Infrared small target detection is widely used in fields such as military and security. UNet, which is a classical semantic segmentation method proposed in 2015, has shown excellent performance and robustness. However, U-Net suffers from the problem of losing small targets in deep layers after multiple down-sampling operations. Dilated convolution, as a special convolution that can increase the receptive field without increasing the number of parameters, is considered to be able to optimize the problems caused by down-sampling. Dense Nested Attention Network (DNANet), due to its superior performance, was chosen as the baseline, but it still has the issue of target loss. This study proposes three optimization directions: deep down-sampling replaced by cascaded dilated convolution, dilated spatial attention, and dilated residual block. In these three directions, this study proposes four methods, respectively DNANet-DS-1, DNANet-DS-2, DNANet-Att, and DNANet-RB. Two open-source infrared small target datasets, NUDT-SIRST and NUAA-SIRST, were used in this study. The four proposed methods were trained and tested on these two datasets. Among them, DNANetRB significantly outperforms other methods on the NUAA-SIRST dataset, so further experiments were conducted to observe the influence of different network depths on DNANet-RB. The experimental result indicates that when the network depth exceeds a certain threshold, the network can only achieve marginal improvements, but the number of parameters will increase significantly. / Infraröd detektering av små mål används ofta inom områden som militär och säkerhet. U-Net, som är en klassisk semantisk segmenteringsmetod som föreslogs 2015, har visat utmärkt prestanda och robusthet. U-Net lider dock av problemet med att förlora små mål i djupa lager efter flera nedprovningsoperationer. Dilaterad konvolution, som är en speciell konvolution som kan öka det receptiva fältet utan att öka antalet parametrar, anses kunna optimera de problem som orsakas av downsampling. DNANet (Dense Nested Attention Network) valdes som baslinje på grund av dess överlägsna prestanda, men det har fortfarande problemet med målförlust. Denna studie föreslår tre optimeringsriktningar: djup nedsampling ersatt av kaskad dilaterad konvolution, dilaterad rumslig uppmärksamhet och dilaterat restblock. I dessa tre riktningar föreslår denna studie fyra metoder, respektive DNANet-DS-1, DNANet-DS-2, DNANet-Att och DNANet-RB. Två dataset med små infraröda mål med öppen källkod, NUDT-SIRST och NUAA-SIRST, användes i denna studie. De fyra föreslagna metoderna tränades och testades på dessa två datamängder. Bland dem överträffar DNANet-RB betydligt andra metoder på NUAA-SIRST-datasetet, så ytterligare experiment genomfördes för att observera påverkan av olika nätverksdjup på DNANet-RB. Det experimentella resultatet visar att när nätverksdjupet överskrider ett visst tröskelvärde kan nätverket bara uppnå marginella förbättringar, men antalet parametrar kommer att öka avsevärt.

Os objetivos deste trabalho foram: Analisar prospectivamente a eficácia da correlação entre parâmetros clínicos, histológicos, e marcadores de proliferação celular buscando melhores indicadores de prognóstico em casos de mastocitoma canino; Testar o uso de nova ferramenta diagnóstica e prognóstica para mastocitomas caninos: a termografia. Para isso, um total de 20 cães com diagnóstico citológico e histopatológico de mastocitoma tiveram suas formações excisadas e foram utilizados para estudo clínico e imunohistoquímico e dentre estes, 15 também para estudo termográfico. As avaliações imunohistoquímicas incluíram quantificação de AgNORs, PCNA, VEGF, localização de KIT. Os estudos termográficos incluíram análise e correlação das temperaturas no ponto central da formação (SpT), e na área da formação (AT) e em ponto de pele sadia (SpNT) e área equivalente, em pele sadia (ANT). Estatisticamente pode-se demonstrar uma correlação positiva significativa entre a classificação proposta determinada pela presença dos fatores prognósticos e o estadiamento proposto pela WHO. Não foi observada correlação estatística entre tempo livre de doença (óbito, novas formações, recidiva ou metástase) e o estadiamento ou fatores prognósticos. 95% (19/20) dos cães teve suas formações classificadas como Grau II e 5% (1/20) Grau I, segundo a classificação histológica de Patnaik (1984). Todos os cães tiveram suas formações classificadas como Baixo Grau, de acordo com a classificação proposta por Kiupell (2011). 5,6% (1/18) dos animais foi considerada padrão KIT - I, 44,4% (8/18) padrão KIT - II e 50% (9/18) padrão KIT - III. Não foi observada correlação estatística entre o padrão KIT e tempo livre de doença ou graduação histológica. Apesar de não significativo estatisticamente, foi notado menor tempo de sobrevida livre de doença nos animais com PCNA e AgNOR acima das medianas (p =0,089 e p = 0,080, respectivamente).O VEGF foi o único marcador a demonstrar relação significativa com o tempo livre de doença (p = 0,004). As análises termográficas indicaram média de temperatura do SpT de 33,18ºC, média de temperatura do SpNT de 33,39ºC, temperatura média de AT de 33,27ºC e temperatura média de ANT de 33,95ºC. A diferença entre os pontos mensurados foi em média -0,21ºC (variando entre -5,60ºC e +4,4ºC). A diferença entre os pontos mensurados foi em média -0,21ºC (variando entre -5,60ºC e +4,4ºC). Esta diferença foi negativa em 7/15 casos (47%) formações mais frias que a pele distante; e positiva em 8/15 casos (53%) formações mais quentes que a pele distante. Não foi possível correlacionar estatisticamente essas alterações de temperatura com a presença dos marcadores estudados, mas as análises estatísticas demonstram que a termografia na região tumoral é estatisticamente diferente da região não tumoral. / The objectives of this study were: To prospectively analyze the effectiveness of the correlation between clinical, histologic, and cell proliferation markers, seeking better indicators of prognosis in cases of canine mast cell tumor; and testing the use of new diagnostic and prognostic tool for canine mast cell tumor: thermography (infrared images); A total of 20 dogs with histopathological and cytological diagnosis of mast cell tumor were excised and their formations were used for immunohistochemical and clinical study, and 15 of those were also used for thermographic study. The evaluations included immunohistochemical quantification of AgNOR, PCNA, VEGF, KIT location. The studies included thermographic images analysis and correlation of the temperatures at the midpoint of tumor (SPT), and tumor area (AT) and point of healthy skin (SpNT) and equivalent area in healthy skin (ANT). We were able to demonstrate a statistically significant positive correlation between the proposed classification determined by the presence of prognostic factors and staging proposed by the WHO. No correlation was found between disease-free interval (death, new formations, recurrence or metastasis) staging, and prognostic factors. 95% (19/20) of the dogs had their tumors classified as Grade II and 5% (1/20) as Grade I, according to the histological classification of Patnaik (1984). All dogs had their tumors classified as low-grade, according to the classification proposed by Kiupell (2011). 5.6% (10/18) of the animals was graduated as KIT - I, 44.4% (8/18) as KIT - II and 50% (9/18) as KIT - III. No correlation was found between the KIT pattern and disease-free interval or histological grade. Although not statistically significant, we observed a shorter disease-free survival in animals with PCNA and AgNOR above the median (p = 0.089 and p = 0.080, respectively). VEGF was the only marker to show a significant relationship with disease-free interval (p = 0.004). The thermographic images analysis indicated average temperature on SpN of 33.18 º C, SpNT average temperature of 33.39 ° C, AT average temperature of 33.27 º C and ANT average temperature of 33.95 ° C. The difference between the measured points averaged -0.21 ° C (ranging between -5.60 ° C and +4.4 ° C). The difference between the measured points averaged -0.21 ° C (ranging between -5.60 ° C and + 4.4 ° C). This difference was negative in 7/15 cases (47%) - formations cooler than the healthy skin, and positive in 8/15 cases (53%) - formations warmer than the healthy skin. We could not statistically correlate these changes in temperature in the presence of the markers studied, but the statistical analyzes demonstrated that in the region thermography tumor is statistically different from non-tumor region.

Orientador: Aparecido Nilceu Marana / Banca: Roberto Marcondes Cesar Junior / Banca: Ivan Rizzo Guilherme / Resumo: O reconhecimento facial é uma das principais formas de identificação humana. Apesar das pesquisas em reconhecimento facial automático terem crescido substancialmente ao longo dos últimos 35 anos, identificar pessoas a partir da face continua sendo um desafio para as áreas de Visão Computacional e Reconhecimento de Padrões. Em função dos cenários variarem desde a identificação a partir de fotografias até o reconhecimento baseado em vídeos sem nenhum tipo de controle ao serem gravados, os maiores desafios estão relacionados à independência contra diferentes tipos de iluminação, pose e expressão. O objetivo desta dissertação é propor técnicas que possam contribuir para a melhoria dos sistemas de reconhecimento facial. A primeira técnica endereça o problema da iluminação através da fusão dos espectros visível e infravermelho da face. Através desta abordagem, as taxas de reconhecimento foram melhoradas em 2.07% enquanto a taxa de erro igual (EER) foi reduzida em 45.47%. A segunda técnica trata do caso da extração e classificação de características faciais. Ela propõe um novo modelo para reconhecimento facial através do uso de características extraídas por Histogramas Census e de uma técnica de reconhecimento de padrões baseada em Máquinas de Vetores de Suporte (SVMs). Este outro grupo de experimentos nos possibilitou aumentar a precisão do reconhecimento no teste FERET fa/fb em 0.5%. Além destes resultados, algumas contribuições adicionais deste trabalho que merecem ser destacadas são a análise da dependência estatística entre classificadores de espectros diferentes e considerações sobre o comportamento de uma única C-SVC SVM para identificação de pessoas de forma eficaz. / Abstract: Face recognition is one of the primary ways of human identification. Although researches on automated face recognition have broadly increased along the last 35 years, it remains a challenging task in the fields of Computer Vision and Pattern Recognition. As the scenarios varies from static and constrained photographs to uncontrolled video images, the challenging issues on automatic face recognition are usually related with variations in illumination, pose and expressions. The goal of this master thesis is to propose techniques for the improvement of face recognition systems. The first technique addresses the problem of illumination by fusing the visible and the infrared spectra of the face. With this approach the recognition rates were improved in 2.07% while the Equal Error Rate (EER) were reduced in 45.47%. The second technique addresses the issue of face features extraction and classification. It proposes a new framework for face recognition by using features extracted by Census Histograms and a pattern recognition technique based on Support Vector Machines (SVMs). This other group of experiments enabled us to increase the recognition accuracy in the FERET fa/fb test in 0.5%. Beyond these results, additional contributions of this work that deserve to be highlighted are the statistical dependency analysis between face recognition systems based on different spectra and a better comprehension about the behavior of a single C-SVC SVM to reliably predict faces identities. / Mestre

Made available in DSpace on 2014-06-11T19:29:40Z (GMT). No. of bitstreams: 0 Previous issue date: 2009-06-19Bitstream added on 2014-06-13T18:07:45Z : No. of bitstreams: 1 chiachia_g_me_sjrp.pdf: 1197775 bytes, checksum: a782f5b01605aa2a8b8bb080a56b3cad (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / O reconhecimento facial é uma das principais formas de identificação humana. Apesar das pesquisas em reconhecimento facial automático terem crescido substancialmente ao longo dos últimos 35 anos, identificar pessoas a partir da face continua sendo um desafio para as áreas de Visão Computacional e Reconhecimento de Padrões. Em função dos cenários variarem desde a identificação a partir de fotografias até o reconhecimento baseado em vídeos sem nenhum tipo de controle ao serem gravados, os maiores desafios estão relacionados à independência contra diferentes tipos de iluminação, pose e expressão. O objetivo desta dissertação é propor técnicas que possam contribuir para a melhoria dos sistemas de reconhecimento facial. A primeira técnica endereça o problema da iluminação através da fusão dos espectros visível e infravermelho da face. Através desta abordagem, as taxas de reconhecimento foram melhoradas em 2.07% enquanto a taxa de erro igual (EER) foi reduzida em 45.47%. A segunda técnica trata do caso da extração e classificação de características faciais. Ela propõe um novo modelo para reconhecimento facial através do uso de características extraídas por Histogramas Census e de uma técnica de reconhecimento de padrões baseada em Máquinas de Vetores de Suporte (SVMs). Este outro grupo de experimentos nos possibilitou aumentar a precisão do reconhecimento no teste FERET fa/fb em 0.5%. Além destes resultados, algumas contribuições adicionais deste trabalho que merecem ser destacadas são a análise da dependência estatística entre classificadores de espectros diferentes e considerações sobre o comportamento de uma única C-SVC SVM para identificação de pessoas de forma eficaz. / Face recognition is one of the primary ways of human identification. Although researches on automated face recognition have broadly increased along the last 35 years, it remains a challenging task in the fields of Computer Vision and Pattern Recognition. As the scenarios varies from static and constrained photographs to uncontrolled video images, the challenging issues on automatic face recognition are usually related with variations in illumination, pose and expressions. The goal of this master thesis is to propose techniques for the improvement of face recognition systems. The first technique addresses the problem of illumination by fusing the visible and the infrared spectra of the face. With this approach the recognition rates were improved in 2.07% while the Equal Error Rate (EER) were reduced in 45.47%. The second technique addresses the issue of face features extraction and classification. It proposes a new framework for face recognition by using features extracted by Census Histograms and a pattern recognition technique based on Support Vector Machines (SVMs). This other group of experiments enabled us to increase the recognition accuracy in the FERET fa/fb test in 0.5%. Beyond these results, additional contributions of this work that deserve to be highlighted are the statistical dependency analysis between face recognition systems based on different spectra and a better comprehension about the behavior of a single C-SVC SVM to reliably predict faces identities.

Os objetivos deste trabalho foram: Analisar prospectivamente a eficácia da correlação entre parâmetros clínicos, histológicos, e marcadores de proliferação celular buscando melhores indicadores de prognóstico em casos de mastocitoma canino; Testar o uso de nova ferramenta diagnóstica e prognóstica para mastocitomas caninos: a termografia. Para isso, um total de 20 cães com diagnóstico citológico e histopatológico de mastocitoma tiveram suas formações excisadas e foram utilizados para estudo clínico e imunohistoquímico e dentre estes, 15 também para estudo termográfico. As avaliações imunohistoquímicas incluíram quantificação de AgNORs, PCNA, VEGF, localização de KIT. Os estudos termográficos incluíram análise e correlação das temperaturas no ponto central da formação (SpT), e na área da formação (AT) e em ponto de pele sadia (SpNT) e área equivalente, em pele sadia (ANT). Estatisticamente pode-se demonstrar uma correlação positiva significativa entre a classificação proposta determinada pela presença dos fatores prognósticos e o estadiamento proposto pela WHO. Não foi observada correlação estatística entre tempo livre de doença (óbito, novas formações, recidiva ou metástase) e o estadiamento ou fatores prognósticos. 95% (19/20) dos cães teve suas formações classificadas como Grau II e 5% (1/20) Grau I, segundo a classificação histológica de Patnaik (1984). Todos os cães tiveram suas formações classificadas como Baixo Grau, de acordo com a classificação proposta por Kiupell (2011). 5,6% (1/18) dos animais foi considerada padrão KIT - I, 44,4% (8/18) padrão KIT - II e 50% (9/18) padrão KIT - III. Não foi observada correlação estatística entre o padrão KIT e tempo livre de doença ou graduação histológica. Apesar de não significativo estatisticamente, foi notado menor tempo de sobrevida livre de doença nos animais com PCNA e AgNOR acima das medianas (p =0,089 e p = 0,080, respectivamente).O VEGF foi o único marcador a demonstrar relação significativa com o tempo livre de doença (p = 0,004). As análises termográficas indicaram média de temperatura do SpT de 33,18ºC, média de temperatura do SpNT de 33,39ºC, temperatura média de AT de 33,27ºC e temperatura média de ANT de 33,95ºC. A diferença entre os pontos mensurados foi em média -0,21ºC (variando entre -5,60ºC e +4,4ºC). A diferença entre os pontos mensurados foi em média -0,21ºC (variando entre -5,60ºC e +4,4ºC). Esta diferença foi negativa em 7/15 casos (47%) formações mais frias que a pele distante; e positiva em 8/15 casos (53%) formações mais quentes que a pele distante. Não foi possível correlacionar estatisticamente essas alterações de temperatura com a presença dos marcadores estudados, mas as análises estatísticas demonstram que a termografia na região tumoral é estatisticamente diferente da região não tumoral. / The objectives of this study were: To prospectively analyze the effectiveness of the correlation between clinical, histologic, and cell proliferation markers, seeking better indicators of prognosis in cases of canine mast cell tumor; and testing the use of new diagnostic and prognostic tool for canine mast cell tumor: thermography (infrared images); A total of 20 dogs with histopathological and cytological diagnosis of mast cell tumor were excised and their formations were used for immunohistochemical and clinical study, and 15 of those were also used for thermographic study. The evaluations included immunohistochemical quantification of AgNOR, PCNA, VEGF, KIT location. The studies included thermographic images analysis and correlation of the temperatures at the midpoint of tumor (SPT), and tumor area (AT) and point of healthy skin (SpNT) and equivalent area in healthy skin (ANT). We were able to demonstrate a statistically significant positive correlation between the proposed classification determined by the presence of prognostic factors and staging proposed by the WHO. No correlation was found between disease-free interval (death, new formations, recurrence or metastasis) staging, and prognostic factors. 95% (19/20) of the dogs had their tumors classified as Grade II and 5% (1/20) as Grade I, according to the histological classification of Patnaik (1984). All dogs had their tumors classified as low-grade, according to the classification proposed by Kiupell (2011). 5.6% (10/18) of the animals was graduated as KIT - I, 44.4% (8/18) as KIT - II and 50% (9/18) as KIT - III. No correlation was found between the KIT pattern and disease-free interval or histological grade. Although not statistically significant, we observed a shorter disease-free survival in animals with PCNA and AgNOR above the median (p = 0.089 and p = 0.080, respectively). VEGF was the only marker to show a significant relationship with disease-free interval (p = 0.004). The thermographic images analysis indicated average temperature on SpN of 33.18 º C, SpNT average temperature of 33.39 ° C, AT average temperature of 33.27 º C and ANT average temperature of 33.95 ° C. The difference between the measured points averaged -0.21 ° C (ranging between -5.60 ° C and +4.4 ° C). The difference between the measured points averaged -0.21 ° C (ranging between -5.60 ° C and + 4.4 ° C). This difference was negative in 7/15 cases (47%) - formations cooler than the healthy skin, and positive in 8/15 cases (53%) - formations warmer than the healthy skin. We could not statistically correlate these changes in temperature in the presence of the markers studied, but the statistical analyzes demonstrated that in the region thermography tumor is statistically different from non-tumor region.

Image based modeling using visual images has undergone major development during the earlier parts of the 21th century. In this thesis a system for automated uncalibrated scene reconstruction using infrared images is implemented and tested. An automated reconstruction system could serve to simplify thermal inspection or as a demonstration tool. Thermal images will in general have lower resolution, less contrast and less high frequency content as compared to visual images. These characteristics of infrared images further complicates feature extraction and matching, key steps in the reconstruction process. In order to remedy the complication preprocessing methods are suggested and tested as well. Infrared modeling will also impose additional demands on the reconstruction as it is of importance to maintain thermal accuracy of the images in the product. Three main results are obtained from this thesis. Firstly, it is possible to obtain camera calibration and pose as well as a sparse point cloud reconstruction from an infrared image sequence using the suggested implementation. Secondly, correlation of thermal measurements from the images used to reconstruct three dimensional coordinates is presented and analyzed. Lastly, from the preprocessing evaluation it is concluded that the tested methods are not suitable. The methods will increase computational cost while improvements in the model are not proportional. / Bildbaserad modellering med visuella bilder har genomgått en stor utveckling under de tidigare delarna av 2000-talet. Givet en sekvens bestående av vanliga tvådimensionella bilder på en scen från olika perspektiv så är målet att rekonstruera en tredimensionell modell. I denna avhandling implementeras och testas ett system för automatiserad okalibrerad scenrekonstruktion från infraröda bilder. Okalibrerad rekonstruktion refererar till det faktum att parametrar för kameran, såsom fokallängd och fokus, är okända och enbart bilder används som indata till systemet. Ett stort användingsområde för värmekameror är inspektion. Temperaturskillnader i en bild kan indikera till exempel dålig isolering eller hög friktion. Om ett automatiserat system kan skapa en tredimensionell modell av en scen så kan det bidra till att förenkla inspektion samt till att ge en bättre överblick. Värmebilder kommer generellt att ha lägre upplösning, mindre kontrast och mindre högfrekvensinnehåll jämfört med visuella bilder. Dessa egenskaper hos infraröda bilder komplicerar extraktion och matchning av punkter i bilderna vilket är viktiga steg i rekonstruktionen. För att åtgärda komplikationen förbehandlas bilderna innan rekonstruktionen, ett urval av metoder för förbehandling har testats. Rekonstruktion med värmebilder kommer också att ställa ytterligare krav på rekonstruktionen, detta eftersom det är viktigt att bibehålla termisk noggrannhet från bilderna i modellen. Tre huvudresultat erhålls från denna avhandling. För det första är det möjligt att beräkna kamerakalibrering och position såväl som en gles rekonstruktion från en infraröd bildsekvens, detta med implementationen som föreslås i denna avhandling. För det andra presenteras och analyseras korrelationen för temperaturmätningar i bilderna som används för rekonstruktionen. Slutligen så visar den testade förbehandlingen inte en förbättring av rekonstruktionen som är propotionerlig med den ökade beräkningskomplexiteten.

Now and then train accidents occur. Collisions between trains and objects such as animals, humans, cars, and fallen trees can result in casualties, severe damage on the train, and delays in the train traffic. Thus, train collisions are a considerable problem with consequences affecting society substantially. The company Termisk Systemteknik AB has on commission by Rindi Solutions AB investigated the possibility to detect anomalies on the railway using a trainmounted thermal imaging camera. Rails are also detected in order to determine if an anomaly is on the rail or not. However, the rail detection method does not work satisfactory at long range. The purpose of this master’s thesis is to improve the previous rail detector at long range by using machine learning, and in particular deep learning and a convolutional neural network. Of interest is also to investigate if there are any advantages using cross-modal transfer learning. A labelled dataset for training and testing was produced manually. Also, a loss function tailored to the particular problem at hand was constructed. The loss function was used both for improving the system during training and evaluate the system’s performance during testing. Finally, eight different approaches were evaluated, each one resulting in a different rail detector. Several of the rail detectors, and in particular all the rail detectors using crossmodal transfer learning, perform better than the previous rail detector. Thus, the new rail detectors show great potential to the rail detection problem.

Training data is an essential ingredient within supervised learning, yet time con-suming, expensive and for some applications impossible to retrieve. Thus it isof interest to use synthetic training data. However, the domain shift of syntheticdata makes it challenging to obtain good results when used as training data fordeep learning models. It is therefore of interest to refine synthetic data, e.g. using image-to-image translation, to improve results. The aim of this work is to compare different methods to do image-to-image translation of synthetic training data of thermal IR-images using GANs. Translation is done both using synthetic thermal IR-images alone, as well as including pixelwise depth and/or semantic information. To evaluate, a new measure based on the Frechét Inception Distance, adapted to work for thermal IR-images is proposed. The results show that the model trained using IR-images alone translates the generated images closest to the domain of authentic thermal IR-images. The training where IR-images are complemented by corresponding pixelwise depth data performs second best. However, given more training time, inclusion of depth data has the potential to outperform training withirdata alone. This gives a valuable insight on how to best translate images from the domain of synthetic IR-images to that of authentic IR-images, which is vital for quick and low cost generation of training data for deep learning models.

點雲（point cloud）為以大量三維坐標描述地表實際情形的資料形式，其中包含其三維坐標及相關屬性。通常點雲資料取得方式為光達測量，其以單一波段雷射光束掃描獲取資料，以光達獲取點雲，常面臨掃描時間差、缺乏多波段資訊、可靠邊緣線及角點資訊、大量離散點雲又缺乏語意資訊（semantic information）難以直接判讀及缺乏多餘觀測量等問題。 攝影測量藉由感測反射自太陽光或地物本身放射之能量，可記錄為二維多光譜影像，透過地物在不同光譜範圍表現之特性，可輔助分類，改善分類成果。若匹配多張高重疊率的多波段影像，可以獲取包含多波段資訊且位於明顯特徵點上的點雲，提供光達以外的點雲資料來源。 傳統空中三角測量平差解算地物點坐標及產製數值表面模型（Digital Surface Model, DSM）時，多採用可見光影像為主；而目前常見之高空間解析度數值航照影像，除了記錄可見光波段之外，亦可蒐集近紅外光波段影像。但較少採用近紅外光波段影像，以求解地物點坐標及建立DSM。 因此本研究利用多波段影像所蘊含的豐富光譜資訊，以取像方式簡易及低限制條件的近景攝影測量方式，匹配多張可見光、近紅外光及紅外彩色影像，分別建立可見光、近紅外光及紅外彩色之DSM，其目的在於探討加入近紅外光波段後，所產生的近紅外光及紅外彩色DSM，和可見光DSM之異同；並比較該DSM是否更能突顯植被區。 研究顯示，以可見光點雲為檢核資料，計算近紅外光與紅外彩色點雲的均方根誤差為其距離門檻值之相對檢核方法，可獲得約21%的點雲增加率；然而使用近紅外光或紅外彩色影像，即使能增加點雲資料量，但對於增加可見光影像未能匹配的資料方面，其效果仍屬有限。 / Point cloud represents the surface as mass 3D coordinates and attributes. Generally, these data are usually collected by LIDAR (LIght Detection And Ranging), which acquires data through single band laser scanning. But the data collected by LIDAR could face problems, such as scanning process is not instantaneous, lack of multispectral information, breaklines, corners, semantic information and redundancies. However, photogrammetry record the electromagnetic energy reflected or emitted from the surface as 2D multispectral images, via ground features with different characteristics differ in spectrum, it can be classified more efficiently and precisely. By matching multiple high overlapping multispectral images, point cloud including multispectral information and locating on obvious feature points can be acquired. This provides another point cloud source aparting from LIDAR. In most studies, visible light (VIS) images are used primarily, while calculating ground point coordinates and generating digital surface models （DSM） through aerotriangulation. Although nowadays, high spatial resolution digital aerial images can acquire not only VIS channel, but also near infrared (NIR) channel as well. But there is lack of research doing the former procedures by using NIR images. Therefore, this research focuses on the rich spectral information in multispectral images, by using easy image collection and low restriction close range photogrammetry method. It matches several VIS, NIR and color infrared (CIR) images, and generate DSMs respectively. The purpose is to analyze the difference between VIS, NIR and CIR data sets, and whether it can emphasize the vegetation area, after adding NIR channel in DSM generation. The result shows that by using relative check points between NIR, CIR data with VIS one. First, VIS point cloud was set as check point data, then, the RMSE (Root Mean Square Error) of NIR and CIR point cloud was calculated as distance threshold. Its data increment is 21% ca. However, the point cloud data amount can be increased, by matching NIR and CIR images. But the effect of increasing data, which was not being matched from VIS images are limited.

Η κατασκευή συστημάτων τομογραφίας του ανθρώπινου ιστού τα οποία θα χρησιμοποιούν το υπέρυθρο φάσμα ακτινοβολίας αποτελεί σημαντική προοπτική για τη δημιουργία νέων ιατρικών διαγνωστικών μεθόδων. Ένα από τα σημαντικότερα προβλήματα που πρέπει να επιλυθούν είναι η μικρή διεισδυτική ικανότητα και ο υψηλός βαθμός απορρόφησης και σκέδασης που παραμορφώνει ισχυρά την ακτινοβολία που διαδίδεται μέσα από τον ανθρώπινο ιστό. Στα πλαίσια της διδακτορικής διατριβής, μελετήθηκε το πρόβλημα του εντοπισμού της θέσης των αγγείων σε ψηφιακές φωτογραφίες του ανθρώπινου δακτύλου που έχουν ληφθεί στο υπέρυθρο φάσμα. Για τον σκοπό αυτό αναπτύχθηκε μεγάλος αριθμός πρωτότυπων μεθόδων κανονικοποίησης της φωτεινότητας της εικόνας, μη-γραμμικής ενίσχυσης της αντίθεσης, αφαίρεσης των γραμμών δακτυλικών αποτυπωμάτων, εντοπισμού του προτύπου ή δικτύου αγγείων και βελτίωσης του προτύπου των αγγείων χρησιμοποιώντας μεθόδους μαθηματικής μορφολογίας. Συνοπτικά στην παρούσα διδακτορική διατριβή προτάθηκαν και εξετάσθηκαν διαφορετικές πρωτότυπες μέθοδοι και αλγόριθμοι με επίβλεψη ή χωρίς επίβλεψη για την εξαγωγή του προτύπου αγγείων από υπέρυθρες εικόνες του ανθρώπινου δακτύλου καθώς και διαφορετικές πρωτότυπες μέθοδοι και αλγόριθμοι χωρίς επίβλεψη για την εξαγωγή του δικτύου αγγείων από αμφιβληστροειδικές εικόνες του ανθρώπινου οφθαλμού. Επίσης, η ερευνητική προσπάθεια επικεντρώθηκε στην βελτίωση των εικόνων που λαμβάνονται από το προτεινόμενο σύστημα απόκτησης εικόνων, γεγονός το οποίο οδήγησε στην ανάπτυξη πρωτότυπων μεθόδων προ-επεξεργασίας και τη μετέπειτα βελτίωση των αρχικών αποτελεσμάτων κατάτμησης που προκύπτουν από την εφαρμογή των μεθόδων ή αλγορίθμων κατάτμησης προτύπου αγγείων, γεγονός το οποίο οδήγησε στην ανάπτυξη πρωτότυπων μεθόδων μετά-επεξεργασίας. / The construction of tomographic systems of human tissue which use the infrared spectrum of radiation constitutes an important capability of making new medical diagnostic methods. One of the most crucial problems which must be resolved is the low penetrating ability and the high degree of absorption and scattering which strongly distort the radiation that pass through the human tissue. In this thesis, the problem of the extraction of finger vein pattern from infrared images of finger and the similar problem of retinal vessel tree segmentation were studied. Moreover, the problem of shading and non-uniform illumination correction was also studied in images which suffer from the above problems either due to imperfect set-up of the image acquisition system or due to the interaction between objects and illumination on the scene. In this thesis, existing algorithms were improved and novel algorithms were developed. Both vein pattern extraction algorithms and shading and non-uniform illumination correction algorithms were proposed. The proposed methods include novel preprocessing modules for intensity normalization, elimination of fingerprint lines, non linear contrast enhancement using spatial information, and shading and non uniform illumination correction. The vein pattern extraction was performed using ten novel methods that use structural classification methods, spatial derivatives information and fuzzy set theory. The effectiveness of the proposed methods and algorithms was evaluated both on real and artificial images distorted by different types of noise and different signal to noise ratios. The majority of the methods present satisfactory accuracy on the detection of vein network, something happens due to the successful collaboration between the preprocessing methods and the vein pattern extraction methods. In addition, the problem of improving the vein network extraction accuracy was successfully handled using advanced postprocessing methods based on binary mathematical morphology. Finally, in this thesis two novel methods for retinal vessel segmentation were proposed and evaluated. They also compared with the most important methods have already been presented in the literature and one of them achieved the best experimental results from all the unsupervised methods evaluated in the publicly available DRIVE database.