This thesis presents a novel Dynamic Gesture Language Recognition (DGLR) system for human-robot and inter-robot communication. We developed and implemented an experimental setup consisting of a humanoid robot/android able to recognize and execute in real time all the arm gestures of the Dynamic Gesture Language (DGL) in similar way as humans do. Our DGLR system comprises two main subsystems: an image processing (IP) module and a linguistic recognition system (LRS) module. The IP module enables recognizing individual DGL gestures. In this module, we use the bag-of-features (BOFs) and a local part model approach for dynamic gesture recognition from images. Dynamic gesture classification is conducted using the BOFs and nonlinear support-vector-machine (SVM) methods. The multiscale local part model preserves the temporal context. The IP module was tested using two databases, one consisting of images of a human performing a series of dynamic arm gestures under different environmental conditions and a second database consisting of images of an android performing the same series of arm gestures. The linguistic recognition system (LRS) module uses a novel formal grammar approach to accept DGL-wise valid sequences of dynamic gestures and reject invalid ones. LRS consists of two subsystems: one using a Linear Formal Grammar (LFG) to derive the valid sequence of dynamic gestures and another using a Stochastic Linear Formal Grammar (SLFG) to occasionally recover gestures that were unrecognized by the IP module. Experimental results have shown that the DGLR system had a slightly better overall performance when recognizing gestures made by a human subject (98.92% recognition rate) than those made by the android (97.42% recognition rate).

This master's thesis focuses on smartphone game for iOS, which uses recognition of face features and other information, which can be obtained from a smartphone's camera and sensors. This work describes a few approaches for real-time face detection and then introduces and compares possibilities for such task on iOS. Moreover, the thesis contains a draft of the final game and its levels. The game showcases various technologies in its levels such as object detection, processing an image color and others. Finally, the thesis introduces the final form of the game that is released and available on the App Store.

This paper is focused on object learning and recognizing in the image and in the image stream. More specifically on learning and recognizing humans or theirs parts in case they are partly occluded, with possible usage on robotic platforms. This task is based on features called Histogram of Oriented Gradients (HOG) which can work quite well with different poses the human can be in. The human is split into several parts and those parts are detected individually. Then a system of voting is introduced in which detected parts votes for the final positions of found people. For training the detector a linear SVM is used. Then the Kalman filter is used for stabilization of the detector in case of detecting from image stream.

This work focuses on classification and recognition of traffic signs in image. It describes briefly some used methods a deeply describes chosen system including extensions and method for creating models needed for classification. There's described implementation of library and demonstration program including important pieces of knowledge discovered during development. There're also results of some experiments and possible enhancements in conclusion.

Unmanned Aerial Vehicles (UAVs) provides a platform for many automated tasks and with an ever increasing advances in computing, these tasks can be more complex. The use of UAVs is expanded in this thesis with the goal of Search and Rescue (SAR), where a UAV can assist fast responders to search for a lost person and relay possible search areas back to SAR teams. To identify a person from an aerial perspective, low-level Histogram of Oriented Gradients (HOG) feature descriptors are used over a segmented region, provided from thermal data, to increase classification speed. This thesis also introduces a dataset to support a Bird’s-Eye-View (BEV) perspective and tests the viability of low level HOG feature descriptors on this dataset. The low-level feature descriptors are known as Boosted Histogram of Oriented Gradients (BHOG) features, which discretizes gradients over varying sized cells and blocks that are trained with a Cascaded Gentle AdaBoost Classifier using our compiled BEV dataset. The classification is supported by multiple sensing modes with color and thermal videos to increase classification speed. The thermal video is segmented to indicate any Region of Interest (ROI) that are mapped to the color video where classification occurs. The ROI decreases classification time needed for the aerial platform by eliminating a per-frame sliding window. Testing reveals that with the use of only color data iv and a classifier trained for a profile of a person, there is an average recall of 78%, while the thermal detection results with an average recall of 76%. However, there is a speed up of 2 with a video of 240x320 resolution. The BEV testing reveals that higher resolutions are favored with a recall rate of 71% using BHOG features, and 92% using Haar-Features. In the lower resolution BEV testing, the recall rates are 42% and 55%, for BHOG and Haar-Features, respectively.

Information spielt in der Natur eine zentrale Rolle. Als intrinsischer Teil des genetischen Codes ist sie das Grundgerüst jeder Struktur und ihrer Entwicklung. Im Speziellen dient sie auch Organismen, ihre Umgebung wahrzunehmen und sich daran anzupassen. Die Grundvoraussetzung dafür ist, dass sie Information ihrer Umgebung sowohl messen als auch interpretieren können, wozu Zellen komplexe Signaltransduktionswege entwickelt haben. In dieser Arbeit konzentrieren wir uns auf Signalprozesse in S.cerevisiae die von osmotischem Stress (High Osmolarity Glycerol (HOG) Signalweg) und der Stimulation mit α-Faktor (Pheromon Signalweg) angesprochen werden. Wir wenden stochastische Modelle an, die das intrinsische Rauschen biologischer Prozesse darstellen können, um verstehen zu können wie Signalwege die ihnen zur Verfügung stehende Information umsetzen. Informationsübertragung wird dabei mit einem Ansatz aus Shannons Informationstheorie gemessen, indem wir sie als einen Kanal in diesem Sinne auffassen. Wir verwenden das Maß der Kanalkapazität, um die Genauigkeit des Phosphorelays einschränken zu können. In diesem Modell, simuliert mit dem Gillespie Algorithmus, können wir durch die Analyse des Signalverhaltens den Parameterraum zusätzlich stark einschränken. Eine weitere Herangehensweise der Signalverarbeitung beschäftigt sich mit dem “Crosstalk” zwischen HOG und Pheromon Signalweg. Wir zeigen, dass die Kontrolle der Signalspezifizität vor allem bei Scaffold-Proteinen liegt, die Komponenten der Signalkaskade binden. Diese konservierten Motive zellulärer Signaltransduktion besitzen eine geeignete Struktur, um Information getreu übertragen zu können. Im letzten Teil der Arbeit untersuchen wir potentielle Gründe für die evolutionäre Selektion von Scaffolds. Wir zeigen, dass ihnen bereits durch die Struktur des Mechanismus möglich ist, Informationsgenauigkeit zu verbessern und einer verteilten Informationsweiterleitung sowohl dadurch als auch durch ihre Robustheit überlegen sind. / Information plays a ubiquitous role in nature. It provides the basis for structure and development, as it is inherent part of the genetic code. It also enables organisms to make sense of their environments and react accordingly. For this, a cellular interpretation of information is needed. Cells have developed sophisticated signaling mechanisms to fulfill this task and integrate many different external cues with their help. Here we focus on signaling that senses osmotic stress (High Osmolarity Glycerol (HOG) pathway) as well as α-factor stimulation (pheromone pathway) in S.cerevisiae. We employ stochastic modeling to simulates the inherent noisy nature of biological processes to assess how systems process the information they receive. This information transmission is evaluated with an information theoretic approach by interpreting signal transduction as a transmission channel in the sense of Shannon. We use channel capacity to both constrain as well as quantify the fidelity in the phosphorelay system of the HOG pathway. In this model, simulated with the Gillespie Algorithm, the analysis of signaling behavior allows us to constrain the possible parameter sets for the system severely. A further approach to signal processing is concerned with the mechanisms that conduct crosstalk between the HOG and the pheromone pathway. We find that the control for signal specificity lies especially with the scaffold proteins that tether signaling components and facilitate signaling by trans-location to the membrane and shielding against miss-activation. As conserved motifs of cellular signal transmission, these scaffold proteins show a particularly well suited structure for accurate information transmission. In the last part of this thesis, we examine the potential reasons for an evolutionary selection of the scaffolding structure. We show that due to its structure, scaffolds are increasing information transmission fidelity and outperform a distributed signal in this regard.

Manure contains nutrients for crop growth; however, overapplication, with time, can result in excess nutrients in soil, which can subsequently be lost in surface runoff. <p>The general purpose of this research is to study the effect of liquid hog manure, applied as an agricultural fertilizer, on water chemistry of surface runoff from rainfall simulation tests. Specifically the research focuses on runoff water chemistry comparisons between lands receiving hog manure at different rates, via different injection methods, and upon different slope positions. <p>To examine these objectives, soil nutrient supply rates (P, NH4-N, and NO3-N) of the 0 5 cm depth of soil adjacent to rainfall simulation positions, and runoff water chemistry (TP, OP, NH4-N, NO3-N, DOC, Cl- and coliforms) during rainfall simulation tests were collected before and after manure addition. <p> Generally, manure application did increase soil NH4-N and NO3-N supply rates, and runoff NH4-N concentration. Soil P supply rate and runoff TP concentration were not affected by the manure addition; however, runoff OP concentration at one site (Perdue) increased significantly due to manure addition. The manure treatments applied in this study did not cause any significant increases in fecal or total coliform in runoff from rainfall simulation tests conducted 7 8 months after manure application. None of the water quality parameters exceeded the Guidelines for Canadian Drinking Water Quality. <p> Manure injection method (regular versus low soil surface disturbance) had consistent effects on runoff chemistry, but application rate did not. The regular disturbance method had significantly higher concentrations of water quality parameters than the low disturbance method. <p> The position of the test on the slope did not result in any consistent trends in runoff chemistry, whether before or after manure addition. Foot slope positions had higher soil NH4-N supply rates than upper slope positions, both before and after manure addition. Soil NH4-N, NO3-N, and P supply rates between landscape positions were not likely influenced by manure addition. <p> Regression tests between soil nutrient supply rates and runoff chemistry indicate that soil NH4-N supply rates are a good index to predict runoff NH4-N concentration, but soil P did not predict runoff P.

Manure contains nutrients for crop growth; however, overapplication, with time, can result in excess nutrients in soil, which can subsequently be lost in surface runoff. <p>The general purpose of this research is to study the effect of liquid hog manure, applied as an agricultural fertilizer, on water chemistry of surface runoff from rainfall simulation tests. Specifically the research focuses on runoff water chemistry comparisons between lands receiving hog manure at different rates, via different injection methods, and upon different slope positions. <p>To examine these objectives, soil nutrient supply rates (P, NH4-N, and NO3-N) of the 0 5 cm depth of soil adjacent to rainfall simulation positions, and runoff water chemistry (TP, OP, NH4-N, NO3-N, DOC, Cl- and coliforms) during rainfall simulation tests were collected before and after manure addition. <p> Generally, manure application did increase soil NH4-N and NO3-N supply rates, and runoff NH4-N concentration. Soil P supply rate and runoff TP concentration were not affected by the manure addition; however, runoff OP concentration at one site (Perdue) increased significantly due to manure addition. The manure treatments applied in this study did not cause any significant increases in fecal or total coliform in runoff from rainfall simulation tests conducted 7 8 months after manure application. None of the water quality parameters exceeded the Guidelines for Canadian Drinking Water Quality. <p> Manure injection method (regular versus low soil surface disturbance) had consistent effects on runoff chemistry, but application rate did not. The regular disturbance method had significantly higher concentrations of water quality parameters than the low disturbance method. <p> The position of the test on the slope did not result in any consistent trends in runoff chemistry, whether before or after manure addition. Foot slope positions had higher soil NH4-N supply rates than upper slope positions, both before and after manure addition. Soil NH4-N, NO3-N, and P supply rates between landscape positions were not likely influenced by manure addition. <p> Regression tests between soil nutrient supply rates and runoff chemistry indicate that soil NH4-N supply rates are a good index to predict runoff NH4-N concentration, but soil P did not predict runoff P.

Computational imaging has been playing an important role in understanding and analysing the captured images. Both image segmentation and restoration has been in-tegral parts of computational imaging. The studies performed in this thesis has been focussed toward developing novel algorithms for image segmentation and restoration. Study related to usage of Morozov Discrepancy Principle in Di use Optical Imaging was also presented here to show that hyper parameter selection could be performed with ease. The Laplacian of Gaussian (LoG) and Canny operators use Gaussian smoothing be-fore applying the derivative operator for edge detection in real images. The LoG kernel was based on second derivative and is highly sensitive to noise when compared to the Canny edge detector. A new edge detection kernel, called as Helmholtz of Gaussian (HoG), which provides higher di suavity is developed in this thesis and it was shown that it is more robust to noise. The formulation of the developed HoG kernel is similar to LoG. It was also shown both theoretically and experimentally that LoG is a special case of HoG. This kernel when used as an edge detector exhibited superior performance compared to LoG, Canny and wavelet based edge detector for the standard test cases both in one- and two-dimensions. The linear inverse problem encountered in restoration of blurred noisy images is typically solved via Tikhonov minimization. The outcome (restored image) of such min-imitation is highly dependent on the choice of regularization parameter. In the absence of prior information about the noise levels in the blurred image, ending this regular-inaction/hyper parameter in an automated way becomes extremely challenging. The available methods like Generalized Cross Validation (GCV) may not yield optimal re-salts in all cases. A novel method that relies on minimal residual method for ending the regularization parameter automatically was proposed here and was systematically compared with the GCV method. It was shown that the proposed method performance was superior to the GCV method in providing high quality restored images in cases where the noise levels are high Di use optical tomography uses near infrared (NIR) light as the probing media to recover the distributions of tissue optical properties with an ability to provide functional information of the tissue under investigation. As NIR light propagation in the tissue is dominated by scattering, the image reconstruction problem (inverse problem) is non-linear and ill-posed, requiring usage of advanced computational methods to compensate this. An automated method for selection of regularization/hyper parameter that incorporates Morozov discrepancy principle(MDP) into the Tikhonov method was proposed and shown to be a promising method for the dynamic Di use Optical Tomography.

During the course of this thesis, two scenarios are considered. In the first one, we contribute to feature extraction algorithms. In the second one, we use features to improve object detection solutions and localization. The two scenarios give rise to into four thesis sub-goals. First, we present a new shape skeleton pruning algorithm based on contour approximation and the integer medial axis. The algorithm effectively removes unwanted branches, conserves the connectivity of the skeleton and respects the topological properties of the shape. The algorithm is robust to significant boundary noise and to rigid shape transformations. It is fast and easy to implement. While shape-based solutions via boundary and skeleton analysis are viable solutions to object detection, keypoint features are important for textured object detection. Therefore, we present a keypoint featurebased planar object detection framework for vision-based localization. We demonstrate that our framework is robust against illumination changes, perspective distortion, motion blur, and occlusions. We increase robustness of the localization scheme in cluttered environments and decrease false detection of targets. We present an off-line target evaluation strategy and a scheme to improve pose. Third, we extend planar object detection to a real-time approach for 3D object detection using a mobile and uncalibrated camera. We develop our algorithm based on two novel naive Bayes classifiers for viewpoint and feature matching that improve performance and decrease memory usage. Our algorithm exploits the specific structure of various binary descriptors in order to boost feature matching by conserving descriptor properties. Our novel naive classifiers require a database with a small memory footprint because we only store efficiently encoded features. We improve the feature-indexing scheme to speed up the matching process creating a highly efficient database for objects. Finally, we present a model-free long-term tracking algorithm based on the Kernelized Correlation Filter. The proposed solution improves the correlation tracker based on precision, success, accuracy and robustness while increasing frame rates. We integrate adjustable Gaussian window and sparse features for robust scale estimation creating a better separation of the target and the background. Furthermore, we include fast descriptors and Fourier spectrum packed format to boost performance while decreasing the memory footprint. We compare our algorithm with state-of-the-art techniques to validate the results.