We propose a novel approach for segmentation of human objects, including face and body, in image sequences. In modern video coding techniques, e.g., MPEG-4 and MPEG-7, human objects are usually the main focus for multimedia applications. We combine temporal and spatial information and employ a neuro-fuzzy mechanism to extract human objects. A fuzzy self-clustering technique is used to divide the video frame into a set of segments. The existence of a face within a candidate face region is ensured by searching for possible constellations of eye-mouth triangles and verifying each eye-mouth combination with the predefined template. Then rough foreground and background are formed based on a combination of multiple criteria. Finally, human objects in the base frame and the remaining frames of the video stream are precisely located by a fuzzy neural network which is trained by a SVD-based hybrid learning algorithm. Through experiments, we compare our system with two other approaches, and the results have shown that our system can detect face locations and extract human objects more accurately.

In this thesis, we present an event orderer application that works on Turkish texts. Events are words denoting an occurrence or happenings in natural language texts. By using the features of the events in a sentence or by the helps of temporal expressions in the sentence, anchoring an event on a timeline or ordering events between other events are called event ordering. The application presented in this thesis, is one of the earliest study in this domain with Turkish and it realizes all needed sub modules for event ordering. It realizes event recognition in Turkish texts and event feature detection in Turkish texts. In addition to this, the application is realizing temporal expression recognition and temporal signal recognition tasks.

Cognitive radio network has emerged as a prevailing technique and an exciting and promising technology which has the potential of dealing with the inflexible prerequisites and the inadequacy of the radio spectrum usage. In cognitive radios, in-band sensing is fundamental for the protection of the licensed spectrum users, enabling secondary users to vacate channels immediately upon detection of primary users. This channel sensing scheme directly affects the quality-of-service of cognitive radio user and licensed user especially with the undesirable delay induced into the system. In this thesis, a combination of different delay reduction schemes from different papers has been introduced, the first paper [47] argues about performing fine sensing for non-real time traffic, while real time traffic continues transmission in the channel. The second paper [46] argues about performing fine sensing after multiple alarms that have been triggered. Both schemes have combined with applying data rate reservation as well in order to reduce as much as possible this crucial factor of delay for IEEE 802.22 wireless regional area network and to improve the channel utilization. Data rate reservation for real time users has been applied in order to reduce the queuing delay for real time services [47]. The average packet delay for the proposed scheme combination has been analyzed, with both numerical and simulation results. The results show that the scheme combination considerably reduces the average packet delay for both real time and non-real time services and hence satisfies the performance of IEEE 802.22 wireless regional networks. Index terms–Channel sensing, Cognitive radio, energy and feature detection, IEEE 802.22, quiet period. / Kognitiv radio nätverk har vuxit fram som en rådande teknik och en spännande och lovande teknik som har potential att hantera de oflexibla förutsättningar och den bristfälliga Radiospektrumanvändningens. I kognitiv radio, är i-band Sensing grundläggande för skyddet av de licensierade spektrumanvändare, möjliggör sekundära användare att utrymma kanaler omedelbart vid detektering av primära användare. Denna kanal sensing system påverkar direkt kvaliteten på tjänsterna för kognitiv radio användare och licensierade användaren särskilt med oönskad fördröjning induceras i systemet.   I denna avhandling har en kombination av olika system delay minskning från olika tidningar införts, den första papper [47] argumenterar om att utföra fina avkänning för icke-realtid trafik, medan realtid trafiken fortsätter sändningen i kanalen. Den andra artikeln [46] argumenterar om att utföra fina avkänning efter flera larm som har utlösts. Båda systemen har i kombination med tillämpning datahastighet bokning samt för att minska så mycket som möjligt denna avgörande faktor för försening för IEEE 802,22 trådlös regionala nätverk och förbättra kanalutnyttjandet. Datahastighet reservation för realtidanvändare har tillämpats för att minska den queuing fördröjningen för realtidstjänster [47]. Den genomsnittliga paket fördröjning för det föreslagna systemet kombinationen har analyserats, med både numeriska och simulering resultat. Resultaten visar att systemet kombinationen avsevärt minskar den genomsnittliga paket fördröjning för både realtid och icke-verkliga tjänster tiden och därmed uppfyller prestanda IEEE 802,22 trådlösa regionala nätverk. / Kungsmarksvagen 71, karlskrona +4520939959

Histopathological classification and grading of biopsy specimens play an important role in early cancer detection and prognosis. Nottingham Grading System (NGS) is one of the standard grading procedures used in breast cancer assessment, where three parameters, Mitotic Count (MC), Nuclear Pleomorphism (NP), and Tubule Formation (TF) are used for prognostic information. The grading takes into account the deviations in cellular structures and appearance between tumour and normal cells, using measures such as density, size, colour, and regularity. Cell structures in tissue images are also known to exhibit multifractal characteristics. This research focused on the multifractal properties of several graded biopsy specimens and analysed the dependency and variation of the fractal parameters with respect to the scores pre-assigned by pathologists. The effectiveness of using multifractal techniques on breast cancer grading was measured with a set of quantitative evaluations for MC, NP, and TF criteria. The developed method for MC scoring has obtained 82.87% true positive rate on detecting mitotic cells. Furthermore, the overall positive classification rates for NP and TF analysis were 67.38% and 71.82%, respectively, while obtaining 30.26% of false classification rate for NP analysis and 27.17% for TF analysis. The results have shown that multifractal formalism is a feasible and novel method that could be used for automatic grading of biopsy sections.

abstract: There is a growing interest in the creation of three-dimensional (3D) images and videos due to the growing demand for 3D visual media in commercial markets. A possible solution to produce 3D media files is to convert existing 2D images and videos to 3D. The 2D to 3D conversion methods that estimate the depth map from 2D scenes for 3D reconstruction present an efficient approach to save on the cost of the coding, transmission and storage of 3D visual media in practical applications. Various 2D to 3D conversion methods based on depth maps have been developed using existing image and video processing techniques. The depth maps can be estimated either from a single 2D view or from multiple 2D views. This thesis presents a MATLAB-based 2D to 3D conversion system from multiple views based on the computation of a sparse depth map. The 2D to 3D conversion system is able to deal with the multiple views obtained from uncalibrated hand-held cameras without knowledge of the prior camera parameters or scene geometry. The implemented system consists of techniques for image feature detection and registration, two-view geometry estimation, projective 3D scene reconstruction and metric upgrade to reconstruct the 3D structures by means of a metric transformation. The implemented 2D to 3D conversion system is tested using different multi-view image sets. The obtained experimental results of reconstructed sparse depth maps of feature points in 3D scenes provide relative depth information of the objects. Sample ground-truth depth data points are used to calculate a scale factor in order to estimate the true depth by scaling the obtained relative depth information using the estimated scale factor. It was found out that the obtained reconstructed depth map is consistent with the ground-truth depth data. / Dissertation/Thesis / M.S. Electrical Engineering 2010

This thesis proposes a solution to the pose estimation problem for mobile devices in an outdoors environment. The proposed solution is intended for usage within an augmented reality application to visualize large objects such as buildings. As such, the system needs to provide both accurate and stable pose estimations with real-time requirements. The proposed solution combines inertial navigation for orientation estimation with a vision-based support component to reduce noise from the inertial orientation estimation. A GNSS-based component provides the system with an absolute reference of position. The orientation and position estimation were tested in two separate experiments. The orientation estimate was tested with the camera in a static position and orientation and was able to attain an estimate that is accurate and stable down to a few fractions of a degree. The position estimation was able to achieve centimeter-level stability during optimal conditions. Once the position had converged to a location, it was stable down to a couple of centimeters, which is sufficient for outdoors augmented reality applications.

This dissertation focuses on two distinct but related problems involving detection in multiple images. The first problem focuses on the accurate detection of runways by fusing Synthetic Vision System (SVS) and Enhanced Vision System (EVS) images. A novel procedure is developed to accurately detect runways and horizons and also enhance runway surrounding areas by fusing enhanced vision system (EVS) and synthetic vision system (SVS) images of the runway while an aircraft is landing. Because the EVS and SVS frames are not aligned, a registration step is introduced to align the EVS and SVS images prior to fusion. The most notable feature of the registration procedure is that it is guided by the information extracted from the weather-invariant SVS images. Four fusion rules based on combining Discrete Wavelet Transform (DWT) sub-bands are implemented and evaluated. The resulting procedure is tested on real EVS-SVS image pairs and also on image pairs containing simulated EVS images with varying levels of turbulence. The subjective and objective evaluations reveal that runways and horizons can be detected accurately even in poor visibility conditions. Furthermore, it is demonstrated that different aspects of the EVS and SVS images can be emphasized by using different DWT fusion rules. Another notable feature is that the entire procedure is autonomous throughout the landing sequence irrespective of the weather conditions. Given the excellent fusion results and the autonomous feature, it can be concluded that the fusion procedure developed is quite promising for incorporation into head-up displays (HUDs) to assist pilots in safely landing aircrafts in varying weather conditions. The second problem focuses on the blind detection of hidden messages that are embedded in images using various steganography methods. A new steganalysis strategy is introduced to blindly detect hidden messages that have been embedded in JPEG images using various steganography techniques. The key contribution is the formulation of a multi-domain feature extraction, ranking, and selection strategy to improve the steganalysis performance. The multi-domain features are statistical measures extracted from DWT, muti-wavelet (MWT), and slantlet (SLT) transforms. Feature ranking and selection is based on evaluating the performance of each feature independently and combining the best uncorrelated features. The resulting feature set is used in conjunction with discriminant analysis and support vector classifiers to detect the presence/absence of hidden messages in images. Numerous experiments are conducted to demonstrate the improved performance of the new steganalysis strategy over existing steganalysis methods.

Depth information of tissue surfaces and laparoscope poses are crucial for accurate surgical guidance and navigation in Computer Assisted Surgeries (CAS). Intra-operative Three Dimensional (3D) reconstruction and laparoscope localization are therefore two fundamental tasks in CAS. This dissertation focuses on the abdominal Minimally Invasive Surgeries (MIS) and presents laparoscopic-video-based methods for these two tasks. Different kinds of methods have been presented to recover 3D surface structures of surgical scenes in MIS. Those methods are mainly based on laser, structured light, time-of-flight cameras, and video cameras. Among them, laparoscopic-video-based surface reconstruction techniques have many significant advantages. Specifically, they are non-invasive, provide intra-operative information, and do not introduce extra-hardware to the current surgical platform. On the other side, laparoscopic-video-based 3D reconstruction and laparoscope localization are challenging tasks due to the specialties of the abdominal imaging environment. The well-known difficulties include: low texture, homogeneous areas, tissue deformations, and so on. The goal of this dissertation is to design novel 3D reconstruction and laparoscope localization methods and overcome those challenges from the abdominal imaging environment. Two novel methods are proposed to achieve accurate 3D reconstruction for MIS. The first method is based on the detection of distinctive image features, which is difficult in MIS images due to the low-texture and homogeneous tissue surfaces. To overcome this problem, this dissertation first introduces new types of image features for MIS images based on blood vessels on tissue surfaces and designs novel methods to efficiently detect them. After vessel features have been detected, novel methods are presented to match them in stereo images and 3D vessels can be recovered for each frame. Those 3D vessels from different views are integrated together to obtain a global 3D vessel network and Poisson reconstruction is applied to achieve large-area dense surface reconstruction. The second method is texture-independent and does not rely on the detection of image features. Instead, it proposes to mount a single-point light source on the abdominal wall. Shadows are cast on tissue surfaces when surgical instruments are waving in front of the light. Shadow boundaries are detected and matched in stereo images to recover the depth information. The recovered 3D shadow curves are interpolated to achieve dense reconstruction of tissue surfaces. One novel stereoscope localization method is designed specifically for the abdominal environment. The method relies on RANdom SAmple Consensus (RANSAC) to differentiate rigid points and deforming points. Since no assumption is made on the tissue deformations, the proposed methods is able to handle general tissue deformations and achieve accurate laparoscope localization results in the abdominal MIS environment. With the stereoscope localization results and the large-area dense surface reconstruction, a new scene visualization system, periphery augmented system, is designed to augment the peripheral areas of the original video so that surgeons can have a larger field of view. A user-evaluation system is designed to compare the periphery augmented system with the original MIS video. 30 subjects including 4 surgeons specialized in abdominal MIS participate the evaluation and a numerical measure is defined to represent their understanding of surgical scenes. T-test is performed on the numerical errors and the null hypothesis that the periphery augmented system and the original video have the same mean of errors is rejected. In other words, the results validate that the periphery augmented system improves users' understanding and awareness of surgical scenes.

Context. Embedded platforms GPUs are reaching a level of perfor-mance comparable to desktop hardware. Therefore it becomes inter-esting to apply Computer Vision techniques to modern smartphones.The platform holds different challenges, as energy use and heat gen-eration can be an issue depending on load distribution on the device. Objectives. We evaluate the viability of a feature detector and de-scriptor on the Xperia Z3. Specifically we evaluate the the pair basedon real-time execution, heat generation and performance. Methods. We implement the feature detection and feature descrip-tor pair Harris-Hessian/FREAK for GPU execution using OpenCL,focusing on embedded platforms. We then study the heat generationof the application, its execution time and compare our method to twoother methods, FAST/BRISK and ORB, to evaluate the vision per-formance. Results. Execution time data for the Xperia Z3 and desktop GeForceGTX660 is presented. Run time temperature values for a run ofnearly an hour are presented with correlating CPU and GPU ac-tivity. Images containing comparison data for BRISK, ORB andHarris-Hessian/FREAK is shown with performance data and discus-sion around notable aspects. Conclusion. Execution times on Xperia Z3 is deemed insufficientfor real-time applications while desktop execution shows that there isfuture potential. Heat generation is not a problem for the implemen-tation. Implementation improvements are discussed to great lengthfor future work. Performance comparisons of Harris-Hessian/FREAKsuggest that the solution is very vulnerable to rotation, but superiorin scale variant images. Generally appears suitable for near duplicatecomparisons, delivering much greater number of keypoints. Finally,insight to OpenCL application development on Android is given

This thesis is concerned with topics related to dense mapping of large scale three-dimensional spaces. In particular, the motivating scenario of this work is one in which a mobile robot with limited computational resources explores an unknown environment using a depth-camera. To this end, low-level topics such as sensor noise, map representation, interpolation, bit-rates, compression are investigated, and their impacts on more complex tasks, such as feature detection and description, camera-tracking, and mapping are evaluated thoroughly. A central idea of this thesis is the use of truncated signed distance fields (TSDF) as a map representation and a comprehensive yet accessible treatise on this subject is the first major contribution of this dissertation. The TSDF is a voxel-based representation of 3D space that enables dense mapping with high surface quality and robustness to sensor noise, making it a good candidate for use in grasping, manipulation and collision avoidance scenarios. The second main contribution of this thesis deals with the way in which information can be efficiently encoded in TSDF maps. The redundant way in which voxels represent continuous surfaces and empty space is one of the main impediments to applying TSDF representations to large-scale mapping. This thesis proposes two algorithms for enabling large-scale 3D tracking and mapping: a fast on-the-fly compression method based on unsupervised learning, and a parallel algorithm for lifting a sparse scene-graph representation from the dense 3D map. The third major contribution of this work consists of thorough evaluations of the impacts of low-level choices on higher-level tasks. Examples of these are the relationships between gradient estimation methods and feature detector repeatability, voxel bit-rate, interpolation strategy and compression ratio on camera tracking performance. Each evaluation thus leads to a better understanding of the trade-offs involved, which translate to direct recommendations for future applications, depending on their particular resource constraints.