M. Tech. Computer System Engineering / Autonomous robots are extensively used equipment in industries and in our daily lives; they assist in manufacturing and production but are used for exploration in dangerous or unknown environments. However for a successful exploration, manufacturing and production, navigation plays an important role. Road detection is a vital factor that assists autonomous robots in perfect navigation. Different methods using camera-vision technique have been developed by various researchers with outstanding results, but their systems are still vulnerable to environmental risks. The frequent weather change in various countries such as South Africa, Nigeria and Zimbabwe where shadow, light intensity and other environmental noises occur on daily basis, can cause autonomous robot to encounter failure in navigation. Therefore, the main research question is: How to enhance the road region detection system to enable an effective and efficient maneuvering of the robot in any weather condition.

Thesis (M.App.Sc.) - Carleton University, 2005. / Includes bibliographical references (p. 172-178). Also available in electronic format on the Internet.

Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2011. / ENGLISH ABSTRACT: Search and Rescue is an essential service provided by States and Militaries to search for, locate and rescue survivors of accidents and incidents. Civil Search and Rescue utilizes a system of well-trained professionals or volunteers, an effective Search and Rescue organization, supported by industry and other providers of infrastructure and assets. The service is rendered to save the lives of civilian individuals in imminent danger of losing their lives. Military (Combat) Search and Rescue is provided by militaries to save the lives of military practitioners in a similar predicament. In addition, Search and Rescue is performed over land and over the sea. All forms of Search and Rescue rely on capable, specialized assets for efficiency en affectivity. Assets are specified and chosen on the grounds of various factors, amongst others operating environment, operational profile, performance and special abilities. This thesis has determined the need for a Search and Rescue asset, capable of performing effective and efficient Search and Rescue over the entire national maritime Search and Rescue Region, up to the Region extremities. An analysis was performed to prove this deficit, and quantify the key performance and special equipment requirements for such an asset. An analysis was also performed which proves that an Unmanned Aircraft System should be an ideal choice to meet this need. Finally, an Unmanned Aircraft System concept was specified that could potentially meet this need. / AFRIKAANSE OPSOMMING: Soek en Redding is ‘n essentiële diens wat deur State en militêre organisasies gebied word om oorlewendes van ongelukke en insidente te soek, op te spoor en na veiligheid te bring. Siviele Soek en Redding maak gebruik van ‘n stelsel van goedopgeleide professionele persone, sowel as vrywilligers, asook ‘n effektiewe Soek en Reddingsorganisasie, ondersteun deur die industrie en ander voorsieners van infrastruktuur en toerusting. Derglike dienste word daargestel om die lewens van siviele persone, wie se lewens in gevaar is, te red. Militêre Soek en Redding word deur militêre organisasies daargetel om die lewens van militêre persone, wie in gevaar is, te red. Soek en Redding word oor land sowel as oor die see uitgevoer. Alle vorms van Soek en Redding maak staat op die beskikbaarheid van gespesialiseerde toerusting met gespesialiseerde gebruiksaanwending, vir maksimale effektiwiteit en doeltreffendheid. Toerusting word gekies op grond van verskeie faktore, onder meer die gebruiksomgewing, operasionele profiele, verlangde prestasie en spesiale vermoëns. Hierdie tesis het die behoefte aan ‘n gespesialiseerde Soek en Redding platform, wat die vermoë het om effektiewe en doeltreffende Soek en Redding uit te voer oor die hele nationale Soek en Redding Gebied, tot en met die ekstreme daarvan, vasgestel. ‘n Analise is uitgevoer om hierdie tekortkoming uit te wys, asook om die sleutel prestasie- en gespesialiseerde toerustingbehoeftes vir so ‘n platform te kwantifiseer. ‘n Verdere analise is uitgevoer om te bewys dat ‘n Onbemande Vliegtuig die beste opsie sou wees vir ‘n platform om aan hierdie behoeftes te voldoen. Ten slotte is ‘n konsep vir ‘n Onbemande Vliegtuig Stelsel voorgetsel wat potensieël hierdie behoefte sou kon vervul.

Approved for public release; distribution in unlimited. / On 1 October 2003 the USAF transferred control of its CONUS-based combat search and rescue(CSAR) assets from Air Combat Command to Air Force Special Operations Command (AFSOC). Transferto AFSOC was CSAR's fourth major reorganization in twenty years, and was the latest in a turbulentprocession of attempts to improve the combat effectiveness of CSAR forces. Despite possessing anabundance of brave, motivated, and extremely capable personnel yearning to accomplish their mission, dysfunctional organizational arrays and nagging organizational constraints have prevented USAF dedicatedCSAR forces from "getting to the fight" for the onset of hostilities in three of this nation's past four majorarmed conflicts. Special operations forces had to fill the void. This analysis evaluates CSAR's positionwithin AFSOC's organizational array to determine if this latest reorganization is likely to produce durableimprovements in CSAR combat effectiveness. My conclusion is that "CSAR friendly" organizational cultureand effective organizational constructs within AFSOC Headquarters, combined with highly receptiveattitudes among CSAR crewmembers, form a historically unique organizational mix that favors the long termsuccess of CSAR forces in AFSOC. To ensure AFSOC's favorable organizational posture is translated toimproved combat capability, leadership must immediately increase CSAR representation on HHQ staffs. / Major, United States Air Force

published_or_final_version / Architecture / Master / Master of Architecture

Thesis (doctoral)--Technische Universität, Berlin, 2005. / Includes bibliographical references (p. 220-238).

This thesis studies the performance of search dogs trained to locate the live scent (live only dogs) and compares their performance to that of search dogs trained to locate either live or cadaver scent depending on the verbal cue given by the handler (cross-trained dogs).

This diploma thesis deals with the topic German-French cooperation on crisis management in the eurozone. Germany and France, represented by chancellor Merkel and president Sarkozy, cooperated together very closely during the crisis and contributed significantly to the further deepening of European economic and monetary union. The aim of this thesis is to analyze and compare the features of the German and French European policy and the German and French ideas about the functioning of economic and monetary union. Secondly, to examine the progress of the German- French cooperation on finding crisis solutions. And finally to define convergence and divergence in the crisis management of both countries. Due to different ideas about economic policy - the German ordoliberalism and French concept called Gouvernance économique - both countries were forced to make mutual concessions. The most important compromises within the anti-crisis measures are the bailouts to indebted countries, European rescue funds or tightening budgetary discipline of European countries by using the fiscal pact. Nevertheless, there are still areas in which both countries disagree, primarily the Eurobonds and other measures to support economic growth. The last part is devoted to the question of German models implementation into the EU and the...

CAPES / Este trabalho tem como objetivo propor um método reconhecimento de pessoas em imagens aéreas obtidas a partir de Veículos Aéreos Não Tripulados de pequeno porte. Esta é uma aplicação de grande interesse, pois pode ser inserida em diversas situações tanto civis quanto militares como, por exemplo, missões de busca e salvamento. O uso de Veículos Aéreos Não Tripulados autônomos tende a aumentar com o barateamento desta tecnologia. Assim, esta tecnologia pode sobressair sobre outras utilizadas atualmente, como satélites e voos com grandes aeronaves. Para o reconhecimento de pessoas em imagens aéreas de forma autônoma, este trabalho propõe métodos na forma de Sistemas de Reconhecimento de Padrões (SRP) aplicados ao reconhecimento de imagens. Para este métodos, foram testadas quatro técnicas de aprendizado de máquina: Redes Neurais Convolucionais, HOG+SVM, Cascata Haar e Cascata LBP. Além disso, a fim de possibilitar o reconhecimento de pessoas em imagens aéreas em tempo real, foram testadas e avaliadas técnicas de detecção e segmentação de objetos: Mapa de Saliências e o Processamento de Imagens Térmicas de baixa resolução (PIT). Neste trabalho foram avaliadas as taxas de reconhecimento dos SRPs, além do seu tempo de processamento em um sistema embarcado de baixo custo e em uma Base de Controle Móvel (BCM). Os resultados de reconhecimento mostraram a efetividade das Redes Neurais Convolucionais, com uma acurácia de 0,9971, seguido do HOG+SVM com 0,9236, Cascata Haar com 0,7348 e por fim, Cascata LBP com 0,6615. Em situações onde foi simulado a oclusão parcial, as Redes Neurais Convolucionais atingiram Sensibilidade média 0,72, HOG+SVM de 0,50 e as Cascatas 0,20. Nos experimentos com os SRPs (algoritmos de segmentação e detecção juntamente com as técnicas de reconhecimento), o Mapa de Saliências pouco afetou as taxas de reconhecimento, quais ficaram muito próximas das obtidas no experimentos de reconhecimento. Já o Processamento de Imagens Térmicas de baixa resolução apresentou dificuldades em executar uma segmentação precisa, obtendo imagens com variação na translação, prejudicando a precisão do sistema. Por fim, este trabalho propõe uma nova abordagem para implementação de um SRP para o reconhecimento de pessoas em imagens áreas, utilizando Processamento de Imagens Térmicas juntamente com as Redes Neurais Convolucionais. Este SRP une altas taxas de reconhecimento com desempenho computacional de ao menos 1 fps na plataforma BCM. / This work aims to propose a method for people recognition in Small Unmanned Aerial Vehicles aerial imagery. This is an application of high interest, it can be used in several situations, both civilian and military, as search and rescue missions. The use of Unmanned Aerial Vehicles autonomously tends to increase with the cheapening of this technology, supporting search and rescue missions. Thus, this technology can excel over others currently used, as satellites and flights with large aircraft. For autonomous people recognition, this work proposes new methods as Pattern Reconigition System (PRS) applied to image recognition, applying it in aerial images. Four Pattern Reconigition techniques were tested: Convolutional Neural Networks, HOG+SVM, Haar Cascade and LBP Cascade. Furthermore, in order to achieve recognition of people in aerial images in Real-Time target and detection techniques were tested and evaluated: Saliency Maps and Low-resolution Thermal Image Processing (TIP). In this work were considered recognition rates of the methods and their computational time in a low-cost embedded system and a Mobile Ground Control Station (MGCS). The recognition results shown the Convolutional Neural Network potential, where an accuracy of 0.9971 was achieved, followed by HOG + SVM with 0.9236, Haar Cascade with 0.7348 and LBP Cascade with 0.6615. In situations simulated partial occlusion, where was the CNNs achieved average Sensitivity of 0.72, HOG+SVM with 0.50 and both Cascades 0.20. In experiments with PRS (targeting and detection algorithms with the recognition techniques), the Saliency Map had little influence in recongition rates, it was close to the rates achieved in recognition experiments. While the Low-resolution Thermal Image Processing had difficulties in segmentation process, where translation variantions occured, it harmed the system precision. Lastly, this work proposes a new approach for PRS implementation for people recognition in aerial imagery, using TIP with CNN. This PRS combines high rates of recognition with an computational performace of, at least, 1 fps in MGCS plataform.

CAPES / Este trabalho tem como objetivo propor um método reconhecimento de pessoas em imagens aéreas obtidas a partir de Veículos Aéreos Não Tripulados de pequeno porte. Esta é uma aplicação de grande interesse, pois pode ser inserida em diversas situações tanto civis quanto militares como, por exemplo, missões de busca e salvamento. O uso de Veículos Aéreos Não Tripulados autônomos tende a aumentar com o barateamento desta tecnologia. Assim, esta tecnologia pode sobressair sobre outras utilizadas atualmente, como satélites e voos com grandes aeronaves. Para o reconhecimento de pessoas em imagens aéreas de forma autônoma, este trabalho propõe métodos na forma de Sistemas de Reconhecimento de Padrões (SRP) aplicados ao reconhecimento de imagens. Para este métodos, foram testadas quatro técnicas de aprendizado de máquina: Redes Neurais Convolucionais, HOG+SVM, Cascata Haar e Cascata LBP. Além disso, a fim de possibilitar o reconhecimento de pessoas em imagens aéreas em tempo real, foram testadas e avaliadas técnicas de detecção e segmentação de objetos: Mapa de Saliências e o Processamento de Imagens Térmicas de baixa resolução (PIT). Neste trabalho foram avaliadas as taxas de reconhecimento dos SRPs, além do seu tempo de processamento em um sistema embarcado de baixo custo e em uma Base de Controle Móvel (BCM). Os resultados de reconhecimento mostraram a efetividade das Redes Neurais Convolucionais, com uma acurácia de 0,9971, seguido do HOG+SVM com 0,9236, Cascata Haar com 0,7348 e por fim, Cascata LBP com 0,6615. Em situações onde foi simulado a oclusão parcial, as Redes Neurais Convolucionais atingiram Sensibilidade média 0,72, HOG+SVM de 0,50 e as Cascatas 0,20. Nos experimentos com os SRPs (algoritmos de segmentação e detecção juntamente com as técnicas de reconhecimento), o Mapa de Saliências pouco afetou as taxas de reconhecimento, quais ficaram muito próximas das obtidas no experimentos de reconhecimento. Já o Processamento de Imagens Térmicas de baixa resolução apresentou dificuldades em executar uma segmentação precisa, obtendo imagens com variação na translação, prejudicando a precisão do sistema. Por fim, este trabalho propõe uma nova abordagem para implementação de um SRP para o reconhecimento de pessoas em imagens áreas, utilizando Processamento de Imagens Térmicas juntamente com as Redes Neurais Convolucionais. Este SRP une altas taxas de reconhecimento com desempenho computacional de ao menos 1 fps na plataforma BCM. / This work aims to propose a method for people recognition in Small Unmanned Aerial Vehicles aerial imagery. This is an application of high interest, it can be used in several situations, both civilian and military, as search and rescue missions. The use of Unmanned Aerial Vehicles autonomously tends to increase with the cheapening of this technology, supporting search and rescue missions. Thus, this technology can excel over others currently used, as satellites and flights with large aircraft. For autonomous people recognition, this work proposes new methods as Pattern Reconigition System (PRS) applied to image recognition, applying it in aerial images. Four Pattern Reconigition techniques were tested: Convolutional Neural Networks, HOG+SVM, Haar Cascade and LBP Cascade. Furthermore, in order to achieve recognition of people in aerial images in Real-Time target and detection techniques were tested and evaluated: Saliency Maps and Low-resolution Thermal Image Processing (TIP). In this work were considered recognition rates of the methods and their computational time in a low-cost embedded system and a Mobile Ground Control Station (MGCS). The recognition results shown the Convolutional Neural Network potential, where an accuracy of 0.9971 was achieved, followed by HOG + SVM with 0.9236, Haar Cascade with 0.7348 and LBP Cascade with 0.6615. In situations simulated partial occlusion, where was the CNNs achieved average Sensitivity of 0.72, HOG+SVM with 0.50 and both Cascades 0.20. In experiments with PRS (targeting and detection algorithms with the recognition techniques), the Saliency Map had little influence in recongition rates, it was close to the rates achieved in recognition experiments. While the Low-resolution Thermal Image Processing had difficulties in segmentation process, where translation variantions occured, it harmed the system precision. Lastly, this work proposes a new approach for PRS implementation for people recognition in aerial imagery, using TIP with CNN. This PRS combines high rates of recognition with an computational performace of, at least, 1 fps in MGCS plataform.