Papers by Keyword: Tracking

Abstract: Internet has become an important tool to gain information; how to effectively detect hot topics from a lot of network information sources, e.g., Tibetan network, seems to be an urgent issue. Traditional hot topic is mainly based on the number of comments to get and the topic contents are usually not considered. In this letter, we study the approach of content-based relevance, i.e., based on user browsing behavior and the topic attention degree to discover the hot topic. And use the complex network theory to analyze the tracking model.

Abstract: The mathematical model of the tracking and positioning system was presented and established by analyzing the kinematics of the free pendulum system. According to the system designs requirements, a performance dedicated circuit was designed for it. The sensors, controllers, and execution units were selected. The circuit of control system was designed. A system was made for debugging and a high-performance fuzzy controller was designed. Its algorithm was based on the fuzzy control PID theory. The core of the fuzzy controller was a set of fuzzy associative memory rules that correlate each group of fuzzy control input sets to a fuzzy control output set. We finished the high precision tracking and locating system design. Through the system performance test, test results showed that the system had good performance.

Abstract: Registration and nonlinearity are two crucial factors affecting the performance of the two-station passive locating system. In this paper, an online joint registration and data fusion algorithm is proposed to estimate the sensor bias and target state simultaneously using the angle-only measurements from the two ownship stations. The system model of the passive radar is firstly developed followed by the expectation-maximization (EM) approach dealing with the derivation of maximum likelihood (ML) function of the complete data. The unscented Kalman filter (UKF) is chosen to alleviate the influence caused by nonlinearity generated in the measurement function. Computer simulation shows that the proposed method is effective and reliable for this specific tracking scenario.

Abstract: We need to track and detect all kinds of business when we prepare to have a test on the network in the Mobile Digital Multimedia Broadcasting System. This paper raise a way can parallelly test all the physical parameters such as RSSI, multipath, constellation diagram, BER and SNR of the service time slot of every frame in CMMB system by making a research on the traditional way of multiple services tracking and parallelly testing in CMMB system.On the basis of traditional way, we increase parity service discriminant moduleodd service parameters test module and even service parameters test module and make reasonable control scheme that odd service parameters test module and even service parameters test module test and receive the input data alternately in time ,that is to say, they independently make internal data processing, which making a good solution to the problems that the occupation of the system resource and insufficient data processing time.

Abstract: Automation boosts competitiveness of manufacturing companies and is pervasive in modern industry. However, skilled manual labour is still used in a variety of complex tasks and is currently irreplaceable. A solution may lie in understanding the interactions between a human worker and the workpiece during a manufacturing task and digitising these interactions to potentially enable automation of the task. In this paper, a method to observe, record and digitise human-workpiece interactions using the Microsoft Kinect^TM is described. A manual threaded-fit assembly of a two-component pen housing is chosen. Essential information about the manual assembly is extracted from the recorded interaction data. The developed mechanism being markerless and unobtrusive is helpful in recording human-workpiece interactions in a factory without affecting normal operations.

Abstract: Magnetic ellipsoid tracking problem is characterized by high nonlinearity. In this study, the determination of target position, magnetic moment, and velocity is formulated as a Bayesian estimation problem for dynamic systems, a recursive approach is proposed to estimate the trajectory and magnetic moment component of the target using data collected with a magnetic gradiometer tensor. Particle filter provides a solution to this problem. In addition to the conventional particle filter, the proposed tracking and classification algorithm uses Gaussian mixed mode to represent the posterior state density of the unknown parameters, which is named as Gaussian mixture sigma point particle filters(GMSPPF). The performance of the proposed method has been evaluated through simulation experiment. The results indicate that the method has achieved the magnetic ellipsoid tracking and GMSPPF has better estimation performance and less computational complexity than other related algorithms.

Abstract: We develop a robust tracking method based on the structural local sparse representation and incremental subspace learning. This representation exploits both partial information and spatial information of the target. The similarity obtained by pooling across the local patches helps locate the target more accurately. In addition, we develop a template update method which combines incremental subspace learning and sparse representation. This strategy adapts the template to the appearance change of the target with less drifting and reduces the influence of the occluded target template as well. Experiments on challenging sequences with evaluation of the state-of-the-art methods show effectiveness of the proposed algorithm.

Abstract: In this paper an imaging system for bus traffic conflict investigation is presented. The system employs geo-referenced stereo sequences and tracking procedure to provide much greater information regarding pre-crash and crash events than what is currently available. The exploitation of the traffic conflict technique potentiality as a surrogate safety measure could constitute an effective tool in understanding how the driver interacts and adapts its behavior with respect to the vehicle, the road characteristics, the traffic control devices and the environment. Experiments performed on real data acquired in urban context confirm the effectiveness of the system for the traffic conflicts measurement and the driver behavior analysis.

Abstract: The software design ideas of smart car tracking with camera are described. The following modules are discussed: the main function structure, the initialization of each module, road information collecting module, road information processing module, servo control module and motor control module. The repeated debugging and the real operation of the smart car show that it can accurately collect the road information, control flexibly, run stably, and its velocity reaches 2.2m/s.

Abstract: The Cramer-Rao Lower Bound (CRLB) for the location accuracy of the netted radar is explored and the CRLB for the nonlinear filtering of a single radar is derived. The calculation process of the CRLB for the location accuracy of the netted radar is given by combining the above results. Simulation tests for the location and tracking accuracy of the netted radar under different conditions are conducted and several factors affecting the tracking accuracy of the netted radar are analyzed. The theoretical achievement derived in this paper can be used as a key theoretical basis for the evaluation of the performance of the netted radar.