Papers by Keyword: Target Tracking

Paper TitlePage

Authors: Yan Bin Han, Geng Shi Zhang, Jin Ping Li
Abstract: In this paper, a feature extraction strategy based on multiple color information fusion was proposed. Firstly this method started with analyzing the transform formula of color space, which transform was mainly thinking about RGB color space to other color spaces. Secondly by analyzing the characteristic of every color space in describing the actual color information, the advantages and disadvantages of every color space were showed. Thirdly through above conclusion, the algorithm which extracted the target feature only using single color information was defective, and then the strategy based on multiple color information fusion was proposed. Lastly the detail fusion strategy was given, which fused the probability distributed information of multiple color into the last probability distributed information as the target feature. The feature extraction strategy in this paper is verified by the camshift algorithm. The results show that the multiple color information fusion can improve the tracking performance of moving target.
Authors: Ning Wang, Hong Wei Quan, Xiu Yin Xue
Abstract: The acoustic sensor networking is an important research topic in multi-sensor target tracking system. An acoustic sensor network consists of multiple acoustic sensors which are located in fixed positions with specific deployment mode. It can improve the robustness and fault-tolerance of the target tracking system, especially when a single or few sensors do not work normally with some faults. This paper discusses the acoustic sensor detection model and gives a method to sensor deployment for target detection in target tracking system.
Authors: Hong Wei Quan, Dong Liang Peng, An Ke Xue
Abstract: A new algorithm for tracking a maneuvering target in presence of clutter or false measurements is addressed. Due to the availability of feature or attribute information in measurement vector, a joint probability density function description of the target state and target class is given. Using the joint state-class description the predictive measurement pdf can be proven to be a Gaussian mixture distribution. A Gaussian mixture Kalman filter is used for state estimation, where maneuver detection can also be avoided. In simulation the results with three tracking algorithms are compared, which have shown that proposed method here is more effective.
Authors: Ming Li, Chao Chen
Abstract: The Mean-Shift algorithm has very good tracking effect when the background is in a simple; but for a complex environment, tracking effect is not very ideal. Therefore, a new gray feature modeling method is proposed in this paper. Firstly, target in the tracking window is uniformly divided into even pieces. Then the pixel gray value of each block is calculated with subtraction of certain rules. Finally, the gray value of gray difference and the whole object value fusion are fused and established the object model. The object model that established not only contains the whole gray value information, but also contains the gray value differences between regions, has a more accurate description of the target, and then distinguish target from background better. The experiment results show that: the target model using the method in this paper to track based on the Mean-Shift algorithm, has good adaptability when the target is partially occluded and has better robustness for complex background.
Authors: Yan Li Zhao, Hua Bing Wang, Xiang Dong Gao, Ying Zhou, Yong Hu Zeng
Abstract: In order to improve the tracking accuracy of the synchronous radar network under blanket jamming with less computation, a new target tracking algorithm based on the optimal linearization is proposed. Firstly, the optimal linearization algorithm for the measurement equation is analyzed. Then the optimal estimation of the position is derived in 2D space according to the bearing angle measurements, and then the estimation is expanded to 3D space in accordance with the pitch angle measurements. Finally, the tracking algorithm for the moving target is presented and simulation testing is conducted. The simulation results show the tracking algorithm without iteration proposed by this paper can make it possible for the radar network under blanket jamming to track the target precisely.
Authors: Hui Zhong Zhuang, Han Li
Abstract: A novel approach to video detection, synchronous detection lines method, is firstly proposed in this paper. It is actually a way to divide the pixel sets of the video images. Then, an algorithm of three-layer probability model based on synchronous detection lines is presented to solve the problems of background updating and target tracking. The results of a practical system show that this approach has better effect to solve the problems of background updating and target tracking.
Authors: Bing Wang, Hao Zhang, Hua Dong Meng
Abstract: In this paper, a novel adaptive waveform selection method is proposed for radar target tracking. In order to minimize the target state estimation MSE (Mean Square Error) on each tracking step, we adjust the PRI (Pulse Recurrence Interval) and pulse width of the emission signal with the constraint of average power. In this method, the position measurement CRLB (Cramer-Rao Lower Bound) is used to define the observation noise power, and then the relationship between the tracking performance and the waveform parameters is established to decide the optimal PRI. Simulations show that this method can improve the tracking accuracy effectively and dynamically.
Authors: Xiao Mei Gong
Abstract: Consider out of sequence measurement (oosm) estimation problem in central tracking system of multi-sensor distributed data fusion, which is due to the communication delay. Apply the particle filter algorithm to overcome this problem and propose a update algorithm for the case of an arbitrary (multi-step) lag in case of nonlinear. Then we compare this algorithm with the known EKF oosm algorithm. Results demonstrate the feasibility and effectiveness of this algorithm.
Authors: Ling Zhao, Jing Zhi Ye, Wen Feng Luo
Abstract: In this paper, a real-time location feedback control system based on multi-sensor network is proposed for the precise control of a moving robot. The target tracking network system is a real test-bed that consists of a group of ultrasonic sensor nodes, a mobile robot and two laptops. In order to pursue excellent tracking performance and modify the robot’s trajectory promptly, Extended Kalman Filtering algorithm as well as a kind of scheduling scheme based on location is applied in the system. The experiment result validates the correctness of the Extended Kalman Filter (EKF) and shows that the target tracking network system is effective for robot feedback control.
Authors: Ai Xia Wang, Peng Wu, Jing Jiao Li, Ai Yun Yan
Abstract: This paper presented a high real time target tracking algorithm – mixed difference tracking algorithm MDT. In the proposed algorithm, frame difference and background difference algorithms are combined to get the location of the target. With background difference algorithm the shape of the target can be extracted. Due to the affection of the dynamic background, single background difference algorithm can not get the location of the moving target. To solve this issue the frame difference algorithm is used to estimate the location, and then combine the results of the background difference algorithm and the frame difference algorithm the location and the size of the target can be extracted. And then filtering algorithm is used to remove noise and isolated points. In the experiment it can be seen that the proposed algorithm can tracking object precisely in real time.
Showing 1 to 10 of 111 Paper Titles