• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.39-46
• /
• 2024

In this paper, we propose an efficient method for estimating the number of people and their locations using multiple IR-UWB radar sensors. Using three IR-UWB radar sensors in the indoor space, the measured signal from the target is processed to remove the clutter using rejection methods. Then, to further remove the clutter and to determine the presence of the human, the time-frequency image representing the micro-Doppler is obtained and classified by a convolutional neural network. Finally, the system finds the number of human objects and estimates each position in a two-dimensional space. In experiments using the measured data, the system successfully estimated the location and number of individuals with a high accuracy ≈ 88.68 %.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.11
• /
• pp.1013-1020
• /
• 2011

This paper deals with the tracking problem of a moving target using multiple unmanned aerial vehicles. A decentralized extended information filter is designed to cooperatively estimate the position and the velocity of the moving target. The extended information filter is adopted to consider the range and the line-of-sight angle as measurement data. The decentralized scheme is applied to enhance the estimation performance using the information provided by other vehicles. Numerical simulation is performed to verify the tracking performance of the proposed decentralized filters.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.11
• /
• pp.878-883
• /
• 2018

A jamming design scheme to disturb target position estimation of a bistatic multiple-input multiple-output(MIMO) radar system is presented. The proposed method exploits the received signals from distributed multiple electronic sensors and combines them to produce a jamming signal. The proposed algorithm can eliminate the target by transmitting the delayed sum or the weighted sum of the received senor signals. Simulation results confirm the performance of the proposed method.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.21 no.1
• /
• pp.47-60
• /
• 2018

In this paper, we proposed a method for eliminating aiming error of unguided anti-tank rocket using improved target tracking. Since predicted fire is necessary to hit moving targets with unguided rockets, a method was proposed to estimate the position and velocity of target using fire control system. However, such a method has a problem that the hit rate may be lowered due to the aiming error of the shooter. In order to solve this problem, we used an image-based target tracking method to correct error caused by the shooter. We also proposed a robust tracking method based on TLD(Tracking Learning Detection) considering characteristics of the FCS(Fire Control System) devices. To verify the performance of our proposed algorithm, we measured the target velocity using GPS and compared it with our estimation. It is proved that our method is robust to shooter's aiming error.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.10-21
• /
• 2023

For various target tracking applications, it is well known that the Kalman filter is the optimal estimator(in the minimum mean-square sense) to predict and estimate the state(position and/or velocity) of linear dynamical systems driven by Gaussian stochastic noise. In the case of nonlinear systems, Extended Kalman filter(EKF) and/or Unscented Kalman filter(UKF) are widely used, which can be viewed as approximations of the(linear) Kalman filter in the sense of the conditional expectation. However, to implement EKF and UKF, the exact dynamical model information and the statistical information of noise are still required. In this paper, we propose the recurrent neural-network based Kalman filter, where its Kalman gain is obtained via the proposed GRU-LSTM based neural-network framework that does not need the precise model information as well as the noise covariance information. By the proposed neural-network based Kalman filter, the state estimation performance is enhanced in terms of the tracking error, which is verified through various linear and nonlinear tracking problems with incomplete model and statistical covariance information.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.2_1
• /
• pp.125-137
• /
• 2020

Tracking micro-sized insects is one of the challenges of protecting ecosystems and biodiversity. In this study, we propose an approach for the autonomous tracking of micro-sized flying insects, and develop an unmanned aerial vehicle (UAV)-based robotic system. The Kalman filter is applied to the received signal strength emitted from radio telemetry to estimate the position while reducing the measurement error and noise. The autonomous tracking strategy is a method in which the UAV rotates at one point to measure the signal strength and control its position in the strongest direction of the signal. We also design a system architecture comprising a tracking sensor system and a UAV system for micro-sized insects. The estimation and autonomous tracking of the target position by the proposed system are verified and evaluated through dynamic simulation. Therefore, in this study, we propose and validate a UAV-based tracking system for micro-sized flying insects, which has not been proposed in studies conducted thus far.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.5
• /
• pp.99-110
• /
• 2017

Improving tracking performance by estimating the status of multiple targets using radar is important. In a clutter environment, a joint event occurs between the track and measurement in multiple target tracking using a tracking filter. As the number increases, the joint event increases exponentially. The problem to be considered when multiple target tracking filter design in such environments is that first, the tracking filter minimizes the rate of false track alarmsby eliminating the false track and quickly confirming the target track. The purpose is to increase the FTD performance. The second consideration is to improve the track maintenance performance by allocating each measurement to a track efficiently when an event occurs. Through two considerations, a single target tracking data association technique is extended to a multiple target tracking filter, and representative algorithms are JIPDAF and LM-IPDAF. In this study, a probabilistic evaluation of many hypotheses in the assignment of measurements was not performed, so that the computation amount does not increase nonlinearly according to the number of measurements and tracks, and the track existence probability based on the track density The LM-IPDAF algorithm was introduced. This paper also proposes a method to reduce the computational complexity by improving the clutter density estimation method for calculating the track existence probability of LM-IPDAF. The performance was verified by a comparison with the existing algorithm through simulation. As a result, it was possible to reduce the simulation processing time by approximately 20% while achieving equivalent performance on the position RMSE and Confirmed True Track.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.12
• /
• pp.265-274
• /
• 2012

In this paper, we propose a method for preceding vehicle detection and tracking with motion estimation by radar-vision sensor fusion. The motion estimation proposed results in not only correction of inaccurate lateral position error observed on a radar target, but also adaptive detection and tracking of a preceding vehicle by compensating the changes in the geometric relation between the ego-vehicle and the ground due to the driving. Furthermore, the feature-based motion estimation employed to lessen computational burden reduces the number of deployment of the vehicle validation procedure. Experimental results prove that the correction by the proposed motion estimation improves the performance of the vehicle detection and makes the tracking accurate with high temporal consistency under various road conditions.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.11
• /
• pp.881-888
• /
• 2020

In this paper, research on estimation of states of a target of interest using Line Of Sight(LOS) angle measurement is performed. Target's position, velocity, and acceleration are chosen to be the states of interests. The LOS measurement is known to be highly non-linear, making target dynamic modeling hard to be implemented into a filter. To solve this issue, the Pseudomeasurement equation was applied to the LOS measurement equation. With the help of this equation, 3D variable turn target dynamic model is applied to the filter model. For better performance, Kinematic Constraint is also implemented into the filter model. As for the filter, Bias Compensation Pseudomeasurement Filter (BCPMF) is used which is known for its robustness to initial conditions. Moreover, Two-Stage Kalman Filter (TSKF) form was also implemented to benefit from the parallel computation. As a result, TBCPMF 3DVT-KC is proposed and simulated to assess performance.

• The Journal of Korean Society for Radiation Therapy
• /
• v.11 no.1
• /
• pp.43-48
• /
• 1999

Purpose : For practical application of the MR image for stereotactic radiosurgery, the target point achieved by acquisition of MR image in a relatively homogeneous phantom has to agree with the actual isocenter of irradiation in real radiosurgery and the amount of distortion of the MR image should be known. Materials and Methods : A dosimetric film with a random target point was inserted into a radish vertically and horizontally on axis Z and they were fixed with a headring. After image acquisition by stereotactic radiosurgery planning system, we achieved stereotactic coordinate of the target point and examined irradiation using the coordinate acquired as isocenter. After the irradiation, the film in the radish was developed and processed and the degree of coincidence between the target point marked on the film and the center of the radiation distribution. In order to measure the degree of distortion of the MR image in a different way, an acryl phantom was made and punctures were made at intervals of 1 cm and a drop of oil was dropped into it. Then, it was inserted into the radish vertically and horizontally on axis Z to acquire the MR image. Each coordinate was achieved and the estimation of distortion of MR image was made both in vertical and horizontal directions Results : The film from the radio was developed and for the one inserted vertically on axis Z, there was a good coincidence in the discrepancy between the target point marked on the film and the center of the radiation distribution. For the one inserted horizontally, the discrepancy between them was under 0.5 mm. As a result of estimating distortion of MR image using acryl, the discrepancy was under 0.45 mm in the case of the phantom inserted vertically on axis Z, and that of the one inserted horizontally was 1.4 mm. Conclusion : We were able to confirm good coincidence in homogeneous phantom in actual treatment position of radiosurgery using the MR image and the discrepancy measured in the analysis of distortion of the MR image did not exceed the permissible level. Therefore, it was evident the system of the hospital is suitable for radiosurgery using MR image.