Motion Detection for Video Surveillance

This thesis is related to the broad subject of automatic motion detection and analysis in videosurveillance image sequence. Besides, proposing the new unique solution, some of the previousalgorithms are evaluated, where some of the approaches are noticeably complementary sometimes.In real time surveillance, detecting and tracking multiple objects and monitoring their activities inboth outdoor and indoor environment are challenging task for the video surveillance system. Inpresence of a good number of real time problems limits scope for this work since the beginning. Theproblems are namely, illumination changes, moving background and shadow detection.An improved background subtraction method has been followed by foreground segmentation, dataevaluation, shadow detection in the scene and finally the motion detection method. The algorithm isapplied on to a number of practical problems to observe whether it leads us to the expected solution.Several experiments are done under different challenging problem environment. Test result showsthat under most of the problematic environment, the proposed algorithm shows the better qualityresult.

QoS Evaluation of BandwidthSchedulers in IPTV Networks OfferedSRD Fluid Video Traffic

Internet protocol TV (IPTV) is predicted to be the key technology winner in the future. Efforts to accelerate the deployment of IPTV centralized model which is combined of VHO, encoders, controller, access network and Home network. Regardless of whether the network is delivering live TV, VOD, or Time-shift TV, all content and network traffic resulting from subscriber requests must traverse the entire network from the super-headend all the way to each subscriber's Set-Top Box (STB).IPTV services require very stringent QoS guarantees When IPTV traffic shares the network resources with other traffic like data and voice, how to ensure their QoS and efficiently utilize the network resources is a key and challenging issue. For QoS measured in the network-centric terms of delay jitter, packet losses and bounds on delay. The main focus of this thesis is on the optimized bandwidth allocation and smooth datatransmission. The proposed traffic model for smooth delivering video service IPTV network with its QoS performance evaluation. According to Maglaris et al [5] First, analyze the coding bit rate of a single video source. Various statistical quantities are derived from bit rate data collected with a conditional replenishment inter frame coding scheme. Two correlated Markov process models (one in discrete time and one incontinuous time) are shown to fit the experimental data and are used to model the input rates of several independent sources into a statistical multiplexer. Preventive control mechanism which is to be include CAC, traffic policing used for traffic control.QoS has been evaluated of common bandwidth scheduler( FIFO) by use fluid models with Markovian queuing method and analysis the result by using simulator andanalytically, Which is measured the performance of the packet loss, overflow and mean waiting time among the network users.

Characters Extraction for Traffic Sign Destination boards in video and still images

Traffic Control Signs or destination boards on roadways offer significant information for drivers. Regulation signs tell something like your speed, turns, etc; Warning signs warn drivers of conditions ahead to help them avoid accidents; Destination signs show distances and directions to various locations; Service signs display location of hospitals, gas and rest areas etc. Because the signs are so important and there is always a certain distance from them to drivers, to let the drivers get information clearly and easily even in bad weather or other situations. The idea is to develop software which can collect useful information from a special camera which is mounted in the front of a moving car to extract the important information and finally show it to the drivers. For example, when a frame contains on a destination drive sign board it will be text something like "Linkoping 50",so the software should extract every character of "Linkoping 50", compare them with the already known character data in the database. if there is extracted character match "k" in the database then output the destination name and show to the driver. In this project C++ will be used to write the code for this software.

Strategies for the use of PIMEX and other video exposure monitoring methods. : Final report from sub-project “implementation strategies” within the HERIVIS project

Video exposure monitoring (VEM) is a group of methods used for occupational hygiene studies. The method is based on a combined use of video recordings with measurements taken with real-time monitoring instruments. A commonly used name for VEM is PIMEX. Since PIMEX initially was invented in the mid 1980’s have the method been implemented and developed in a number of countries. With the aim to give an updated picture of how VEM methods are used and to investigate needs for further development have a number of workshops been organised in Finland, UK, the Netherlands, Germany and Austria. Field studies have also been made with the aim to study to what extent the PIMEX method can improve workers motivation to actively take part in actions aimed at workplace improvements.The results from the workshops illustrates clearly that there is an impressive amount of experiences and ideas for the use of VEM within the network of the groups participating in the workshops. The sharing of these experiences between the groups, as well as dissemination of it to wider groups is, however, limited. The field studies made together with a number of welders indicate that their motivation to take part in workplace improvements is improved after the PIMEX intervention. The results are however not totally conclusive and further studies focusing on motivation are called for.It is recommended that strategies for VEM, for interventions in single workplaces, as well as for exposure categorisation and production of training material are further developed. It is also recommended to conduct a research project with the intention of evaluating the effects of the use of VEM as well as to disseminate knowledge about the potential of VEM to occupational hygiene experts and others who may benefit from its use.

QoS evaluation of Bandwidth Schedulers in IPTV Networks Offered SRD Fluid Video Traffic

Internet protocol TV (IPTV) is predicted to be the key technology winner in the future. Efforts to accelerate the deployment of IPTV centralized model which is combined of VHO, encoders, controller, access network and Home network. Regardless of whether the network is delivering live TV, VOD, or Time-shift TV, all content and network traffic resulting from subscriber requests must traverse the entire network from the super-headend all the way to each subscriber's Set-Top Box (STB). IPTV services require very stringent QoS guarantees When IPTV traffic shares the network resources with other traffic like data and voice, how to ensure their QoS and efficiently utilize the network resources is a key and challenging issue. For QoS measured in the network-centric terms of delay jitter, packet losses and bounds on delay. The main focus of this thesis is on the optimized bandwidth allocation and smooth data transmission. The proposed traffic model for smooth delivering video service IPTV network with its QoS performance evaluation. According to Maglaris et al [5] first, analyze the coding bit rate of a single video source. Various statistical quantities are derived from bit rate data collected with a conditional replenishment inter frame coding scheme. Two correlated Markov process models (one in discrete time and one in continuous time) are shown to fit the experimental data and are used to model the input rates of several independent sources into a statistical multiplexer. Preventive control mechanism which is to be including CAC, traffic policing used for traffic control. QoS has been evaluated of common bandwidth scheduler( FIFO) by use fluid models with Markovian queuing method and analysis the result by using simulator and analytically, Which is measured the performance of the packet loss, overflow and mean waiting time among the network users.

A Computer Vision Framework For Finger-Tapping Evaluation In Parkinson's Disease

Objective: To define and evaluate a Computer-Vision (CV) method for scoring Paced Finger-Tapping (PFT) in Parkinson's disease (PD) using quantitative motion analysis of index-fingers and to compare the obtained scores to the UPDRS (Unified Parkinson's Disease Rating Scale) finger-taps (FT). Background: The naked-eye evaluation of PFT in clinical practice results in coarse resolution to determine PD status. Besides, sensor mechanisms for PFT evaluation may cause patients discomfort. In order to avoid cost and effort of applying wearable sensors, a CV system for non-invasive PFT evaluation is introduced. Methods: A database of 221 PFT videos from 6 PD patients was processed. The subjects were instructed to position their hands above their shoulders besides the face and tap the index-finger against the thumb consistently with speed. They were facing towards a pivoted camera during recording. The videos were rated by two clinicians between symptom levels 0-to-3 using UPDRS-FT. The CV method incorporates a motion analyzer and a face detector. The method detects the face of testee in each video-frame. The frame is split into two images from face-rectangle center. Two regions of interest are located in each image to detect index-finger motion of left and right hands respectively. The tracking of opening and closing phases of dominant hand index-finger produces a tapping time-series. This time-series is normalized by the face height. The normalization calibrates the amplitude in tapping signal which is affected by the varying distance between camera and subject (farther the camera, lesser the amplitude). A total of 15 features were classified using K-nearest neighbor (KNN) classifier to characterize the symptoms levels in UPDRS-FT. The target ratings provided by the raters were averaged. Results: A 10-fold cross validation in KNN classified 221 videos between 3 symptom levels with 75% accuracy. An area under the receiver operating characteristic curves of 82.6% supports feasibility of the obtained features to replicate clinical assessments. Conclusions: The system is able to track index-finger motion to estimate tapping symptoms in PD. It has certain advantages compared to other technologies (e.g. magnetic sensors, accelerometers etc.) for PFT evaluation to improve and automate the ratings

Teaching Intercultural Communication in Foreign Language Education through Video Conferencing

Since 1980s, Western linguists and specialists on second language acquisition have emphasized the importance of enhancing students’ intercultural communication competence in foreign language education. At the same time, the demand for intercultural communicative competence increased along with the advances of communication technology with its increasingly global reach and the process of globalization itself.In the field of distance language education, these changes have resulted in a shift of focus from the production and distribution of learning materials towards communication and learning as a social process, facilitated by various internet-based platforms. The current focus on learners interacting and communicating synchronously trough videoconferencing is known as the fourth generation of distance language education. Despite the fact that teaching of Chinese as a foreign language (CFL) faces the same or even greater challenges as teaching other languages, the intercultural communication perspective is still quite a new trend in CFL and its implementation and evaluation are still under development. Moreover, the advocates of the new trends in CFL have so far focused almost exclusively on classroom-based courses, neglecting the distance mode of CFL and leaving it as an open field for others to explore. In this under-researched context, Dalarna University (Sweden), where I currently work, started to provide web-based courses of the Chinese language in 2007. Since 2010, the Chinese language courses have been available only in the distance form, using the same teaching materials as the previous campus-based courses. The textbooks used in both settings basically followed the functional nationalism approach. However, in order to catch up with the main trend of foreign-language education, we felt a need to implement the cross-cultural dimension into the distance courses as well. Therefore in 2010, a pilot study has been carried out to explore opportunities and challenges for implementing a cross-cultural perspective into existing courses and evaluating the effectiveness of this implementation based on the feedback of the students and on the experience of the teacher/researcher.

Användning av OER och video i undervisning och lärande

Abstract NGL 2015 Workshop Användning av OER och video i undervisning och lärande Sten Sundin Hållbus Totte Mattsson Open Educational Resources; OER, även kallat öppna lärresurser, är resurser som finns tillgängliga på Internet som kan användas fritt och i många fall också bearbetas fritt. Fördelarna med OER i allmänhet är att kunna återanvända andra personers expertkunskap och material. Många lärresurser håller en hög kvalitet och är även mycket pedagogiska. Detta förbättrar lärandet och innebär nya möjligheter i undervisningen som en lärare själv annars inte skulle kunnat åstadkomma, som t.ex. att själv göra tidskrävande videoinspelningar. Att undervisa med mer stöd av video, bilder och icketextbaserad information kan även gynna studenters olika lärstilar. Denna workshop syftar till att introducera användning av OER och video för lärare som inte är bekanta med OERbegreppet och som i större utsträckning önskar använda video i undervisningen. Under workshopen kommer deltagarna att arbeta i grupp med relevanta söktjänster för att hitta och undersöka användbara OER eller videoresurser. Länkar och anteckningar från sökningarna kommer att delas till övriga workshopdeltagare på en webbaserad samarbetsyta som kommer att vara tillgänglig även efter workshopen Plan för workshopen ● Introduktion. Fördelar med att använda OER och video i undervisning och lärande. (5 min) ● Min användning av lär och videoresurser idag (gruppdiskussion). Vad är mina tidigare erfarenheter inom området? Hur hittar jag lär och videoresurser för min undervisning? Beskriv hur din nuvarande situation ser ut (15 min) ● Presentation av OER och video i undervisning och varför detta är viktigt för lärare. Olika typer av OER, Creative Commonslicenser, samt hur man hittar OER och andra kostnadsfria lärresurser. Exempel på söktjänster, samt samlingar med OER och videoresurser som kan undersökas. Användning och redigering av YouTubevideos (10 min) ● Arbete i mindre grupper om 2-4 personer. Grupperna har tillgång till listor med passande sökverktyg för att hitta användbara OER och videoresurser. De resurser som har hittats sparas på en gemensam plats med webbverktyget Padlet (50 min) ● Sammanfattning. Alla resultat från sessionen kommer att finnas tillgängliga på en Padletyta som finns kvar efter workshopen så att deltagarna kan fortsätta att dela idéer och undersöka resurser som har hittats. (10 min) Målgrupp Lärare, bibliotekarier och andra utbildare som är intresserade av att öka sina kunskaper om frågor kring OER och video i undervisning och lärande

Real time video segmentation for recognising paint marks on bad wooden railway sleepers

Wooden railway sleeper inspections in Sweden are currently performed manually by a human operator; such inspections are based on visual analysis. Machine vision based approach has been done to emulate the visual abilities of human operator to enable automation of the process. Through this process bad sleepers are identified, and a spot is marked on it with specific color (blue in the current case) on the rail so that the maintenance operators are able to identify the spot and replace the sleeper. The motive of this thesis is to help the operators to identify those sleepers which are marked by color (spots), using an “Intelligent Vehicle” which is capable of running on the track. Capturing video while running on the track and segmenting the object of interest (spot) through this vehicle; we can automate this work and minimize the human intuitions. The video acquisition process depends on camera position and source light to obtain fine brightness in acquisition, we have tested 4 different types of combinations (camera position and source light) here to record the video and test the validity of proposed method. A sequence of real time rail frames are extracted from these videos and further processing (depending upon the data acquisition process) is done to identify the spots. After identification of spot each frame is divided in to 9 regions to know the particular region where the spot lies to avoid overlapping with noise, and so on. The proposed method will generate the information regarding in which region the spot lies, based on nine regions in each frame. From the generated results we have made some classification regarding data collection techniques, efficiency, time and speed. In this report, extensive experiments using image sequences from particular camera are reported and the experiments were done using intelligent vehicle as well as test vehicle and the results shows that we have achieved 95% success in identifying the spots when we use video as it is, in other method were we can skip some frames in pre-processing to increase the speed of video but the segmentation results we reduced to 85% and the time was very less compared to previous one. This shows the validity of proposed method in identification of spots lying on wooden railway sleepers where we can compromise between time and efficiency to get the desired result.

Implementation of Video Monitoring In Aluminium Industry

The aim was to evaluate results and experiences from development of new technology, a training program and implementation of strategies for the use of a video exposure monitoring method, PIMEX. Starting point of this study is an increased incidence of asthma among workers in the aluminium industry. Exposure peaks of fumes are supposed to play an important role. PIMEX makes it possible to link used work practice, use of control technology, and so forth to peaks. Nine companies participated in the project, which was divided into three parts, development of PIMEX technology, production of training material, and training in use of equipment and related strategies. The use of the video exposure monitoring method PIMEX offers prerequisites supporting workers participation in safety activities. The experiences from the project reveal the importance of good timing of primary training, technology development, technical support, and follow up training. In spite of a delay of delivery of the new technology, representatives from the participating companies declared that the experiences showed that PIMEX gave an important contribution for effective control of hazards in the companies. Eight out of nine smelters used the PIMEX method as a part of a strategy for control of workers exposure to fumes in potrooms. Possibilities to conduct effective control measures were identified. This article describes experiences from implementation of a, for this branch, new method supporting workers participation for workplace improvements.

Rapport från projektet Multimodala uppgifter och bedömning i matematik : Video och kollaborativa samtal som metod vid lärares bedömning av elevers matematiska kunskaper

This research will discuss some experiences from a four year school research study. It was conducted in cooperation with teachers from four municipalities in Dalarna. The aim of the research was to examine teachers´ professional development when they participated in collaborative discussions based on video recordings and video edited material from specific lessons in their own practice. The study had two foci one was to investigate methods and tools that teachers can use to develop their ability to assess their students while working on multimodal tasks. The other was to examine how video can be used by teachers wanting to obtain knowledge about assessing students. The study is based on several theories about when teachers collaborate to create new knowledge. The first is the design theoretical approach – where visual ethnography and a semiotic approach contribute to problematize the use and mixture of different modes. A basic assumption of the framework here is that meanings are made and communicated in mathematics through a wide range of semiotic modes. By using video as an essential tool in the research the framework theories concerning visual ethnography, video documentation and individuals as reflective practitioners were also needed. The findings can be divided into the following themes: the use of tasks for assessment, collaborative discussion, equipment, ethical dilemmas. Collaborative discussions were evaluated as a meaningful way of sharing knowledge. The use of video recordings in association with these discussions raised important ethical issues. Working with the assessment framework was of great interest to the teachers but it took a lot of time from their ordinary work. In this way the project highlighted more general aspects of school development. The research also concerns teachers´ use of collaborative discussions in assessment work, multimodal tasks in mathematics and video as a research tool in general.

Video- och Projektions-design : En fallstudie i videoscenografi

Denna uppsats har för avsikt att beskriva och redogöra för området videoscenografi och hur en videoscenograf arbetar. Videoscenografer har 90- och 00-talets snabba utveckling av prestanda inom datakraften att tacka för sin funktion, i en värld som kräver alltmer av kreatören frågar jag mig hur videoscenografen ser på sin omvärld. Videoscenografen verkar i området mellan det konstnärliga, scentekniska och grafiska. Deras position är fortfarande under förvirring just eftersom deras arbetsfält är så brett. Uppsatsen klargör för läsaren vad det är de sysslar med inom en scenkonstproduktion och varför videoscenografin är en sak för framtiden. Video inom scenkonstproduktioner blir allt viktigare, samtidigt som dekormålares arbete blir allt mindre, men endå tvingas videoscenografen att utföra sitt arbete under trängda förhållanden, med full ljussättning på scen, eller samtidigt som repetitioner pågår där de riskerar att störa en kreativ process. Insynen i vad de sysslar med är högst begränsad eftersom det är ett ungt yrke, med så pass få utövare. Denna uppsats klargör för varför videoscenografens arbete är viktigt och varför de bör ges mer tid att utföra sitt arbete.

Recording and Using Provenance in a Protein Compressibility Experiment

Very large scale computations are now becoming routinely used as a methodology to undertake scientific research. In this context, `provenance systems' are regarded as the equivalent of the scientist's logbook for in silico experimentation: provenance captures the documentation of the process that led to some result. Using a protein compressibility analysis application, we derive a set of generic use cases for a provenance system. In order to support these, we address the following fundamental questions: what is provenance? how to record it? what is the performance impact for grid execution? what is the performance of reasoning? In doing so, we define a technologyindependent notion of provenance that captures interactions between components, internal component information and grouping of interactions, so as to allow us to analyse and reason about the execution of scientific processes. In order to support persistent provenance in heterogeneous applications, we introduce a separate provenance store, in which provenance documentation can be stored, archived and queried independently of the technology used to run the application. Through a series of practical tests, we evaluate the performance impact of such a provenance system. In summary, we demonstrate that provenance recording overhead of our prototype system remains under 10% of execution time, and we show that the recorded information successfully supports our use cases in a performant manner.

PReServ: Provenance Recording for Services

The importance of understanding the process by which a result was generated in an experiment is fundamental to science. Without such information, other scientists cannot replicate, validate, or duplicate an experiment. We define provenance as the process that led to a result. With large scale in-silico experiments, it becomes increasingly difficult for scientists to record process documentation that can be used to retrieve the provenance of a result. Provenance Recording for Services (PReServ) is a software package that allows developers to integrate process documentation recording into their applications. PReServ has been used by several applications and its performance has been benchmarked.