Yazar "Yilmaz, Ozgur" seçeneğine göre listele
Listeleniyor 1 - 12 / 12
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe 3D Modeling of a Scene with an Autonomous Robot(Ieee, 2016) Pur, Sezai Furkan; Kasap, Mahmut; Yilmaz, OzgurIn today's technology, the popularity of the robotic systems is getting increased due to the fact that they facilitate Daily life and that they are becoming more functionality. In line with it, the robots that are cheap and easy to obtain are getting crucial. In the current study, a robot was created using materials cheap and easy to provide. After that, an autonomous navigation algorithm was designed and a 3D modeling system was formed with KinectFusion algorithm using an ASUS Xtion camera, which is able to give a rapid depth map, on a graphic card with an embedded NVIDIA Jetson TK1 having a rapid graphic processor. Then, this was integrated on the robot. In this way, it was aimed to create an autonomous robot being able to give a 3 dimensional model of the scene by moving autonomously and without striking the obstacle around.Öğe Analogy making and logical inference on images using cellular automata based hyperdimensional computing(CEUR-WS, 2015) Yilmaz, OzgurIn this paper, we introduce a framework of reservoir computing that is capable of both connectionist machine intelligence and symbolic computation. Cellular automaton is used as the reservoir of dynamical systems. A cellular automaton is a very sparsely connected network with logical nodes and nonlinear/logical connection functions, hence the proposed system corresponds to a binary valued and nonlinear neuro-symbolic architecture. Input is randomly projected onto the initial conditions of automaton cells and nonlinear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the reservoir. In addition to being used as the feature representation for pattern recognition, binary reservoir vectors can be combined using Boolean operations as in hyperdimensional computing, paving a direct way symbolic processing. To demonstrate the capability of the proposed system, we make analogies directly on image data by asking 'What is the Automobile of Air'?, and make logical inference using rules by asking 'Which object is the largest?'. © 2016 Elsevier B.V., All rights reserved.Öğe Camera aided navigation for the visually impaired(Institute of Electrical and Electronics Engineers Inc., 2016) Isik, Kadir; Taskin, Erol; Unal, M. Fatih; Yilmaz, Ozgur; Baştan, MuhammetOne of the most challenging problems a visually impaired person experiences is outdoor navigation. We present an Android application to be used by the visually impaired for GPS and compass based navigation, and a camera based visual navigation for accurate guidance which uses visual matching on previously saved visual landmarks. The system has an ergonomic and intuitive touch based user interface suitable for visually impaired. © 2017 Elsevier B.V., All rights reserved.Öğe Camera Aided Navigation for the Visually Impaired(Ieee, 2016) Isik, Kadir; Taskin, Erol; Unal, M. Fatih; Yilmaz, Ozgur; Bastan, MuhammetOne of the most challenging problems a visually impaired person experiences is outdoor navigation. We present an Android application to be used by the visually impaired for GPS and compass based navigation, and a camera based visual navigation for accurate guidance which uses visual matching on previously saved visual landmarks. The system has an ergonomic and intuitive touch based user interface suitable for visually impaired.Öğe Classification of Occluded Objects using Fast Recurrent Processing(Elsevier Science Bv, 2015) Yilmaz, OzgurRecurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset and shown to achieve 2x improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.Öğe Detection and localization of specular surfaces using image motion cues(Springer, 2014) Yilmaz, Ozgur; Doerschner, KatjaSuccessful identification of specularities in an image can be crucial for an artificial vision system when extracting the semantic content of an image or while interacting with the environment. We developed an algorithm that relies on scale and rotation invariant feature extraction techniques and uses motion cues to detect and localize specular surfaces. Appearance change in feature vectors is used to quantify the appearance distortion on specular surfaces, which has previously been shown to be a powerful indicator for specularity (Doerschner et al. in Curr Biol, 2011). The algorithm combines epipolar deviations (Swaminathan et al. in Lect Notes Comput Sci 2350:508-523, 2002) and appearance distortion, and succeeds in localizing specular objects in computer-rendered and real scenes, across a wide range of camera motions and speeds, object sizes and shapes, and performs well under image noise and blur conditions.Öğe Effects of surface reflectance and 3D shape on perceived rotation axis(Assoc Research Vision Ophthalmology Inc, 2013) Doerschner, Katja; Yilmaz, Ozgur; Kucukoglu, Gizem; Fleming, Roland W.Surface specularity distorts the optic flow generated by a moving object in a way that provides important cues for identifying surface material properties (Doerschner, Fleming et al., 2011). Here we show that specular flow can also affect the perceived rotation axis of objects. In three experiments, we investigate how three-dimensional shape and surface material interact to affect the perceived rotation axis of unfamiliar irregularly shaped and isotropic objects. We analyze observers' patterns of errors in a rotation axis estimation task under four surface material conditions: shiny, matte textured, matte untextured, and silhouette. In addition to the expected large perceptual errors in the silhouette condition, we find that the patterns of errors for the other three material conditions differ from each other and across shape category, yielding the largest differences in error magnitude between shiny and matte, textured isotropic objects. Rotation axis estimation is a crucial implicit computational step to perceive structure from motion; therefore, we test whether a structure from a motion-based model can predict the perceived rotation axis for shiny and matte, textured objects. Our model's predictions closely follow observers' data, even yielding the same reflectance-specific perceptual errors. Unlike previous work (Caudek & Domini, 1998), our model does not rely on the assumption of affine image transformations; however, a limitation of our approach is its reliance on projected correspondence, thus having difficulty in accounting for the perceived rotation axis of smooth shaded objects and silhouettes. In general, our findings are in line with earlier research that demonstrated that shape from motion can be extracted based on several different types of optical deformation (Koenderink & Van Doorn, 1976; Norman & Todd, 1994; Norman, Todd, & Orban, 2004; Pollick, Nishida, Koike, & Kawato, 1994; Todd, 1985).Öğe How Much Computation and Distributedness is Needed in Sequence Learning Tasks?(Springer Int Publishing Ag, 2016) Margem, Mrwan; Yilmaz, OzgurIn this paper, we are analyzing how much computation and distributedness of representation is needed to solve sequence-learning tasks which are essential for many artificial intelligence applications. We propose a novel minimal architecture based on cellular automata. The states of the cells are used as the reservoir of activities as in Echo State Networks. The projection of the input onto this reservoir medium provides a systematic way of remembering previous inputs and combining the memory with a continuous stream of inputs. The proposed framework is tested on classical synthetic pathological tasks that are widely used in evaluating recurrent algorithms. We show that the proposed algorithm achieves zero error in all tasks, giving a similar performance with Echo State Networks, but even better in many different aspects. The comparative results in our experiments suggest that, computation of high order attribute statistics and representing them in a distributed manner is essential, but it can be done in a very simple network of cellular automaton with identical binary units. This raises the question of whether real valued neuron units are mandatory for solving complex problems that are distributed over time. Even very sparsely connected binary units with simple computational rules can provide the required computation for intelligent behavior.Öğe Machine Learning Using Cellular Automata Based Feature Expansion and Reservoir Computing(Old City Publishing Inc, 2015) Yilmaz, OzgurIn this paper, we introduce a novel framework of cellular automata based computing that is capable of long short-term memory. Cellular automaton is used as the reservoir of dynamical systems. Input is randomly projected onto the initial conditions of automaton cells and non-linear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the feature vector. The proposed framework requires orders of magnitude less computation compared to Echo State Networks. We prove that cellular automaton reservoir holds a distributed representation of attribute statistics, which provides a more effective computation than local representation. It is possible to estimate the kernel for linear cellular automata via metric learning, that enables a much more efficient distance computation in support vector machines framework.Öğe Stereo and Kinect Fusion for Continuous 3D Reconstruction and Visual Odometry(Ieee, 2013) Yilmaz, Ozgur; Karakus, FatihRobust and accurate 3D reconstruction of the scene is essential for many robotic and computer vision applications. We are proposing a system solution that can accurately reconstruct the scene both indoor and outdoor, in real-time. The system utilizes both active and passive visual sensors in conjunction with peripheral hardware for communication, and suggests a significant accuracy improvement over state-of-the-art SLAM algorithms via stereo visual odometry integration.Öğe Stereo and KinectFusion for continuous 3D reconstruction and visual odometry(Tubitak Scientific & Technological Research Council Turkey, 2016) Yilmaz, Ozgur; Karakus, FatihRobust and accurate 3D reconstruction of a scene is essential for many robotic and computer vision applications. Although recent studies propose accurate reconstruction algorithms, they are only suitable for indoor operation. We are proposing a system solution that can accurately reconstruct the scene both indoors and outdoors, in real time. The system utilizes both active and passive visual sensors in conjunction with peripheral hardware for communication and suggests an accuracy improvement in both reconstruction and pose estimation accuracy over state-of-the-art SLAM algorithms via stereo visual odometry integration. We also introduce the concept of multisession reconstruction, which is relevant for many real-world applications. In our solution to this concept, distinct regions in a scene can be reconstructed in detail in separate sessions using the KinectFusion framework and merged into a global scene using continuous visual odometry camera tracking.Öğe Symbolic Computation Using Cellular Automata-Based Hyperdimensional Computing(Mit Press, 2015) Yilmaz, OzgurThis letter introduces a novel framework of reservoir computing that is capable of both connectionist machine intelligence and symbolic computation. A cellular automaton is used as the reservoir of dynamical systems. Input is randomly projected onto the initial conditions of automaton cells, and nonlinear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the reservoir. The proposed framework is shown to be capable of long-term memory, and it requires orders of magnitude less computation compared to echo state networks. As the focus of the letter, we suggest that binary reservoir feature vectors can be combined using Boolean operations as in hyperdimensional computing, paving a direct way for concept building and symbolic processing. To demonstrate the capability of the proposed system, we make analogies directly on image data by asking, What is the automobile of air?
