abstract: Non-line-of-sight (NLOS) imaging of objects not visible to either the camera or illumina- tion source is a challenging task with vital applications including surveillance and robotics. Recent NLOS reconstruction advances have been achieved using time-resolved measure- ments. Acquiring these time-resolved measurements requires expensive and specialized detectors and laser sources. In work proposes a data-driven approach for NLOS 3D local- ization requiring only a conventional camera and projector. The localisation is performed using a voxelisation and a regression problem. Accuracy of greater than 90% is achieved in localizing a NLOS object to a 5cm × 5cm × 5cm volume in real data. By adopting the regression approach an object of width 10cm to localised to approximately 1.5cm. To generalize to line-of-sight (LOS) scenes with non-planar surfaces, an adaptive lighting al- gorithm is adopted. This algorithm, based on radiosity, identifies and illuminates scene patches in the LOS which most contribute to the NLOS light paths, and can factor in sys- tem power constraints. Improvements ranging from 6%-15% in accuracy with a non-planar LOS wall using adaptive lighting is reported, demonstrating the advantage of combining the physics of light transport with active illumination for data-driven NLOS imaging. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2019

Computed tomography (CT) is routinely used for diagnosing lung disease and developing treatment plans using images of intricate lung structure with submillimeter resolution. Automated segmentation of anatomical structures in such images is important to enable efficient processing in clinical and research settings. Convolution neural networks (ConvNets) are largely successful at performing image segmentation with the ability to learn discriminative abstract features that yield generalizable predictions. However, constraints in hardware memory do not allow deep networks to be trained with high-resolution volumetric CT images. Restricted by memory constraints, current applications of ConvNets on volumetric medical images use a subset of the full image; limiting the capacity of the network to learn informative global patterns. Local patterns, such as edges, are necessary for precise boundary localization, however, they suffer from low specificity. Global information can disambiguate structures that are locally similar. The central thesis of this doctoral work is that both local and global information is important for segmentation of anatomical structures in medical images. A novel multi-scale ConvNet is proposed that divides the learning task across multiple networks; each network learns features over different ranges of scales. It is hypothesized that multi-scale ConvNets will lead to improved segmentation performance, as no compromise needs to be made between image resolution, image extent, and network depth. Three multi-scale models were designed to specifically target segmentation of three pulmonary structures: lungs, fissures, and lobes. The proposed models were evaluated on a diverse datasets and compared to architectures that do not use both local and global features. The lung model was evaluated on humans and three animal species; the results demonstrated the multi-scale model outperformed single scale models at different resolutions. The fissure model showed superior performance compared to both a traditional Hessian filter and a standard U-Net architecture that is limited in global extent. The results demonstrated that multi-scale ConvNets improved pulmonary CT segmentation by incorporating both local and global features using multiple ConvNets within a constrained-memory system. Overall, the proposed pipeline achieved high accuracy and was robust to variations resulting from different imaging protocols, reconstruction kernels, scanners, lung volumes, and pathological alterations; demonstrating its potential for enabling high-throughput image analysis in clinical and research settings.

<div>Following a natural disaster, one of the most important facet that influence a persons chances of survival/being found out is the time with which they are rescued. Traditional means of search operations involving dogs, ground robots, humanitarian intervention; are time intensive and can be a major bottleneck in search operations. The main aim of these operations is to rescue victims without critical delay in the shortest time possible which can be realized in real-time by using UAVs. With advancements in computational devices and the ability to learn from complex data, deep learning can be leveraged in real time environment for purpose of search and rescue operations. This research aims to solve the traditional means of search operation using the concept of deep learning for real time object detection and Photogrammetry for precise geo-location mapping of the objects(person,car) in real time. In order to do so, various pre-trained algorithms like Mask-RCNN, SSD300, YOLOv3 and trained algorithms like YOLOv3 have been deployed with their results compared with means of addressing the search operation in</div><div>real time.</div><div><br></div>

Deep learning has been making headlines in recent years and is often portrayed as an emerging technology on a meteoric rise towards fully sentient artificial intelligence. In reality, deep learning is the most recent renaissance of a 70 year old technology and is far from possessing true intelligence. The renewed interest is motivated by recent successes in challenging problems, the accessibility made possible by hardware developments, and dataset availability. The predecessor to deep learning, commonly known as the artificial neural network, is a computational network setup to mimic the biological neural structure found in brains. However, unlike human brains, artificial neural networks, in most cases cannot make inferences from one problem to another. As a result, developing an artificial neural network requires a large number of examples of desired behavior for a specific problem. Furthermore, developing an artificial neural network capable of solving the problem can take days, or even weeks, of computations. Two specific problems addressed in this dissertation are both input association problems. One problem challenges a neural network to identify overlapping regions in images and is used to evaluate the ability of a neural network to learn associations between inputs of similar types. The other problem asks a neural network to identify which observed wireless signals originated from observed potential sources and is used to assess the ability of a neural network to learn associations between inputs of different types. The neural network solutions to both problems introduced, discussed, and evaluated in this dissertation demonstrate deep learning’s applicability to problems which have previously attracted little attention.

Sammanfattning Detta är en kvalitativ fallstudie av fem specialpedagogers arbete med specialundervisning i matematik. Syftet är att kartlägga deras arbete och uppfattningar genom att beskriva och analysera hur de organiserar sin undervisning i matematik, hur de undervisar ämnesinnehållet och hur de ger feedback till eleverna i klassrummet, samt hur de själva beskriver det de uppfattar som det specialpedagogiska inslaget i sin undervisning. För insamling av empirin har en kvalitativ metod med halvstrukturerade djupintervjuer samt observationer i form av ljudinspelningar och ostrukturerade fältanteckningar under lektioner gjorts. Ramfaktorteorier, fenomenografiska teorier, inlärningsteorier samt fallstudien, har styrt mitt sätt att bearbeta och analysera det empiriska materialet. Resultatet visar att det lärande som erbjuds eleverna av fyra av specialpedagogerna bidrar till ett ytinriktat lärande, och feedback som erbjuds bidrar till yttre motivation. Det specialpedagogiska inslaget anser de vara att se människan bakom ett beteende, att ha en positiv förväntan, att utgå från barnet, att vara personlig, att tycka om eleverna och att vara konkret i undervisningen. Den femte pedagogen erbjuder ett djupinriktat lärande och erbjuder ett arbetssätt under lektionerna som skapar vilja och motivation att lära sig. Det specialpedagogiska inslaget anser hon vara att ta reda på var eleven befinner sig kunskapsmässigt och utgå därifrån så eleven har möjlighet att förstå det den inte har förstått. / Summary This is a qualitative case study of five special educators work with special education in mathematics. The aim is to identify their work and ideas by describing and analyzing how they organize their teaching of mathematics, how they teach the subject matter, how they give feedback to students in the classroom, how they describe what they perceive to be the special education component of their teaching. For the collection of empirical data, a qualitative approach with semi-structured interviews and observations in the form of audio recordings and unstructured field notes during classes was used. Frame factor theory, phenomenographic theory, learning theories and case study have leaded me through the way of processing and analyzing the empirical material. Results show that the learning that four of the special educators offer the students contributes to a surface approach to learning, and the feedback they offer contributes to external motivation. The special education components they say are important: to see the person behind a behavior, have positive expectations, let the teaching be based on the child’s experience, to be personal, to like the students and to be concrete in teaching. The fifth special educator offers the students a contribution to deep approach to learning and she offers a way to work at the lessons that creates motivation and willingness to learn. The special education component she thinks is important is to find out what knowledge the child has, and work from there so the child has the possibility to understand what he or she hasn’t understood.

Humankind is facing global ecological problems and resulting from these social issues, while continually destroying the ecosystems which are the life-support mechanisms of the planet and human civilization. The socio-economic system is largely influenced by top-down decision making. Political decisions are a high leverage in sustainability issues, but contemporarily they are conducted in the reductionist way, focusing on short-term profit and jeopardizing the planet and people in the long run. The thesis explores the ways of integrating more holistic approach into political decision making. The study describes the connection between cognitive processes (e.g. learning or decision making) and somatic experiences: human decisions are considered a dynamic product of interaction between the cognition, body and environment. The theory of deep learning helps to understand how decision making can be transformed, and embodied cognitive science explains what facilitates the process of deep learning. The study develops the concept of “body-environment dialogue” — the somatic and cognitive integration of an agent and the context through which the agent receives non-verbal information processed then into the agent’s inner knowledge. The way of processing the information, unlike analytical thinking, is grounded into mindfulness and reflection. It results in the holistic insight about the global socio-ecological system and its interconnections, awakes intrinsic values and causes the change in one’s decisions and actions. Embodied experiences and connection with natural environment are considered the ways to facilitate deep learning which, in turn, affects decision making. The empirical part of the research tests the possibility to affect decision making through embodied contact with nature and the local context. The experimental study project based on 3-day outdoor experiential course demonstrates a certain change in the participants’ decision making as well as illustrates the challenges and drawbacks of such approach.

No description available.

The aim of this doctoral thesis is to present a body of work aimed at reducing the time spent by animators manually constructing keyframed animation. To this end we present a number of state of the art machine learning techniques applied to the domain of character animation. Data-driven tools for the synthesis and production of character animation have a good track record of success. In particular, they have been adopted thoroughly in the games industry as they allow designers as well as animators to simply specify the high-level descriptions of the animations to be created, and the rest is produced automatically. Even so, these techniques have not been thoroughly adopted in the film industry in the production of keyframe based animation [Planet, 2012]. Due to this, the cost of producing high quality keyframed animation remains very high, and the time of professional animators is increasingly precious. We present our work in four main chapters. We first tackle the key problem in the adoption of data-driven tools for key framed animation - a problem called the inversion of the rig function. Secondly, we show the construction of a new tool for data-driven character animation called the motion manifold - a representation of motion constructed using deep learning that has a number of properties useful for animation research. Thirdly, we show how the motion manifold can be extended as a general tool for performing data-driven animation synthesis and editing. Finally, we show how these techniques developed for keyframed animation can also be adapted to advance the state of the art in the games industry.

abstract: This action research study is the culmination of several action cycles investigating cognitive information processing and learning strategies based on students approach to learning theory and assessing students' meta-cognitive learning, motivation, and reflective development suggestive of deep learning. The study introduces a reading assignment as an integrative teaching method with the purpose of challenging students' assumptions and requiring them to think from multiple perspectives thus influencing deep learning. The hypothesis is that students who are required to critically reflect on their own perceptions will develop the deep learning skills needed in the 21st century. Pre and post surveys were used to assess for changes in students' preferred approach to learning and reflective practice styles. Qualitative data was collected in the form of student stories and student literature circle transcripts to further describe student perceptions of the experience. Results indicate stories that include examples of critical reflection may influence students to use more transformational types of reflective learning actions. Approximately fifty percent of the students in the course increased their preference for deep learning by the end of the course. Further research is needed to determine the effect of narratives on student preferences for deep learning. / Dissertation/Thesis / Ed.D. Leadership and Innovation 2012

Pose estimation is the problem of detecting poses of people in images, multiperson pose estimation is the problem of detecting poses of multiple persons in images. This thesis investigates multi-person pose estimation by applying the associative embedding method on images from soccer videos. Three models are compared, first a pre-trained model, second a fine-tuned model and third a model extended to handle image sequences. The pre-trained method performed well on soccer images and the fine-tuned model performed better then the pre-trained model. The image sequence model performed equally as the fine-tuned model but not better. This thesis concludes that the associative embedding model is a feasible option for pose estimation in soccer videos and should be further researched.