Multi-target tracking is considered to be a significant issue in various areas of monitoring, supervision, and updated communication services. It is a logical, generalized, single-target tracking problem. Therefore, it is of paramount importance to apply filters to meas More
Multi-target tracking is considered to be a significant issue in various areas of monitoring, supervision, and updated communication services. It is a logical, generalized, single-target tracking problem. Therefore, it is of paramount importance to apply filters to measure the direction or relative distance of the target from the viewer. Not showing the position of the sensor is the functional advantage of such sensors. One of the main issues in tracking is the dependence of estimation accuracy on the moving path of the viewer when the sensor only measures the direction of the target. With this background in mind, it is essential to estimate the position of the target. The present study aimed to determine the optimal path of the viewer in the tracking of two moving targets in order to improve the tracking performance. Target tracking was performed by a viewer only by measuring the direction of the target toward the viewer. Initially, the viewer path was introduced as a mathematical profile, and its coefficients were determined using an optimization algorithm, which demonstrated the lowest error rate in target tracking using the Kalman filter as an optimal estimator. Afterwards, another path was introduced, which was developed based on the estimates obtained by two Kalman filters, followed by the unscented Kalman filter. At the final stage, the most efficient method to continue the desired viewer path was proposed based on the comparison of the two methods, and the results of the optimization path were obtained using a multi-objective genetic algorithm.
Manuscript profile
Nowadays, the wireless sensor network (WSN) is used in many different fields and applications. Enemy tracking and wildlife habitats monitoring are the examples of target tracking by using of large number of sensor nodes. The main idea in this area is to find some usable More
Nowadays, the wireless sensor network (WSN) is used in many different fields and applications. Enemy tracking and wildlife habitats monitoring are the examples of target tracking by using of large number of sensor nodes. The main idea in this area is to find some usable target information such as location, speed and movement direction of the target because they must be available any time. By the way, the sensor nodes in sensor network model have a severe energy limit and cannot be recharged simply. In this paper, an efficient algorithm abbreviated EAASA is presented in order to reduce energy consumption while maintaining the quality of target tracking. The simulation results are compared to the AASA (cluster-based target tracking algorithm) algorithm and show that the proposed algorithm has been able to reduce energy consumption significantly while maintaining tracking quality. This method has increased the life time of the network and reduced the rate of loss of the target.
Manuscript profile
The conventional Tracking-Learning-Detection (TLD) algorithm is sensitive to illumination change and clutter and low frame rate and results in drift even missing. To overcome these shortcomings and increase robustness, by improving the TLD structure via integr More
The conventional Tracking-Learning-Detection (TLD) algorithm is sensitive to illumination change and clutter and low frame rate and results in drift even missing. To overcome these shortcomings and increase robustness, by improving the TLD structure via integrating mean-shift and co-training learning can be achieved better results undergo low frame rate (LFR) condition and the robustness and accuracy tracking of the TLD structure increases. Because of, the Mean-Shift tracking algorithm is robust to rotation, partial occlusion and scale changing and it is simple to implement and takes less computational time. On the other, the co-training learning algorithm with two independent classifiers can learn changes of the target features in during the online tracking process. Therefore, the extended structure can solve the problem of lost object tracking in LFR videos and other challenges simultaneously. Finally, comparative evaluations of the proposed method to other top state-of-the-art tracking algorithms under the various scenarios from the TB-100 known dataset, demonstrate the superior performance of the proposed algorithm compared to other tracking algorithms in terms of tracking robustness and stability performance. Finally, the proposed structure based on the TLD architecture, in scenarios with the various challenges mentioned, will improve on average about 33% of the results, compared to the traditional TLD algorithm.
Manuscript profile
Sanad
Sanad is a platform for managing Azad University publications
