Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Target Tracking Based on Mean Shift and KALMAN Filter with Kernel Histogram Filtering  [cached]
Sara Qazvini Abhari,Towhid Zargar Ershadi
Computer and Information Science , 2011, DOI: 10.5539/cis.v4n2p152
Abstract: Visual object tracking is required in many tasks such as video compression, surveillance, automated video analysis, etc. mean shift algorithm is one of popular methods to this task and has some advantages comparing to other tracking methods. This method would not be appropriate in the case of large target appearance changes and occlusion; therefore target model update could actually improve this method. KALMAN filter is a suitable approach to handle model update. We performed mean shift algorithm with model update ability for tracking in this paper and achieve good results.
Kernel Spatial Histogram Target Tracking Based on Template Drift Correction

WANG Yong,CHEN Fen-Xiong,GUO Hong-Xiang,

自动化学报 , 2012,
Abstract: Aiming at the limitations of the traditional mean shift, such as invariable kernel bandwidth, inadequate color distribution representation of target and the accumulative tracking errors, an improved tracking algorithm with the following strategies is proposed. The target model and the candidate are described by a modified second-order spatial histogram including color and spatial information, and the similarity between them is evaluated by Bhattacharyya coefficient. According to the target region parameter resulted from template drift correction which can eliminate the tracking errors, the target model can be estimated repeatedly. The tracking region parameters are updated through an affine transform combining corner detection and edge detection. Besides, the target motion is predicted by either Kalman filter or linear filter according to the Kalman residual error. Experimental results show that the proposed algorithm is robust against similarity distraction, scale and orientation variations and short-term occlusion.
A new improved filter for target tracking: compressed iterative particle filter  [PDF]
Hongbo Zhu, Hai Zhao, Dan Liu, Chunhe Song
Natural Science (NS) , 2011, DOI: 10.4236/ns.2011.34039
Abstract: Target tracking in video is a hot topic in computer vision field, which has wide applications in surveillance, robot navigation and human-machine interaction etc. Meanshift is widely used algorithm in video target tracking field. The basic mean shift algorithm only considers the color of targets as the tracking characteris- tic feature, so if the appearance of the target changes greatly or there exits other objects whose color is similar to the target, the tracking process will fail. To enhance the stability and robustness of the algorithm, we introduce par- ticle filter into the tracking process. Basic particle filter has some disadvantages such as low accuracy, high computational complexity. In this paper, an improved particle filter GA-UPF was proposed, in which a new re-sampling algorithm was used to predict target centroid position. The target tracking system of binocular stereo vision is designed and implemented. Experi- mental results have shown that our algorithm can tracking object in video with high accuracy and low computational complexity.
Some Aspects on Filter Design for Target Tracking
Bertil Ekstrand
Journal of Control Science and Engineering , 2012, DOI: 10.1155/2012/870890
Abstract: Tracking filter design is discussed. It is argued that the basis of the present stochastic paradigm is questionable. White process noise is not adequate as a model for target manoeuvring, stochastic least-square optimality is not relevant or required in practice, the fact that requirements are necessary for design is ignored, and root mean square (RMS) errors are insufficient as performance measure. It is argued that there is no process noise and that the covariance of the assumed process noise contains the design parameters. Focus is on the basic tracking filter, the Kalman filter, which is convenient for clarity and simplicity, but the arguments and conclusions are relevant in general. For design the possibility of an observer transfer function approach is pointed out. The issues can also be considered as a consequence of the fact that there is a difference between estimation and design. The - filter is used for illustration.
Distributed Particle Filter for Target Tracking in Sensor Networks
Hong-Qing Liu;Hing-Cheung So;Frankie Kit Wing Chan;Kenneth Wing Kin Lui
PIER C , 2009, DOI: 10.2528/PIERC09092905
Abstract: In this paper, we present a distributed particle filter (DPF) for target tracking in a sensor network. The proposed DPF consists of two major steps. First, particle compression based on support vector machine is performed to reduce the cost of transmission among sensors. Second, each sensor fuses the compressed information from its neighboring nodes with use of consensus or gossip algorithm to estimate the target track. Computer simulations are included to verify the effectiveness of the proposed approach.
An Improved Particle Filter for Target Tracking in Sensor Systems  [PDF]
Xue Wang,Sheng Wang,Jun-Jie Ma
Sensors , 2007, DOI: 10.3390/s7010144
Abstract: Sensor systems are not always equipped with the ability to track targets. Sudden maneuvers of a target can have a great impact on the sensor system, which will increase the miss rate and rate of false target detection. The use of the generic particle filter (PF) algorithm is well known for target tracking, but it can not overcome the degeneracy of particles and cumulation of estimation errors. In this paper, we propose an improved PF algorithm called PF-RBF. This algorithm uses the radial-basis function network (RBFN) in the sampling step for dynamically constructing the process model from observations and updating the value of each particle. With the RBFN sampling step, PF-RBF can give an accurate proposal distribution and maintain the convergence of a sensor system. Simulation results verify that PF-RBF performs better than the Unscented Kalman Filter (UKF), PF and Unscented Particle Filter (UPF) in both robustness and accuracy whether the observation model used for the sensor system is linear or nonlinear. Moreover, the intrinsic property of PF-RBF determines that, when the particle number exceeds a certain amount, the execution time of PF-RBF is less than UPF. This makes PF-RBF a better candidate for the sensor systems which need many particles for target tracking.
H-Infinity Filter Based Particle Filter for Maneuvering Target Tracking
Qicong Wang;Jing Li;Meixiang Zhang;Chenhui Yang
PIER B , 2011, DOI: 10.2528/PIERB11031504
Abstract: In this paper, we propose a novel H-infinity filter based particle filter (H∞PF), which incorporates the H-infinity filter (H∞F) algorithm into the particle filter (PF). The basic idea of the H∞PF is that new particles are sampled by the H∞F algorithm. Since the H∞F algorithm can fully take into account the current measurements, when the new algorithm calculates the proposed probability density distribution, the sampling particles can take advantage of the system current measurements to predict the system state. The particles distribution we obtained approaches nearer to the state posterior probability distribution and the H∞PF alleviates the sample degeneracy problem which is common in the PF, especially when the maneuvers of the target tracking are large. Furthermore, the H∞F algorithm can adjust gain imbalance factor by adjusting disturbance decay factor, from that the new algorithm can get the compromise between the accuracy and robustness and we can obtain satisfied accuracy and robustness. Some simulations and experimental results show that the proposed particle filter performed better than the PF and the Kalman particle filter (KPF) in tracking maneuvering target.
Study on Multi-Target Tracking Based on Particle Filter Algorithm  [cached]
Junying Meng,Jiaomin Liu,Yongzheng Li,Juan Wang
Research Journal of Applied Sciences, Engineering and Technology , 2013,
Abstract: Particle filter is a probability estimation method based on Bayesian framework and it has unique advantage to describe the target tracking non-linear and non-Gaussian. In this study, firstly, analyses the particle degeneracy and sample impoverishment in particle filter multi-target tracking algorithm and secondly, it applies Markov Chain Monte Carlo (MCMC) method to improve re-sampling process and enhance performance of particle filter algorithm.
Fuzzy-Control-Based Particle Filter for Maneuvering Target Tracking
Xianfeng Wang;Jun-Feng Chen;Zhi-Guo Shi;Kang Sheng Chen
PIER , 2011, DOI: 10.2528/PIER11051907
Abstract: In this paper, we propose a novel fuzzy-control-based particle filter (FCPF) for maneuvering target tracking, which combines the advantages of standard particle filter (SPF) and multiple model particle filter (MMPF). That is, the SPF is adopted during non-maneuvering movement while the MMPF is adopted during maneuvering movement. The key point of the FCPF is to use a fuzzy controller, which could imitate the thoughts of human beings in some degree, to detect the target's maneuver and use a backward correction sub-algorithm to alleviate the performance degradation of MMPF caused by detection delay. Simulation results indicate that the proposed algorithm has a much better tracking accuracy than the SPF while keeps approximately equal computational complexity. Compared with MMPF, both algorithms have no tracking lost, but the tracking accuracy of the proposed FCPF is a little better than the MMPF, and the FCPF consumes about 66% computation time of the MMPF. Thus, the proposed algorithm offers a more effective way for maneuvering target tracking.
Optimal Particle Filter Object Tracking Algorithm Based on Features Fusion and Clustering Kernel Function Smooth Sampling

计算机科学 , 2012,
Abstract: An improved particle filter object tracking algorithm was proposed to solve object tracking problems in com- plex scene. hhis paper used united histogram to describe target grayscale and gradient direction features imformation, and designed a self-adaptive features fusion observation model to adapt the changing scene. To solve particles degeneracy problem of basic particle filter, a resampling method based on clustering kernel function smooth was proposed. hhe ex- perimental results based on simulation and the actual scenes show that this algorithm is more adaptable and possesses higher accuracy, can track the moving object in complex scene effectively.
Page 1 /100
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.