Video surveillance today can look very different depending on the objective and on the location where it is used. Some applications need a high image resolution and frame rate to carefully analyze the vision of a camera, while other applications could use a poorer resolution and a lower frame rate to achieve it's goals. The communication between a camera and an observer depends much on the distance between them and on the contents. If the observer is far away the information will reach the observer with delay, and if the medium carrying the information is unreliable the observer has to have this in mind. Lost information might not be acceptable for some applications, and some applications might not need it's information instantly. In this master thesis, IP network communication for an automatic tolling station has been simulated where several video streams from different sources have to be synchronized. The quality of the images and the frame rate are both very important in these types of surveillance, where simultaneously exposed images are processed together. The report includes short descriptions of some networking protocols, and descriptions of two implementations based on the protocols. The implementations were done in C++ using the basic socket API to evaluate the network communication. Two communication methods were used in the implementations, where the idea was to push or to poll images. To simulate the tolling station and create a network with several nodes a number of Raspberry Pis were used to execute the implementations. The report also includes a discussion about how and which video/image compression algorithms the system might benefit of. The results of the network communication evaluation shows that the communication should be done using a pushing implementation rather than a polling implementation. A polling method is needed when the transportation medium is unreliable, but the network components were able to handle the amount of simultaneous sent information very well without control logic in the application.

This Master Thesis report was written by Umeå University Engineering Physics student Richard Tano during his thesis work at Ericsson Luleå. Monitoring network quality is of utmost importance to network providers. This can be done with models evaluating QoS (Quality of Service) and conforming to ITU-T Recommendations. When determining video stream quality there is of more importance to evaluatethe QoE (Quality of Experience) to understand how the user perceives the quality. This isranked in MOS (Mean opinion scores) values. An important aspect of determining the QoEis the video content type, which is correlated to the coding complexity and MOS values ofthe video. In this work the possibilities to improve quality estimation models complying to ITU-T study group 12 (q.14) was investigated. Methods were evaluated and an algorithm was developed that applies time series analysis of packet statistics for determination of videostreams MOS scores. Methods used in the algorithm includes a novel assembling of frequentpattern analysis and regression analysis. A model which incorporates the algorithm for usage from low to high bitrates was dened. The new model resulted in around 20% improvedprecision in MOS score estimation compared to the existing reference model. Furthermore an algorithm using only regression statistics and modeling of related statistical parameters was developed. Improvements in coding estimation was comparable with earlier algorithm but efficiency increased considerably. / Detta examensarbete skrevs av Richard Tano student på Umeå universitet åt Ericsson Luleå. Övervakning av nätets prestanda är av yttersta vikt för nätverksleverantörer. Detta görs med modeller för att utvärdera QoS (Quality of Service) som överensstämmer med ITU-T rekommendationer. Vid bestämning av kvaliten på videoströmmar är det mer meningsfullt att utvärdera QoE (Quality of Experience) för att få insikt i hur användaren uppfattar kvaliten. Detta graderas i värden av MOS (Mean opinion score). En viktig aspekt för att bestämma QoE är typen av videoinnehåll, vilket är korrelerat till videons kodningskomplexitet och MOS värden. I detta arbete undersöktes möjligheterna att förbättra kvalitetsuppskattningsmodellerna under uppfyllande av ITU-T studygroup 12 (q.14). Metoder undersöktes och en algoritm utvecklades som använder tidsserieanalys av paketstatistik för uppskattning av videoströmmars MOS-värden. Metoder som ingår i algoritmen är en nyutvecklad frekventa mönster metod tillsammans med regressions analys. En modell som använder algoritmen från låg till hög bithastighet definierades. Den nya modellen gav omkring 20% förbättrad precision i uppskattning av MOS-värden jämfört med existerande referensmodell. Även en algoritm som enbart använder regressionsstatistik och modellerande av statistiska parametrar utvecklades. Denna algoritm levererade jämförbara resultat med föregående algoritm men gav även kraftigt förbättrad effektivitet.

<p>A channel change in digital television is usually conducted at a reference frame, which are sent at certain intervals. A higher compression ratio could however be obtained by sending reference frames at arbitrary long intervals. This would on the other hand increase the average channel change time for the end user. This thesis investigates various approaches for reducing the average channel change time while using arbitrary long intervals between reference frames, and presents an implementation and evaluation of one of these methods, called Baydec.</p><p>The approach of Baydec for solving the channel switch problem is to statistically estimate what the original image looked like, starting with an incoming P-frame and estimate an image between the original and current image. Baydec gathers statistical data from typical video sequences and calculates expected likelihood for estimation. Further on it uses the Simulated Annealing search method to maximise the likelihood function.</p><p>This method is more general than the requirements of this thesis. It is not only applicable to channel switches between video streams, but can also be used for random access in general. Baydec could also be used if an I-frame is dropped in a video stream.</p><p>However, Baydec has so far shown only theoretical result, but very small visual improvements. Baydec produces images with better PSNR than without the method in some cases, but the visual impression is not better than for the motion compensated residual images. Some examples of future work to improve Baydec is also presented.</p>

Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-04-18T15:01:39Z No. of bitstreams: 1 MARCELL MANFRIN BARBACENA - DISSERTAÇÃO PPGCC 2014..pdf: 1468565 bytes, checksum: b94d20ffdace21ece654986ffd8fbb63 (MD5) / Made available in DSpace on 2018-04-18T15:01:39Z (GMT). No. of bitstreams: 1 MARCELL MANFRIN BARBACENA - DISSERTAÇÃO PPGCC 2014..pdf: 1468565 bytes, checksum: b94d20ffdace21ece654986ffd8fbb63 (MD5) Previous issue date: 2014 / Impulsionadas pela crescente demanda por sistemas de segurança para proteção do indivíduo e da propriedade nos dias atuais, várias pesquisas têm sido desenvolvidas com foco na implantação de sistemas de vigilância por vídeo com ampla cobertura. Um dos problemas de pesquisa em aberto nas áreas de visão computacional e redes de computadores envolvem a escalabilidade desses sistemas, principalmente devido ao aumento do número de câmeras transmitindo vídeos em tempo real para monitoramento e processamento. Neste contexto, o objetivo geral deste trabalho é avaliar o impacto que a redução da taxa de transmissão dos fluxos de vídeos impõe na eficácia dos algoritmos de detecção de pessoas utilizados em sistemas inteligentes de videovigilância. Foram realizados experimentos utilizando vídeos em alta resolução no contexto de vigilância com tomadas externas e com um algoritmo de detecção de pessoas baseado em histogramas de gradientes orientados, nos quais se coletou, como medida de eficácia do algoritmo, a métrica de área sob a curva de precisão e revocação para, em sequência, serem aplicados os testes estatísticos de Friedman e de comparações múltiplas com um controle na aferição das hipóteses levantadas. Os resultados obtidos indicaram que é possível uma redução da taxa de transmissão em mais de 70% sem que haja redução da eficácia do algoritmo de detecção de pessoas. / Motivated by the growing demand for security systems to protect persons and properties in the nowadays, several researches have been developed focusing on the deployment of widearea video coverage surveillance systems. One open research problem in the areas of computer vision and computer networks involves the scalability of these systems, mainly due to the increasing number of cameras transmitting real-time video for monitoring and processing. In this context, the aim of this study was to evaluate the impact that transmission data-rate reduction of video streams imposes on the effectiveness of people detection algorithms used in intelligent video surveillance systems. With a proposed experimental design, experiments were performed using high-resolution wide-area external coverage video surveillance and using an algorithm for people detection based on histograms of oriented gradients. As a measure of effectiveness of the people detection algorithm, the metric of area under the precision-recall curve was collected and statistical tests of Friedman and multiple comparisons with a control were applied to evaluate the hypotheses. The results indicated that it is possible to reduce transmission rate by more than 70% without decrease in the effectiveness of the people detection algorithm.

A channel change in digital television is usually conducted at a reference frame, which are sent at certain intervals. A higher compression ratio could however be obtained by sending reference frames at arbitrary long intervals. This would on the other hand increase the average channel change time for the end user. This thesis investigates various approaches for reducing the average channel change time while using arbitrary long intervals between reference frames, and presents an implementation and evaluation of one of these methods, called Baydec. The approach of Baydec for solving the channel switch problem is to statistically estimate what the original image looked like, starting with an incoming P-frame and estimate an image between the original and current image. Baydec gathers statistical data from typical video sequences and calculates expected likelihood for estimation. Further on it uses the Simulated Annealing search method to maximise the likelihood function. This method is more general than the requirements of this thesis. It is not only applicable to channel switches between video streams, but can also be used for random access in general. Baydec could also be used if an I-frame is dropped in a video stream. However, Baydec has so far shown only theoretical result, but very small visual improvements. Baydec produces images with better PSNR than without the method in some cases, but the visual impression is not better than for the motion compensated residual images. Some examples of future work to improve Baydec is also presented.