Visual surveillance systems are increasingly common in our society today. There is a conflict between the demands for security of the public and the demands to preserve the personal integrity. This thesis suggests a solution in which parts of the surveillance images are covered in order to conceal the identities of persons appearing in video, but not their actions or activities. The covered parts could be encrypted and unlocked only by the police or another legal authority in case of a crime. This thesis implements a proof-of-concept demonstrator using a combination of image processing techniques such as foreground segmentation, mathematical morphology, geometric camera calibration and region tracking. The demonstrator is capable of tracking a moderate number of moving objects and conceal their identity by replacing them with a mask or a blurred image. Functionality for replaying recorded data and unlocking individual persons are included. The concept demonstrator shows the chain from concealing the identities of persons to unlocking only a single person on recorded data. Evaluation on a publicly available dataset shows overall good performance.

The actor-observer effect suggests that actors attribute to the situation while observers attribute to the actor's disposition. This effect has come under scrutiny because of an alternative perspective that accounts for anomalous finding. This alternative, called the contextual perspective, suggests that actors and observers foreground different aspects of the context because of a relationship with the context, and has roots in Gestalt psychology and phenomenology. I manipulated a researcher's prompt and the presence of a distressed confederate as the context for attributions, and hypothesized that actors and observers would differ on attributions to choice, situation, and disposition because of presence of a distressed confederate. Actors were presented with either a distressed or non-distressed confederate and either a prompt to leave, a prompt to stay, or no prompt. For example, some actors experienced a distressed confederate and were asked to leave while others experienced a non-distressed confederate and were asked to stay. Actors then made a decision to either stay and help the confederate or leave. Observers watched one of ten videos, each of one actor condition in which the actor either stayed or left (five actor conditions by 2 options of stay or leave). Actors' and observers' choice, situational, and dispositional attributions were analyzed using factorial MANOVAs. Actors and observers foregrounded the distressed confederate when making attributions to choice, situation, and disposition. Furthermore, observers' attributions to choice were also influenced by the actor's behavior. These findings support the contextual perspective since context does influence actors' and observers' attributions.

Security cameras installed in public spaces or in private organizations continuously record video data with the aim of detecting and preventing crime. For that reason, video content analysis applications, either for real time (i.e. analytic) or post-event (i.e. forensic) analysis, have gained high interest in recent years. In this thesis, the primary focus is on two key aspects of video analysis, reliable moving object segmentation and carried object detection & identification. A novel moving object segmentation scheme by background subtraction is presented in this thesis. The scheme relies on background modelling which is based on multi-directional gradient and phase congruency. As a post processing step, the detected foreground contours are refined by classifying the edge segments as either belonging to the foreground or background. Further contour completion technique by anisotropic diffusion is first introduced in this area. The proposed method targets cast shadow removal, gradual illumination change invariance, and closed contour extraction. A state of the art carried object detection method is employed as a benchmark algorithm. This method includes silhouette analysis by comparing human temporal templates with unencumbered human models. The implementation aspects of the algorithm are improved by automatically estimating the viewing direction of the pedestrian and are extended by a carried luggage identification module. As the temporal template is a frequency template and the information that it provides is not sufficient, a colour temporal template is introduced. The standard steps followed by the state of the art algorithm are approached from a different extended (by colour information) perspective, resulting in more accurate carried object segmentation. The experiments conducted in this research show that the proposed closed foreground segmentation technique attains all the aforementioned goals. The incremental improvements applied to the state of the art carried object detection algorithm revealed the full potential of the scheme. The experiments demonstrate the ability of the proposed carried object detection algorithm to supersede the state of the art method.

<p>Foreground segmentation is a common first step in tracking and surveillance applications.  The purpose of foreground segmentation is to provide later stages of image processing with an indication of where interesting data can be found.  This thesis is an investigation of how foreground segmentation can be performed in two contexts: as a pre-step to trajectory tracking and as a pre-step in indoor surveillance applications.</p><p>Three methods are selected and detailed: a single Gaussian method, a Gaussian mixture model method, and a codebook method.  Experiments are then performed on typical input video using the methods.  It is concluded that the Gaussian mixture model produces the output which yields the best trajectories when used as input to the trajectory tracker.  An extension is proposed to the Gaussian mixture model which reduces shadow, improving the performance of foreground segmentation in the surveillance context.</p>

A great number of methods based on local features or global appearances have been proposed in the literature for geospatial object detection and recognition from satellite images. However, since these approaches do not have enough discriminative capabilities between object and non-object classes, they produce results with innumerable false positives during their detection process. Moreover, due to the sliding window mechanisms, these algorithms cannot yield exact location information for the detected objects. Therefore, a geospatial object recognition algorithm based on the object shape mask is proposed to minimize the aforementioned imperfections. In order to develop such a robust recognition system, foreground extraction performance of some of popular fully and semi-automatic image segmentation algorithms, such as normalized cut, k-means clustering, mean-shift for fully automatic, and interactive Graph-cut, GrowCut, GrabCut for semi-automatic, are evaluated in terms of their subjective and objective qualities. After this evaluation, the retrieval performance of some shape description techniques, such as ART, Hu moments and Fourier descriptors, are investigated quantitatively. In the proposed system, first of all, some hypothesis points are generated for a given test image. Then, the foreground extraction operation is achieved via GrabCut algorithm after utilizing these hypothesis points as if these are user inputs. Next, the extracted binary object masks are described by means of the integrated versions of shape description techniques. Afterwards, SVM classifier is used to identify the target objects. Finally, elimination of the multiple detections coming from the generation of hypothesis points is performed by some simple post-processing on the resultant masks. Experimental results reveal that the proposed algorithm has promising results in terms of accuracy in recognizing many geospatial objects, such as airplane and ship, from high resolution satellite imagery.

The aim of this thesis is to investigate and analyze practices in multilingual mathematics classrooms in compulsory school in Sweden. By using ethnographic methods, mainly participant observation, data were collected in a number of multilingual mathematics classrooms in suburban areas of a major city. The data include field notes, interviews and informal conversations with students, teachers and school administrators. The analysis is based on a coordination of Foucault’s discourse theory and Skovsmose’s critical mathematics education. The socio-political viewpoint defines power as relational and as having an effect on school mathematics practices. Discourse, agency, foreground and identity are used as analytic tools. In five articles, the thesis investigates how the various discourses affect multilingual students’ agency, foreground and identity formation as engaged mathematics learners. The effects of students’ and teachers’ agency on discourse switching in multilingual mathematics classrooms are also investigated. The findings indicate that bilingual communication in the mathematics classroom enhances students’ identity formation as engaged mathematics learners. Language- and content-based instruction seems to do the same, though monolingual instruction may jeopardize students’ identities as bilinguals while the discourse may normalize Swedish and Swedishness exclusively. Focus on linguistic dimensions in mathematics build up a communicative reform-oriented school mathematics discourse. The competing and intersecting discourses available in the multilingual mathematics classroom affect students’ agency, foreground and identity formation as engaged mathematics learners. For example, a reform-oriented school mathematics discourse intersecting with a social-relational discourse affects students’ active agency allowing power relations to be negotiated. A principal conclusion is that the success or failure of multilingual students in multilingual mathematics classrooms cannot be explained in terms of language and cultural factors alone, but only in relation discourse, and to social and political conditions in society at large. / At the time of the doctoral defense, the following papers were unpublished and had a status as follows: Paper 3: Accepted. Paper 4: Manuscript. Paper 5: Manuscript.

This thesis proposes a new chroma keying method that can automatically detect background, foreground, and unknown regions. For background color detection, we use K-means clustering in color space to calculate the limited number of clusters of background colors. We use spatial information to clean the background regions and minimize the unknown regions. Our method only needs minimum inputs from user. For unknown regions, we implement the alpha matte based on Wang's robust matting algorithm, which is considered one of the best algorithms in the literature, if not the best. Wang's algorithm is based on modified random walk. We proposed a better color selection method, which improves matting results in the experiments. In the thesis, a detailed implementation of robust matting is provided. The experimental results demonstrate that our proposed method can handle images with one background color, images with gridded background, and images with difficult regions such as complex hair stripes and semi-transparent clothes.

This thesis proposes a new chroma keying method that can automatically detect background, foreground, and unknown regions. For background color detection, we use K-means clustering in color space to calculate the limited number of clusters of background colors. We use spatial information to clean the background regions and minimize the unknown regions. Our method only needs minimum inputs from user. For unknown regions, we implement the alpha matte based on Wang's robust matting algorithm, which is considered one of the best algorithms in the literature, if not the best. Wang's algorithm is based on modified random walk. We proposed a better color selection method, which improves matting results in the experiments. In the thesis, a detailed implementation of robust matting is provided. The experimental results demonstrate that our proposed method can handle images with one background color, images with gridded background, and images with difficult regions such as complex hair stripes and semi-transparent clothes.

Background Subtraction is one of the fundamental pre-processing steps in video processing. It helps to distinguish between foreground and background for any given image and thus has numerous applications including security, privacy, surveillance and traffic monitoring to name a few. Unfortunately, no single algorithm exists that can handle various challenges associated with background subtraction such as illumination changes, dynamic background, camera jitter etc. In this work, we propose a Multiple Background Model based Background Subtraction (MB2S) system, which is universal in nature and is robust against real life challenges associated with background subtraction. It creates multiple background models of the scene followed by both pixel and frame based binary classification on both RGB and YCbCr color spaces. The masks generated after processing these input images are then combined in a framework to classify background and foreground pixels. Comprehensive evaluation of proposed approach on publicly available test sequences show superiority of our system over other state-of-the-art algorithms.

The aim of this dissertation is twofold. On one hand, I describe the use of tense in the second language of the deaf – written Swedish. There is no previous description of this. On the other hand, I operationalize the transitivity model (Hopper &amp; Thompson 1980) and test its scope. I test in part whether transitivity as it is described by Hopper &amp; Thompson (1980) can be used to explain the use of tense by the deaf in my study. The reason why I connect transitivity with the use of tense is that I would like to see whether a transitivity analysis of a text can replace classification into foreground and background. If so, a transitivity analysis should be a sufficient method for testing the discourse hypothesis, which maintains that second language learners use their emerging verb morphology to signal foreground and background rather than tense. The material I use for both these aims consists of a total of 129 essays written by deaf high school students. The results show that the percentage of clauses with an appropriate choice of tense in all three subsets of material is high. One interesting trend that could be discerned with regard to use of tense is that when informants use a tense that is appropriate for the genre, their command of that tense is better than when it is used in a genre for which it is less appropriate. Calculations testing the hypothesis of co-variance between the components in the transitivity model show in general that such co-variance exists. Nonetheless, the degree of this varies and is far from total. Taken together, the calculations made in this investigation provide support for the claim that these nine components co-vary with one another. The results also show that there is no correlation between the components and the use of tense. Judging from the results, the value of the different components (positive or negative) appears to have no importance in determining whether the choice of tense is appropriate or not. Nor is there any significant difference in the subsets of material for my investigation of whether the number of positive values that a clause has is relevant in classifying the choice of tense as appropriate.