The ubiquitous nature of CCTV Surveillance cameras means substantial amounts of data being generated. In case of an investigation, this data must be manually browsed and analysed in search of relevant information for the case. As an example, it took more than 450 detectives to examine the hundreds of thousands of hours of videos in the investigation of the 2011 London Riots: one of the largest the London's MET police has ever seen. Anything that can help the security forces save resources in investigations such as this, is valuable. Consequently, automatic analysis of surveillance scenes is a growing research area. One of the research fronts tackling this issue, is the semantic understanding of the scene. In this, the output of computer vision algorithms is fed into Semantic Frameworks, which combine all the information from different sources and try to reach a better knowledge of the scene. However, representing and reasoning with imprecise and uncertain information remains an outstanding issue in current implementations. The Demspter-Sha er (DS) Theory of Evidence has been proposed as a way to deal with imprecise and uncertain information. In this thesis we use it for the main contributions. In our rst contribution, we propose the use of the DS theory and its Transferable Belief Model (TBM) realisation as a way to combine Bayesian priors, using the subjectivist view of the Bayes' Theorem, where the probabilities are beliefs. We rst compute the a priori probabilities of all the pair of events in the model. Then a global potential is created for each event using the TBM. This global potential will encode all the prior knowledge for that particular concept. This has the bene t that when this potential is included in a knowledge base because it has been learned, all the knowledge it entails comes with it. We also propose a semantic web reasoner based on the TBM. This reasoner consists of an ontology to model any domain knowledge using the TBM constructs of Potentials, Focal Elements, and Con gurations. The reasoner also consists of the implementations of the TBM operations in a semantic web framework. The goal is that after the model has been created, the TBM operations can be applied and the knowledge combined and queried. These operations are computationally complex, so we also propose parallel heuristics to the TBM operations. This allows us to apply this paradigm on problems of thousands of records. The nal contribution, is the use of the TBM semantic framework with the method to combine the prior knowledge to detect riots on CCTV footage from the 2011 London riots. We use around a million and a half manually annotated frames with 6 di erent concepts related to the riot detection task, train the system, and infer the presence of riots in the test dataset. Tests show that the system yields a high recall, but a low precision, meaning that there are a lot of false positives. We also show that the framework scales well as more compute power becomes available.

No description available.

This thesis explores the influences of provincial grant programs on Canadian streetscape camera systems. Using qualitative interviews (N=32) and document analysis, the study explores the policymaking processes and outcomes of six Ontario cities that have engaged with the Civil Remedies and Proceeds of Crime grants. Grant programs have not only provided the financial support to facilitate the establishment or expansion of camera systems, but they have also encouraged particular patterns of implementation, design and operation of Canadian streetscape systems through the processes and conditions of the grant program, as well as through the encouragement of regional networking, policy learning and policy diffusion via policy tourism. While the Civil Remedies and Proceeds of Crime grants have influenced some similarities in streetscape camera systems, variation exists, particularly concerning privacy policies, due to idiosyncratic interpretation and adoption of diffused policies and an ambiguous and unclear privacy protection framework. / Graduate / 0626 / 0627 / dennymah@uvic.ca

This thesis is done by two students from Blekinge Institute of Technology as an end of the master of engineering program with emphasis on applied mechanics. The thesis is done in cooperation with Axis Communications AB in Lund which develop surveillance cameras. The task was to design and implement an Angular Vibration Testing Equipment. Axis needs this to test their surveillance cameras for angular vibrations. These vibrations occur usually on cameras located on poles placed at roads and at train stations. The thesis has been carried out in three different phases where the first phase handled a deeper understanding of the problem, planning and investigating of related works. Axis has a solution for smaller cameras called Shakespeare MK I and this was used as an inspiration for us. The second phase included concept generation and concept evaluation. This has been done with brainstorming, workshop and concept scoring. At the last phase a prototype was built and tested and a detailed design was made. Two versions of the prototype were made and they showed that the concept works well. The project resulted in a working prototype that can transform linear motion to rotation around two axes. A drawing and a cost calculation were made for the final concept. The final construction is still not completely optimized and has improvement and adjustment possibilities that might be needed.

Made available in DSpace on 2016-04-26T18:13:18Z (GMT). No. of bitstreams: 1 Caio Favero Marchi.pdf: 22773905 bytes, checksum: 60dcceb2b3dc81852213e20a958e5fa3 (MD5) Previous issue date: 2013-09-19 / The object of this study is one of the patterns (Surveillance) of the Security Lens of that which researchers from Brunel University have called Design with Intent (DwI). Based on the question suggested by the object of the study itself (What would happen if citizens knew, or at least believed, that their behavior is being seen or monitored by people in positions of power or authority?) and in the dissemination, more patent every day, of surveillance and control devices in the major metropolises of the world, as is the case of São Paulo, the question that will guide us is: to which extent does the pattern Surveillance, a development of the Security Lens of DwI, incite social behaviors? With the purpose of answering this question and to prove the hypotheses that this method standardizes social behaviors and that it acts, moreover, as a control device of contemporary societies, this study will make use of a hybrid methodology, composed of bibliographic research, documental research and unstructured and undirected interviews. The theoretical frame of reference of the bibliographic research will include Castel (2005) and Bauman (2009) to present the issue of fear and insecurity in large cities; Vaz (2004; 2005; 2006), Kellner (2001) and Wainberg (2005) to clarify the contribution of mass media in the construction of the image of urban violence; Foucault (1997; 2008), Deleuze (2010), Hardt (2000), Rose (1999) and Costa (2004) to elaborate an overview of the transformations and characteristics of the different societal models; Lockton, Harrison and Stanton (2011) to introduce and deepen the debates on the importance of DwI; and Norris and Armstrong (199), Bruno (2010) and Kanashiro (2010) to broach the topic of surveillance and the development of its technological devices (CCTV). The documental research will collect information on violence and fear in the capital of the state of São Paulo from magazines, newspapers and television reports. Finally, we will carry out interviews with the supervisor of the Video Monitoring Center of the São Paulo State Military Police and with the captain of the Batallion that holds the Operation Center of the São Paulo State Military Police (COPOM). These interviews will attempt to extract from primary sources data and information that illustrate some passages of the text in order to allow us to draw a conclusion about the matter in a consistent manner / segurança (Security Lens) daquilo que estudiosos da Universidade de Brunel intitularam Design with Intent (DwI). Com base na questão sugerida pelo próprio objeto de estudo dessa investigação (O que aconteceria se os cidadãos soubessem, ou ao menos acreditassem, que seu comportamento está sendo visto ou monitorado por pessoas que são detentoras de poder ou autoridade?) e na disseminação, cada dia mais evidente, dos dispositivos de vigilância e controle nas grandes metrópoles urbanas do globo, como é o caso de São Paulo, a questão que nos servirá como elemento norteador é: em que medida o pattern Surveillance, desdobramento da lente de segurança do DwI, incita comportamentos sociais? Com o objetivo de responder a essa problemática e de comprovar as hipóteses de que tal método padroniza os comportamentos sociais e ainda atua como um dispositivo de controle das sociedades contemporâneas, esse estudo se utilizará de uma metodologia híbrida, composta por uma pesquisa bibliográfica, uma pesquisa documental e entrevistas não estruturadas e não dirigidas. A pesquisa bibliográfica contará com um referencial teórico formado por Castel (2005) e Bauman (2009) para apresentar a questão do medo e da insegurança nas grandes cidades; Vaz (2004; 2005; 2006), Kellner (2001) e Wainberg (2005) para esclarecer a contribuição da mídia de massa na construção da imagem da violência urbana; Foucault (1997; 2008), Deleuze (2010), Hardt (2000), Rose (1999) e Costa (2004) para elaborar um panorama sobre as transformações e as características dos diferentes modelos de sociedade; Lockton, Harrison e Stanton (2011) para introduzir e aprofundar os debates sobre a importância do DwI; e Norris e Armstrong (1999), Bruno (2010) e Kanashiro (2006) para abordar o tema da vigilância e o desenvolvimento de seus dispositivos tecnológicos (CCTV). A pesquisa documental coletará informações sobre a violência e o medo na capital paulistana em revistas, jornais e matérias televisivas. Por fim, serão realizadas entrevistas não estruturadas e não dirigidas com o supervisor do Centro de Vídeo Monitoramento da Polícia Militar do Estado de São Paulo e com o capitão do Batalhão que abriga o Centro de Operações da Polícia Militar do Estado de São Paulo (COPOM). Essas entrevistas buscarão extrair de fontes primárias dados e informações que ilustrem algumas passagens do texto e que possibilitem que uma conclusão sobre o assunto seja elaborada de forma consistente

High resolution surveillance video cameras are invaluable resources for effective crime prevention and forensic investigations. However, increasing communication bandwidth requirements of high definition surveillance videos are severely limiting the number of cameras that can be deployed. Higher bitrate also increases operating expenses due to higher data communication and storage costs. Hence, it is essential to develop low complexity algorithms which reduce data rate of the compressed video stream without affecting the image fidelity. In this thesis, a computer vision aided H.264 surveillance video encoder and four associated algorithms are proposed to reduce the bitrate. The proposed techniques are (I) Speeded up foreground segmentation, (II) Skip decision, (III) Reference frame selection and (IV) Face Region-of-Interest (ROI) coding. In the first part of the thesis, a modification to the adaptive Gaussian Mixture Model (GMM) based foreground segmentation algorithm is proposed to reduce computational complexity. This is achieved by replacing expensive floating point computations with low cost integer operations. To maintain accuracy, we compute periodic floating point updates for the GMM weight parameter using the value of an integer counter. Experiments show speedups in the range of 1.33 - 1.44 on standard video datasets where a large fraction of pixels are multimodal. In the second part, we propose a skip decision technique that uses a spatial sampler to sample pixels. The sampled pixels are segmented using the speeded up GMM algorithm. The storage pattern of the GMM parameters in memory is also modified to improve cache performance. Skip selection is performed using the segmentation results of the sampled pixels. In the third part, a reference frame selection algorithm is proposed to maximize the number of background Macroblocks (MB’s) (i.e. MB’s that contain background image content) in the Decoded Picture Buffer. This reduces the cost of coding uncovered background regions. Distortion over foreground pixels is measured to quantify the performance of skip decision and reference frame selection techniques. Experimental results show bit rate savings of up to 94.5% over methods proposed in literature on video surveillance data sets. The proposed techniques also provide up to 74.5% reduction in compression complexity without increasing the distortion over the foreground regions in the video sequence. In the final part of the thesis, face and shadow region detection is combined with the skip decision algorithm to perform ROI coding for pedestrian surveillance videos. Since person identification requires high quality face images, MB’s containing face image content are encoded with a low Quantization Parameter setting (i.e. high quality). Other regions of the body in the image are considered as RORI (Regions of reduced interest) and are encoded at low quality. The shadow regions are marked as Skip. Techniques that use only facial features to detect faces (e.g. Viola Jones face detector) are not robust in real world scenarios. Hence, we propose to initially detect pedestrians using deformable part models. The face region is determined using the deformed part locations. Detected pedestrians are tracked using an optical flow based tracker combined with a Kalman filter. The tracker improves the accuracy and also avoids the need to run the object detector on already detected pedestrians. Shadow and skin detector scores are computed over super pixels. Bilattice based logic inference is used to combine multiple likelihood scores and classify the super pixels as ROI, RORI or RONI. The coding mode and QP values of the MB’s are determined using the super pixel labels. The proposed techniques provide a further reduction in bitrate of up to 50.2%.

Det har kommit att bli allt vanligare att installera nätverksbaserade övervakningskameror i hemmet som en säkerhetsåtgärd. Tidigare studier som undersöker nätverksbaserade övervakningskameror visar att dessa kameror utgör en möjlig säkerhetsrisk för de boende då det teoretiskt sätt är möjligt för personer som har kunskaper i att bryta sig in i datorsystem att spionera på de boende i hemmet genom övervakningskamerorna. Detta arbete har syftat till att undersöka om människor uppfattar den nätverksbaserade övervakningskameran, vars avsedda verkan är att övervaka hemmet och skydda det mot inbrott, som en säkerhetsrisk för intrång i deras integritet. Genom kvalitativa intervjuer undersöktes användares upplevelse av nätverksbaserade övervakningskameror i hemmet. Studien omfattade sex deltagare vilka rekryterades genom ett kriteriebaserat snöbollsurval. Genom en kvalitativ innehållsanalys kom studien fram till ett resultat som visar på samband i hur dessa övervakningskameror påverkar deltagarnas upplevda integritet i hemmet. Till exempel visade resultatet att deltagarna initialt kände sig iakttagna av dessa kameror. Dessa samband kan ligga till grund för fortsatt forskning kring hur nätverksbaserade övervakningskameror kan utvecklas för att förbättra användarupplevelsen av dem. / It has become increasingly common to install network-based surveillance cameras in homes as a security measure. Previous studies examining network-based surveillance cameras shows that these cameras pose a possible security risk to users as it is theoretically possible for people who have the knowledge to break into computer systems to spy on the residents of a home through the surveillance cameras. This study aimed to investigate whether users perceive the network-based surveillance camera, whose purpose is to monitor the home and protect it from intruders, as a security risk of intrusion into their privacy. Through qualitative interviews the users experience of network-based surveillance cameras in home has been examined. The study included six participants who were recruited though a criterion-based snowball selection. Through a qualitative content analysis, the study resulted in correlations between the participants experience of the network-based surveillance cameras and their impact on the participants perceived integrity. For example, the result showed that the participants initially felt observed by these cameras. The findings can be basis for further research on how network-based surveillance cameras can evolve to improve the user experience.