Abstract: Target initialization can dramatically change the performance of the tracker, since the initial window determines for the tracker what to track. In order to achieve a better tracking performance; The present invention relates to a method of semi automatic target initialization based on visual saliency for a given point coordinate in the vicinity of target by the user. Performance boost of tracker is mainly based on two key features of target initialization algorithm: It is capable of compensating erroneous user input; also selecting the most distinctive, salient part of object as target, so better discrimination is achieved between the target and background. Experimental results show that tracking performance is boosted in scenarios, in which the tracking is initialized by the proposed algorithm. Very low computational cost and requirement of only a point coordinate as input in the neighborhood of the target make this approach preferable in real time tracking applications.

Abstract: The present invention relates to the field of image processing and methodologies to passively focus an image automatically, using the electronic sensor signal. The method comprises steps of; receiving a pixel image, generating at least two histograms of the received image using at least two different frequency components, finding widths of acquired histograms and storing them as a focus measure, finding difference between last received frame's highest frequency component histogram width and at least one previously received frame's histogram width corresponding to the same component, determine whether there is a meaningful difference, and determine the focus direction signal by using the difference. The system comprises; an image sensor to acquire an electronic pixel image; an image processing unit configured to receive an image and implement the method using this image and output a focus direction signal found by the method; and a memory unit configured to store image histogram widths.

Abstract: A real-time, semi-automatic method for discriminant track initialization in thermal imagery is very critical for tracking since it determines what to track for the tracker. Therefore, any insignificant or false information may result in redundant features or deceptive appearance that can cause premature track losses. To achieve long-term tracking, a real-time, semi-automatic track initialization methodology for images is proposed which takes a single image coordinate as input, then generates target bounding box for the most salient segment. The present invention is designed for real-time applications in which erroneous user input is unavoidable. Therefore, error compensation capability of present invention both introduces many practical advantageous together with performance boost. Low computational cost and requirement of only a point coordinate as input in the vicinity of the target make this approach preferable in real-time tracking applications.

Abstract: The feed reflected Doherty amplifier utilizes the output characteristics of the carrier amplifier to control the input signal of the peaking amplifier to improve the gain, linearity and efficiency of a Doherty amplifier. The feed reflected Doherty amplifier comprises an input power splitter, a carrier amplifier branch and a peaking amplifier branch combined into a common load, an output directional coupler and an input directional coupler connected via a phase shift element.

Abstract: The present invention relates to the field of image processing and methodologies to construct a descriptor from binary silhouette images. The method comprises the steps of; receiving a parametric equation of a closed planar curve, choosing nodes on the closed planar curve with equal intervals, generating a continuous scale space of the nodes on the curve by successively convolving the planar curve with a Gaussian filter and down-sampling it after each octave, calculating orientation vectors and orientation angle values for each sampled point at each interval of each octave, creating a orientation scale space (OSS) which is a matrix obtained from stacking each orientation angle value on top of each other, representing the outline with a descriptor including all the orientation vectors and their respective parameters position and scale.

Abstract: The present invention relates to a high security system (1) and method (100) which prevents unauthorized (foreign) radios (R) that are not defined in the system from being served by the main communication system (MCS) in professional radio systems and which thus secures the communication of the radios (R) that are registered in the system.

Abstract: The present invention relates to the field of computation and covers methods to find one to one mapping between fiducial markers on a tracked object and fiducial marker projections on the image plane captured by a camera in optical object tracking systems. A method for solving correspondence problem is realized to find correspondences between 3D points of an object and 2D projection of that object onto the image plane so that this can be used to find the object's 3D location and orientation. It is designed to work without current pose of the tracked object thus it is equally efficient on initial correspondence problem as correspondence problem. Furthermore, a method for selecting LED groups to be used for solving correspondence problem is also presented, which uses pose data representing possible poses of tracked object under working conditions thus LEDS groups are selected to satisfy use case requirements.

Abstract: The present invention relates to the field of computation and simulation and covers methods to optimize the fiducial marker positions in optical object tracking systems, by simulating the visibility.

Abstract: Target initialization can dramatically change the performance of the tracker, since the initial window determines for the tracker what to track. In order to achieve a better tracking performance; The present invention relates to a method of semi automatic target initialization based on visual saliency for a given point coordinate in the vicinity of target by the user. Performance boost of tracker is mainly based on two key features of target initialization algorithm: It is capable of compensating erroneous user input; also selecting the most distinctive, salient part of object as target, so better discrimination is achieved between the target and background. Experimental results show that tracking performance is boosted in scenarios, in which the tracking is initialized by the proposed algorithm. Very low computational cost and requirement of only a point coordinate as input in the neighborhood of the target make this approach preferable in real time tracking applications.

Abstract: The present invention relates to a method for incremental learning of a classification model, where pre-defined weak incremental learners are distributed over the distinct regions in a set of partitionings of the input domain. The partitionings and regions are organized via a binary tree and they are allowed to vary in a data-driven way, i.e., in a way to minimize the classification error rate. Moreover, to test a given data point, a mixture of decisions is obtained through the models learned in the regions that this point falls in. Hence, naturally, in the cold start phase of the data stream, the simpler models belonging to the larger regions are favored and as more data get available, the invention automatically puts more weights on the more complex models.

Abstract: This topic is related to a waveguide propagation apparatus, converting microstrip propagation to waveguide propagation, providing hermeticity on the mounting area, eliminating the cabling component causing degradation on the overall performance, involving at least a microwave module (2), and comprising a combination of a base part (3) and a cover part (4).

Abstract: The present invention relates to the field of computation and covers methods to find one to one mapping between fiducial markers on a tracked object and fiducial marker projections on the image plane captured by a camera in optical object tracking systems. A method for solving correspondence problem is realized to find correspondences between 3D points of an object and 2D projection of that object onto the image plane so that this can be used to find the object's 3D location and orientation. It is designed to work without current pose of the tracked object thus it is equally efficient on initial correspondence problem as correspondence problem. Furthermore, a method for selecting LED groups to be used for solving correspondence problem is also presented, which uses pose data representing possible poses of tracked object under working conditions thus LEDS groups are selected to satisfy use case requirements.

Abstract: Recurrent neural networks are powerful tools for handling incomplete data problems in machine learning thanks to their significant generative capabilities. However, the computational demand for algorithms to work in real time applications requires specialized hardware and software solutions. We disclose a method for adding 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 an incomplete data problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations.

Abstract: The present invention relates to a method for object tracking where the tracking is realized based on object classes, where the classifiers of the objects are trainable without a need for supervision and where the tracking errors are reduced and robustness is increased.

Abstract: The present invention relates to the field of image processing and image stabilization methodologies used on image acquisition and processing systems. A method and apparatus to generate an image sequence output that is stable and free of any sudden jumps from an image sequence input acquired with an imaging system whose line of sight is fixed but may drift in time, and by efficiently updating the reference frames that are used in the image stabilization, the method can be optimized.

Abstract: The present invention relates to the field of image processing and methodologies to construct a descriptor from binary silhouette images. The method comprises the steps of receiving a parametric equation of a closed planar curve, choosing nodes on the closed planar curve with equal intervals, generating a continuous scale space of the nodes on the curve by successively convolving the planar curve with a Gaussian filter and down-sampling it after each octave, calculating, orientation vectors and orientation angle values for each sampled point at each interval of each octave, creating a orientation scale space (OSS) which is a matrix obtained from stacking each orientation angle value on top of each other, representing the outline with a descriptor including all the orientation vectors and their respective parameters position and scale.

Abstract: Novel N-structured In As/Al Sb(Al Ga Sb)/Ga Sb based type-II SL pin detector with p on n and n on p configurations are given to detect light in the Mid Wavelength Infrared Range—MWIR with a cut-off wavelength of 5 ?m. Better carrier confinements are performed by placing AlSb layers switching from InAs layers to Ga Sb layers successively in the growth direction throughout the SL pin diode where zero bias detectivity is improved as 6×1013 A/Hz1/2 at a wavelength of 4.2 ?m at 79K. RoA value is measured as 1.8×106 ?cm2 which is better than nBn devices. Dark current density is also obtained in the range of 4-7×10?7 A/cm at zero bias and Vb=0.3V respectively at 79K.

Abstract: The present invention is related to a microwave component packaging technique which ensures that there is no space between component and pocket after inserting the component into pocket. The continuity of ground connections at the microwave gates of the components is provided just compressing the component without using electrically conductive epoxy material.

Abstract: The present invention relates to a location information acquiring system developed to be used in professional trunked radio devices, comprising a global location data organization unit (4) wherein the locations of the subscribers can be acquired one after another sending location queries to a plurality of radios at the same time, which makes channel use more efficient, which can perform global location data transmission swiftly, which is in communication with the wireless communication unit (5), and which is adapted such that it will perform location queries to a plurality of subscriber radios (2) at the same time and acquiring the location information of the said radios (2), a global location data transmission unit (8) which is adapted such that it will perform the transmission of location information when it is radio's (2) turn, and a timer (14); and a method comprising the steps of sending, receiving query, and sending location information with timing.

Abstract: A method for optimizing fiducial marker and camera positions/orientations is realized to simulate camera and fiducial positions and pose estimation algorithm to find best possible marker/camera placement comprises the steps of: acquiring mesh data representing possible camera positions and feasible orientation boundaries of cameras on the environment of tracked object; acquiring mesh data representing possible active marker positions and feasible orientation placements of markers on a tracked object; pose data representing possible poses of tracked object under working conditions; initializing the control parameter for camera placement; create initial solution strings for camera placement; solving marker placement problem for the current camera placement; evaluating the quality of the current LED and camera placement taking pose coverage, pose accuracy, number of placed markers, number of placed camera etc. into account; determining if a stopping criterion is satisfied.