Huazhong Xu

Wuhan University of Technology, Wu-han-shih, Hubei, China

Are you Huazhong Xu?

Claim your profile

Publications (11)0.4 Total impact

  • Huazhong Xu, Fei Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we present a novel method for object tracking in surveillance scenes. We improve the 'ViBe' background subtraction algorithm by adding the scale invariant local ternary pattern operator 'SILTP' so as to detect moving shadow and increase the accuracy of segmentation. An object tracking method based on Compressive Tracking and Kalman filter by using the result of background subtraction is presented, improve the accuracy and robustness of the tracking system in surveillance scenes.
    Image and Graphics (ICIG), 2013 Seventh International Conference on; 01/2013
  • Yang Zhang, Huazhong Xu, Man Luo
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper introduces a real-time method to extract vehicles in road environment, and mainly includes four parts as follows: firstly, using Double Level background learning method to obtain a stable background image and get a rough vehicle area. Secondly, using HSV color space and texture characteristics of SILTP mixed constraint method to suppress the influence of shadow. Thirdly, using Energy Density Analysis to enhance the area-of-interest, and finally, showing some experimental results.
    Image and Graphics (ICIG), 2013 Seventh International Conference on; 01/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a real-time method to detect and track specific vehicles, toward monitoring the abnormal activities in the traffic environment. Firstly, a novel background subtraction approach is used to get the accurate foreground segmentations and shadow suppression. Then a HIK (Histogram Intersection Kernel) based SVM classifier is trained to recognize whether a vehicle is suspicious. Finally, the Camshift based tracking is used to fast track the specific vehicles. Experiments in a real traffic scenario show the promise of the proposed approach.
    ICIMCS 2011, The Third International Conference on Internet Multimedia Computing and Service, Chengdu, China, August 5-7, 2011; 01/2011
  • Huazhong Xu, Pei Lv, Lei Meng
    [Show abstract] [Hide abstract]
    ABSTRACT: Real-time people flow information is very useful for security application as well as people management. This paper presents a counting system which consists of four modules: foreground extraction, head-shoulder component detection, tracking and trajectory analysis. Firstly, in order to reduce computation costs and cope with various complex surveillance situations for foreground extraction, an adaptive components number selection strategy for mixture of Gaussians model is proposed. Secondly, pedestrians are detected by their head-shoulders, because this part is less varied and less likely occluded from a downward-slope view. Thirdly, each pedestrian is tracked through consecutive frames using the Kalman filter techniques and cost function. Finally, the resulting trajectories are analyzed to count people entering or leaving the scene. Experiment results indicate that our method can be applied in actual application.
    Computer Design and Applications (ICCDA), 2010 International Conference on; 07/2010
  • Huazhong Xu, Zilin Li
    [Show abstract] [Hide abstract]
    ABSTRACT: A Fuzzy Controller for the compensation of the Direct-axis current component in the flux-weakening control system of the Permanent Magnet Synchronous Motor (PMSM) is proposed in this paper. The output torque of PMSM falls down when it operates in the high-speed as the reason of its parameters variation. In order to minimize the influences from the armature reaction, the quadrature-axis current reference component and its deviation with the detection value are chose as the inputs of the Fuzzy controller, and output of the Direct-axis compensation value is obtained as the setting value of the current regulator. The proposed control method is implemented in the experimental platform based on TI DSP chip, the experiment results demonstrate that the Fuzzy control rules and parameters adopted in this paper can improve the performance of torque effectively.
    Computer Design and Applications (ICCDA), 2010 International Conference on; 07/2010
  • Huazhong Xu, Jie Luo, Man Luo
    [Show abstract] [Hide abstract]
    ABSTRACT: With the rapid development of economy, private cars grow at an exponential rate and cities become more and more crowded. The speed of expanding urban area and increased urban road significantly lags behind the economic development. So the introduction of advanced Intelligent Transportation Systems (ITS) may be a well solution, which can solve the urban transport problems fundamentally. As the emergence of Wireless Sensor Networks (WSN), the ITS has turned into a new epoch. But there are still a number of key technologies wanting urgent solution. If we can locate and track the cars accurately, the ITS what is build based on the WSN will become more achievable. In this paper, an improved Monte Carlo Localization box (MCB) algorithm was proposed for the location of mobile nodes in ITS, which is named Genetic MCB, and by mcl-simulation can get fairly satisfactory results.
  • Huazhong Xu, Xiaowei Luo, Chao Liang
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we have implemented a mobile personalized sports video customization system for mobile users by using a novel approach. The system is based on the B/S architecture, with this architecture, the whole system can be divided into two parts: a friendly client browser on smart phones and an intelligent multimedia analysis server. For the client browser, a friend UI is designed for mobile users to customize their favorite video clips. For the multimedia server, with the analysis of video content as well as user preference, semantics-specific video clips can be tailored to the particular users to effectively improve their visual enjoyment. The whole approach of the multimedia analysis is implemented in a two steps. First, sports video content is automatically indexed by detailed textual descriptions, which are derived from latent semantic analysis of web-casting text, based on the semantic annotation, a video database is constructed. And then video content and user preference are collaborated into event importance computation mechanism, after that the server can tailor the optimal set of video clips to the particular user. Particularly, we adopt basketball and football games as our initial sports genres because they not only widely adopted study bed but also globally popular sports, which possess great values in both research and application. Both quantitative and qualitative experiments validate the effectiveness of our system.
  • Huazhong Xu, Jun Xie
    [Show abstract] [Hide abstract]
    ABSTRACT: The permanent magnet synchronous motor (PMSM) is increasingly playing an important role in alternating current transmission system. Recently, lots of researches have been investigated for the PMSM system without speed and position sensors. A vector-control system of the improved MRAS for PMSM is proposed in this paper. The new Model Reference Adaptive System (MRAS) based on speed positive feedback can improve the performance of the system. Also, the speed and torque fluctuations are reduced. Simulation results show that the validity of the proposed strategy is more effective to estimate speed.
  • Huazhong Xu, Jinquan He, Changzhe Chen
    [Show abstract] [Hide abstract]
    ABSTRACT: A vector control strategy of PMSM based on Pan-Boolean algebra self-adapting PID control is proposed in this paper, which is unnecessary to set up the exact mathematical model of the controlled plant. According to the deviation and deviation rate at different time, it is able to eliminate the influences of the parameters of the controlled plant and the disturbance of the external environment by online adjusting the parameters of the PID controller. For the PMSM speed adjustment system, the PI controller is used in current loop and Pan-Boolean algebra self-adjusting PID controller is used in speed loop instead of traditional PI controller. The effectiveness of the proposed control method is verified by simulation based on Matlab and implemented using experimental platform based on DSP chip. The simulation and experimental results show that the performance and robustness of the controller are better than the conventional PI controller in the PMSM control system.
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a global threshold selection method to do infrared image segmentation, which uses both gray-level distribution and spatial information, namely, two-dimensional OTSU method (2D OTSU). It often gets better anti-noise performance. What's more, taking consideration of the complexity of its computation, we introduce a new heuristic optimization algorithm, called the particle swarm optimization (PSO) algorithm to search the result. So an algorithm for PSO-based 2D Otsu segmentation is proposed. The experiments of segmentation the infrared images are illustrated to show that the proposed method can get ideal segmentation result with less computation cost.
    Proceedings of SPIE - The International Society for Optical Engineering 11/2007; DOI:10.1117/12.749274 · 0.20 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a fast and robust algorithm for classification and recognition of ships based on the two-dimensional Principal Component Analysis (2DPCA) method. The three-dimensional ship models achieve by modeling software of MultiGen, and then they are projected by Vega simulating software for two-dimensional ship silhouettes. The 2DPCA method as against conventional PCA method for simulated ship recognition using training and testing experiments, as the training and testing sample size is large, and there are great variations in different azimuth and elevation for ship viewpoints. The experiment of ship recognition using the global feature of ships is not satisfied with us, so we proposed an improved 2DPCA method based on the local feature of ships. Some recognition results from simulated data are presented, it shows that the improved 2DPCA method outperform PCA in ship recognition and also superior to PCA in terms of computational efficiency for feature extraction. So our method is more preferable for ship classification and recognition.
    Proceedings of SPIE - The International Society for Optical Engineering 11/2007; DOI:10.1117/12.749331 · 0.20 Impact Factor