ocupação humana é um dos fatores que mais contribui para o desmatamento das áreas de preservação ambiental, acarretando uma série de problemas aos sistemas ecológicos. A detecção precoce do fogo visa eliminar ou minimizar o dano que será causado por um incidente de fogo. Redes de Sensores sem Fio (RSSFs) tem se mostrado uma boa alternativa para aplicacões de monitoramento ambiental, visto que podem coletar e enviar informações em tempo real, como umidade, vento e temperatura de vários pontos da floresta. Devido a problemas como limitação de energia, falha na comunicacão e perda de n´os sensores, a topologia da rede muda constantemente, exigindo mecanismos que permitem alcançar a auto-organização e a tolerância a falhas. Este trabalho propõe o desenvolvimento de um modelo e uma aplicação em RSSFs auto-organizável e tolerante a falhas para detecção de fogo em áreas de preservação. Para alcançar a auto-organização e a tolerância a falhas incentiva-se as interações locais entre n´os vizinhos que monitoram uma mesma região e a coordenacão de tarefas, por meio de um nó coordenador equipado com um framework para desenvolvimento de aplicações tolerante a falhas baseado em componentes. Utilizando uma técnica de redundância de componentes com abordagem adaptativa, a solucão de detecção de fogo foi implementada. Cada componente, ou seja, diferentes implementações de uma mesma especificação, ´e carregado e descarregado da memória em tempo de execucão enquanto o nó assume o papel de coordenador. Os resultados são armazenados e após execução de todos componentes é obtido um consenso. Para análise e validação do modelo e da aplicação simulou-se 60 eventos na rede de sensores em um cenário real, utilizando o simulador Sinalgo. Os resultados foram classificados como Verdadeiros (parcial ou total) ou Falsos (parcial ou total). Em 45% dos consensos identificou-se uma possível falha na aplicação e somente em 35% houve um consenso total.

This master's thesis deals with fire detection in videosequences. Attention is paid to the known characteristics of fire and basic principles of existing solutions which deal with this issue. The thesis also describes design, implementation and testing of a fire detector that is based on the recognition of suspicious areas by fire color modeling, combined with detection of motion and light intensity variations.

The aim of this work was to use remote sensing data from the MODIS instrument of the Terra satellite to detect bush fires in Australia. This included preprocessing the demodulator output, bit synchronization and reassembly of data packets. IMAPP was used to do the geolocation and data calibration. The fire detection used a combination of fixed threshold techniques with difference tests and background comparisons. The results were projected in a rectangular latidue/longitude map to remedy the bow tie effect. Algorithms were implemented in C and Matlab. It proved to be possible to detect fires in the available data. The results were compared with fire detection done done by NASA and fire detections based on other sensors and found to be very similar. / Das Ziel dieser Arbeit war die Nutzung von Fernerkundungsdaten des MODIS Instruments an Bord des Satelliten Terra zur Erkennung von Buschfeuern in Australien. Das schloss die Vorverarbeitung der Daten vom Demodulator, die Bitsynchronisation und die Umpacketierung der Daten ein. IMAPP wurde genutzt um die Daten zu kalibrieren und zu geolokalisieren. Die Feuererkennung bedient sich einer Kombination von absoluten Schwellwerttests, Differenztests und Vergleichen mit dem Hintergrund. Die Ergebnisse wurden in eine rechteckige Laengen/Breitengradkarte projiziert um dem BowTie Effekt entgegenzuwirken. Die benutzten Algrorithmen wurden in C und Matlab implementiert. Es zeigte sich, dass es moeglich ist in den verfuegbaren Daten Feuer zu erkennen. Die Ergebnisse wurden mit Feuererkennungen der NASA und Feuererkennung die auf anderen Sensoren basieren verglichen und fuer sehr aehnlich befunden.

The last decades has seen the rise of digitization and automation of certain tasks at dangerous work environments though this has not yet affected the firefighting profession. With sensors and remote vehicles it is possible to aid the firefighters in analyzing a situation and aid them in the extinguishing efforts which reduces risks and time spent finding the fires. This thesis proposes a solution to such a problem by designing and implementing a case study. The test system was tested in a controlled environment to verify the functionality of the system. The results show that this is possible using low resolution thermal imaging equipment. The case study also shows that standard imaging equipment is a useful tool to determine the severity of the scene as well as searching for people. / Under de senaste decennierna har digitaliseringen och automatisering av uppgifter i farliga arbetsmiljöer ökat, detta har inte ännu påverkat brandkåren. Med hjälp av sensorer och fjärrstyrda fordon kan detta göra det möjligt att hjälpa brandmän att analysera en situation och hjälpa till med brandsläckning vilket reducerar riskerna och tid att hitta bränder. Denna avhandling framför en lösning till ett sådant problem genom att skapa och implementera en fallstudie. Testsystemet var testat i en kontrollerad miljö att verifiera funktionaliteten av systemet. Resultaten visar att det är möjligt att använda sig av en lågupplöst värmekamera. Fallstudien visade även att bildutrustning är ett användbart verktyg för att bestämma allvarlighetsgraden av miljön och för att söka efter människor.

Submitted by SBI Biblioteca Digital (sbi.bibliotecadigital@puc-campinas.edu.br) on 2018-02-19T18:35:33Z No. of bitstreams: 1 THIAGO DE ALMEIDA CORREIA.pdf: 4124942 bytes, checksum: 5f6dc7a856830e61da5524f9c2986e14 (MD5) / Made available in DSpace on 2018-02-19T18:35:34Z (GMT). No. of bitstreams: 1 THIAGO DE ALMEIDA CORREIA.pdf: 4124942 bytes, checksum: 5f6dc7a856830e61da5524f9c2986e14 (MD5) Previous issue date: 2017-12-15 / Pontif?cia Universidade Cat?lica de Campinas ? PUC Campinas / This document presents a planning and communication strategy in wireless sensor networks for the real-time detection of forest fires. Wireless sensor networks, even being a low-cost technology, can be used for risk applications such as in the forest fire prevention and detection, effectively compared to other technologies more expensive. They can also be used in the monitoring of information that could contribute to diagnose the cause of a particular forest fire. The communication strategy was implemented in a wireless sensor network installed in a eucalyptus forest. In addition to the communication strategy, this project carried out a physical planning of the area, to locate the best points of installation of the sensor nodes. In both tests were used radio modules operating at 915 MHz. The geographic localization of each radio module was planned based on the intensity of the signal received by each module and considering its position within a mesh topology. The effectiveness of the communication strategy was measured through the PER and the average delay. The robustness of the strategy in case of radio module failure were also investigated and evaluated. / No presente trabalho ? apresentada uma estrat?gia comunica??o em redes de sensores sem fio para a detec??o em tempo real de inc?ndios florestais. Redes de sensores sem fios mesmo sendo uma tecnologia de baixo custo, podem ser utilizadas para aplica??es de risco como na preven??o e detec??o de inc?ndios florestais, de forma eficaz comparada com outras tecnologias mais caras. Elas tamb?m podem ser utilizadas na coleta de informa??es contribuindo em diagnosticar a causa de um determinado inc?ndio florestal. A estrat?gia de comunica??o foi implementada em uma rede de sensores sem fio instalada dentro de uma floresta de eucalipto. Al?m da estrat?gia de comunica??o este projeto realizou um planejamento f?sico da ?rea, para localizar os melhores pontos de instala??o dos n?s sensores. Para ambos os testes foram utilizados m?dulos de r?dio operando em 915 MHz. O posicionamento geogr?fico de cada m?dulo de r?dio foi planejado baseando-se na intensidade do sinal recebido por cada m?dulo e considerando o seu posicionamento dentro de uma topologia em malha. A efic?cia da estrat?gia de comunica??o foi mensurada atrav?s dos par?metros: taxa de perda de pacotes, atraso m?dio da coleta e processamento dos pacotes. A robustez da estrat?gia perante falhas do m?dulo de r?dio, tamb?m foi investigada e avaliada.

Remote sensing data has great potential for wildfire detection and monitoring with enhanced spatial resolution and temporal coverage. Earth Observation satellites have been employed to systematically monitor fire activity over large regions in two ways: (i) to detect the location of actively burning spots (during the fire event), and (ii) to map the spatial extent of the burned scars (during or after the event). Active fire detection plays an important role in wildfire early warning systems. The open-access of Sentinel-2 multispectral data at 20-m resolution offers an opportunity to evaluate its complementary role to the coarse indication in the hotspots provided by MODIS-like polar-orbiting and GOES-like geostationary systems. In addition, accurate and timely mapping of burned areas is needed for damage assessment. Recent advances in deep learning (DL) provides the researcher with automatic, accurate, and bias-free large-scale mapping options for burned area mapping using uni-temporal multispectral imagery. Therefore, the objective of this thesis is to evaluate multispectral remote sensing data (in particular Sentinel-2) for wildfire detection, including active fire detection using a multi-criteria approach and burned area detection using DL models.        For active fire detection, a multi-criteria approach based on the reflectance of B4, B11, and B12 of Sentinel-2 MSI data is developed for several representative fire-prone biomes to extract unambiguous active fire pixels. The adaptive thresholds for each biome are statistically determined from 11 million Sentinel-2 observations samples acquired over summertime (June 2019 to September 2019) across 14 regions or countries. The primary criterion is derived from 3 sigma prediction interval of OLS regression of observation samples for each biome. More specific criteria based on B11 and B12 are further introduced to reduce the omission errors (OE) and commission errors (CE).        The multi-criteria approach proves to be effective in cool smoldering fire detection in study areas with tropical &amp; subtropical grasslands, savannas &amp; shrublands using the primary criterion. At the same time, additional criteria that thresholds the reflectance of B11 and B12 can effectively decrease the CE caused by extremely bright flames around the hot cores in testing sites with Mediterranean forests, woodlands &amp; scrub. The other criterion based on reflectance ratio between B12 and B11 also avoids the effects of CE caused by hot soil pixels in sites with tropical &amp; subtropical moist broadleaf forests. Overall, the validation performance over testing patches reveals that CE and OE can be kept at a low level  (0.14 and 0.04) as an acceptable trade-off. This multi-criteria algorithm is suitable for rapid active fire detection based on uni-temporal imagery without the requirement of multi-temporal data. Medium-resolution multispectral data can be used as a complementary choice to the coarse resolution images for their ability to detect small burning areas and to detect active fires more accurately.        For burned area mapping, this thesis aims to expound on the capability of deep DL models for automatically mapping burned areas from uni-temporal multispectral imagery. Various burned area detection algorithms have been developed using Sentinel-2 and/or Landsat data, but most of the studies require a pre-fire image, dense time-series data, or an empirical threshold. In this thesis, several semantic segmentation network architectures, i.e., U-Net, HRNet, Fast- SCNN, and DeepLabv3+ are applied to Sentinel-2 imagery and Landsat-8 imagery over three testing sites in two local climate zones. In addition, three popular machine learning (ML) algorithms (LightGBM, KNN, and random forests) and NBR thresholding techniques (empirical and OTSU-based) are used in the same study areas for comparison.        The validation results show that DL algorithms outperform the machine learning (ML) methods in two of the three cases with the compact burned scars,  while ML methods seem to be more suitable for mapping dispersed scar in boreal forests. Using Sentinel-2 images, U-Net and HRNet exhibit comparatively identical performance with higher kappa (around 0.9) in one heterogeneous Mediterranean fire site in Greece; Fast-SCNN performs better than others with kappa over 0.79 in one compact boreal forest fire with various burn severity in Sweden. Furthermore, directly transferring the trained models to corresponding Landsat-8 data, HRNet dominates in the three test sites among DL models and can preserve the high accuracy. The results demonstrate that DL models can make full use of contextual information and capture spatial details in multiple scales from fire-sensitive spectral bands to map burned areas. With the uni-temporal image, DL-based methods have the potential to be used for the next Earth observation satellite with onboard data processing and limited storage for previous scenes.    In the future study, DL models will be explored to detect active fire from multi-resolution remote sensing data. The existing problem of unbalanced labeled data can be resolved via advanced DL architecture, the suitable configuration on the training dataset, and improved loss function. To further explore the damage caused by wildfire, future work will focus on the burn severity assessment based on DL models through multi-class semantic segmentation. In addition, the translation between optical and SAR imagery based on Generative Adversarial Network (GAN) model could be explored to improve burned area mapping in different weather conditions. / Fjärranalysdata har stor potential för upptäckt och övervakning av skogsbränder med förbättrad rumslig upplösning och tidsmässig täckning. Jordobservationssatelliter har använts för att systematiskt övervaka brandaktivitet över stora regioner på två sätt: (i) för att upptäcka placeringen av aktivt brinnande fläckar (under brandhändelsen) och (ii) för att kartlägga den brända ärrens rumsliga omfattning ( under eller efter evenemanget). Aktiv branddetektering spelar en viktig roll i system för tidig varning för skogsbränder. Den öppna tillgången till Sentinel-2 multispektral data vid 20 m upplösning ger en möjlighet att utvärdera dess kompletterande roll i förhållande till den grova indikationen i hotspots som tillhandahålls av MODIS-liknande polaromloppsbanesystem och GOES-liknande geostationära system. Dessutom krävs en korrekt och snabb kartläggning av brända områden för skadebedömning. Senaste framstegen inom deep learning (DL) ger forskaren automatiska, exakta och förspänningsfria storskaliga kartläggningsalternativ för kartläggning av bränt område med unitemporal multispektral bild. Därför är syftet med denna avhandling att utvärdera multispektral fjärranalysdata (särskilt Sentinel- 2) för att upptäcka skogsbränder, inklusive aktiv branddetektering med hjälp av ett multikriterietillvägagångssätt och detektering av bränt område med DL-modeller. För aktiv branddetektering utvecklas en multikriteriemetod baserad på reflektionen av B4, B11 och B12 i Stentinel-2 MSI data för flera representativa brandbenägna biom för att få fram otvetydiga pixlar för aktiv brand. De adaptiva tröskelvärdena för varje biom bestäms statistiskt från 11 miljoner Sentinel-2 observationsprover som förvärvats under sommaren (juni 2019 till september 2019) i 14 regioner eller länder. Det primära kriteriet härleds från 3-sigma-prediktionsintervallet för OLS-regression av observationsprover för varje biom. Mer specifika kriterier baserade på B11 och B12 införs vidare för att minska utelämningsfel (OE) och kommissionsfel (CE). Det multikriteriella tillvägagångssättet visar sig vara effektivt när det gäller upptäckt av svala pyrande bränder i undersökningsområden med tropiska och subtropiska gräsmarker, savanner och buskmarker med hjälp av det primära kriteriet. Samtidigt kan ytterligare kriterier som tröskelvärden för reflektionen av B11 och B12 effektivt minska det fel som orsakas av extremt ljusa lågor runt de heta kärnorna i testområden med skogar, skogsmarker och buskage i Medelhavsområdet. Det andra kriteriet som bygger på förhållandet mellan B12 och B11:s reflektionsgrad undviker också effekterna av CE som orsakas av heta markpixlar i områden med tropiska och subtropiska fuktiga lövskogar. Sammantaget visar valideringsresultatet för testområden att CE och OE kan hållas på en låg nivå (0,14 och 0,04) som en godtagbar kompromiss. Algoritmen med flera kriterier lämpar sig för snabb aktiv branddetektering baserad på unika tidsmässiga bilder utan krav på tidsmässiga data. Multispektrala data med medelhög upplösning kan användas som ett kompletterande val till bilder med kursupplösning på grund av deras förmåga att upptäcka små brinnande områden och att upptäcka aktiva bränder mer exakt. När det gäller kartläggning av brända områden syftar denna avhandling till att förklara hur djupa DL-modeller kan användas för att automatiskt kartlägga brända områden från multispektrala bilder i ett tidsintervall. Olika algoritmer för upptäckt av brända områden har utvecklats med hjälp av Sentinel-2 och/eller Landsat-data, men de flesta av studierna kräver att man har en förebränning. bild före branden, täta tidsseriedata eller ett empiriskt tröskelvärde. I den här avhandlingen tillämpas flera arkitekturer för semantiska segmenteringsnätverk, dvs. U-Net, HRNet, Fast- SCNN och DeepLabv3+, på Sentinel- 2 bilder och Landsat-8 bilder över tre testplatser i två lokala klimatzoner. Dessutom används tre populära algoritmer för maskininlärning (ML) (Light- GBM, KNN och slumpmässiga skogar) och NBR-tröskelvärden (empiriska och OTSU-baserade) i samma undersökningsområden för jämförelse. Valideringsresultaten visar att DL-algoritmerna överträffar maskininlärningsmetoderna (ML) i två av de tre fallen med kompakta brända ärr, medan ML-metoderna verkar vara mer lämpliga för kartläggning av spridda ärr i boreala skogar. Med hjälp av Sentinel-2 bilder uppvisar U-Net och HRNet jämförelsevis identiska prestanda med högre kappa (omkring 0,9) i en heterogen brandplats i Medelhavet i Grekland; Fast-SCNN presterar bättre än andra med kappa över 0,79 i en kompakt boreal skogsbrand med varierande brännskadegrad i Sverige. Vid direkt överföring av de tränade modellerna till motsvarande Landsat-8-data dominerar HRNet dessutom på de tre testplatserna bland DL-modellerna och kan bevara den höga noggrannheten. Resultaten visade att DL-modeller kan utnyttja kontextuell information fullt ut och fånga rumsliga detaljer i flera skalor från brandkänsliga spektralband för att kartlägga brända områden. Med den unika tidsmässiga bilden har DL-baserade metoder potential att användas för nästa jordobservationssatellit med databehandling ombord och begränsad lagring av tidigare scener. I den framtida studien kommer DL-modeller att undersökas för att upptäcka aktiva bränder från fjärranalysdata med flera upplösningar. Det befintliga problemet med obalanserade märkta data kan lösas med hjälp av en avancerad DL-arkitektur, lämplig konfiguration av träningsdatasetet och förbättrad förlustfunktion. För att ytterligare utforska de skador som orsakas av skogsbränder kommer det framtida arbetet att fokusera på bedömningen av brännskadornas allvarlighetsgrad baserat på DL-modeller genom semantisk segmentering av flera klasser. Dessutom kan översättningen mellan optiska bilder och SAR-bilder baserad på en GAN-modell (Generative Adversarial Network) undersökas för att förbättra kartläggningen av brända områden under olika väderförhållanden. / <p>QC 20210525</p>

The master’s thesis „Support for instruction in electric fire alarm system” describes principles and engineering solution of electric fire alarm system. It is background for activity task about EPS for students in VUT in Brno. It illustrates how to act on this task and configuration fire panel and components EPS with the support of software FSP 5000. The practice contains proposal EPS with support in fire system designer.