The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper we propose a new solution to the problem of tracking multiple speakers from multiple microphone arrays in a reverberant acoustic environment. The acoustic environment with its complex reflection patterns with its underlying data association uncertainty pose the two most significant challenges in the multi-speaker tracking problem. We provide an approach that employs individual Time Difference...
In this paper, we propose an efficient vehicle model recognition method which utilize 3D cuboid box for detection and Convolutional Neural Networks (CNN)-based classifier. Our method automatically localizes the unique part of the vehicle as features which enhance the classification performance. The proposed method is tested on the dataset called BoxCars which contain 63,750 images with 148 categories...
The optimal sub-pattern assignment (OSPA) metric is a distance between two sets of points that jointly accounts for the dissimilarity in the number of points and the values of the points in the respective sets. The OSPA metric is often used for measuring the distance between two sets of points in Euclidean space. A common example is in multi-target filtering, where the aim is to estimate the set of...
This paper deals with multiple detection target tracking. We propose a novel algorithm to cover the many-to-one measurements-to-track association where the linear multitarget integrated track splitting algorithm is extended to accommodate for multiple detection target tracking using measurement partition method. After measurement-selection, measurement cells, where one measurement cell may contain...
A radar system for tracking ground vehicle targets to realize adaptive cruise control requires an accurate vehicle tracking filter. Especially, for ground vehicle tracking, one has to consider the case in which the radar measurements are affected by glint noises generated by the targets located near the observer vehicle. Furthermore, this vehicle tracking should be performed in cluttered environments...
Ballistic reentry target trajectory tracking is an important application of nonlinear filtering problems. Under non-Gaussian noise, Standard Particle Filter (SPF) and many revised PFs (i.e. MSRCQPF) can obtain good results. However, the two algorithms may meet some defects respectively, such as particle degradation, large computational complexity and so on. This paper propose a multimode sampling...
A non-isothermal Continuous Stirred Tank Reactor (CSTR) is the most important element of chemical industrial equipment which exhibits a highly nonlinear behavior. It is one of multi-input multi-output (MIMO) nonlinear systems affected by disturbances. The operation of the non-isothermal CSTR is disturbed by external factors such as changes in the inlet concentration and temperature. Therefore, the...
The stabilization with a General Dissipativity Constraint (GDC) has been governed by the non-negativeness of ΔV(x, k) along the trajectories (i.e. ΔV(x, k) 0), in which ΔV(x, k) 0 is a storage function. We have stated and proved the state convergence with the GDC a previous work, but the stability has not been addressed thoroughly. In this paper, we analyze the stability that is obtained from...
The paper proposes a new technique for deadlock control for a class of generalized Petri net (PN) with S4PR net, from the concept of control siphon. One important property of PN is to design structure, in terms of siphons, in order to the characterization of the deadlock prevent, and analytic structure of the synchronization subsystem which is needed to control place in a system. An efficient siphon...
With regard to the pulse width modulation (PWM) of seven-phase motor system if the three-phase space vector pulse width modulation (SVPWM) is simply extended to the seven phase motor system that is the seven phase of the traditional SVPWM it will produce a great harmonic current. In order to restrain the harmonic content of phase current the voltage vector synthesized in the 3rd harmonic subspace...
With a combination of ant system and labeled multi-Bernoulli(LMB)filter, a novel framework is proposed for the problem of simultaneous localization and mapping (SLAM). Within the proposed framework, the locations and the number of features can be jointly estimated and managed by random finite set. Besides, a real-time moving ant estimator (RMAE) is employed to estimate moving vehicle trajectory. Compared...
As a kind of common digital signal processing methods, mathematical morphology filter (MMF) has been employed to process the one dimensional sampled signals. However, because of the heavy time-consumption, it is difficult to use this method in data acquisition and processing system. Therefore, an improved MMF is proposed in this study on the basis of MMF and the process of data updating during one...
Space debris poses great challenge for the safe operation of spacecraft. This paper addresses the problem of distributed space debris tracking with consensus Labeled Multi-Bernoulli filtering. Sensor network of nodes with sensing, processing and communication capabilities is used to track space debris. Labeled Multi-Bernoulli filtering is used as the tracking filter. Data incest problem is solved...
This paper presents a novel solution to the occlusion handling problem in pedestrian tracking using labeled random finite set theory. The occlusion handling module uses motion and color cues of tracked targets to recover target labels after occlusion. An effective algorithm is also proposed for false alarm detection and removal which is designed based on tracked targets features such as, overlap ratio,...
VGG 16 and Inception-v3 networks were trained using a texture dataset of muddied and clean cows. A new dataset with 600 images that is similar to the actual texture dataset was introduced and used to train the networks. The method used to train the networks was transfer learning. ImageNet weights were trained using the similar dataset, then the newly trained weights were trained again using the actual...
Dynamics analysis of cells' movement is essential in medical research. Multiple cells tracking through fluorescence microscopy imaging is often challenged by many roadblocks including the severe image noise, adhesion among cells, and low resolution of image. To gain full dynamics of multiple cells, a novel raindrop and ripple optimization (RRO) algorithm is proposed for multiple cells tracking in...
In this paper, we consider multi-sensor with non-overlapping radar field of view in the framework of labeled random finite sets (L-RFS). In this case, a target may be simultaneously observed by some of the sensors, or even none sensor. It is different from the existing assumption of all sensors with the same fields in tracking community. We first describe the field of view by modeling the detection...
Human action recognition is a challenging research in computer vision applications because variety of human actions can be misclassified as some other action types. In this paper, we proposed a method for human action recognition based on dual tree complex wavelet transform (DTCWT). DTCWT has better edge representation and approximate shift-invariant properties compared to real-valued wavelet transforms...
We present the application of decentralized Model Predictive Control (MPC) without terminal constraints to the Automatic Generation Control (AGC) problem in power systems. A dissipation-based constraint is additionally enforced to each MPC optimization of a control area — a subsystem within an interconnected system, to assure the overall system stability. A systematic tuning procedure for the enforced...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.