• Journal of Advanced Navigation Technology
• /
• v.5 no.1
• /
• pp.74-84
• /
• 2001

Recently a new algorithm which combines advantages of the IMM and IE methods has been suggested. The combined-IMM/IE algorithm could improve the performance to some extent. However, the problem of large increase of tracking error near the maneuver detection due to the sudden maneuver input has not been solved. In this paper, we propose two schemes which can resolve this limitations of combined-IMM/IE algorithm. For illustrations of the performance of the proposed methods. Monte-Carlo simulations are carried out and the results are analyzed.

• Journal of Advanced Navigation Technology
• /
• v.14 no.5
• /
• pp.618-624
• /
• 2010

This paper address the problem of tracking multiple objects encountered in many situations in developing condensation algorithms. The difficulty lies on the fact that the implementation of condensation algorithm is not easy for the general users. We propose an automatic code generation program for condensation algorithm using MATLAB tool. It will help for general user who is not familiar with condensation algorithm to apply easily for real system. The merit of this program is that a that a general industrial engineer can easily simulate the designed system and confirm the its performance on the fly.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.3
• /
• pp.315-327
• /
• 2017

In this paper, we present a method for estimating of position and velocity of a moving target by using the range and the bearing measurements from multiple sensors of aiming unit. In many cases, conventional low cost gyro sensor and a portable laser range finder(LRF) degrade the accuracy of estimation. To enhance these problems, we propose two methods. The first is background image tracking and the other is principal component analysis (PCA). The background tracking is used to assist the low cost gyro censor. And the PCA is used to cope with the problems of a portable LRF. In this paper, we prove that our method is robust with respect to low-frequency, biased and noisy inputs. We also present a comparison between our method and the extended Kalman filter(EKF).

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.150-157
• /
• 2015

Pedestrian detection has largely been researched as one of the important technologies for autonomous driving vehicle and preventing accidents. There are two categories for pedestrian detection, camera-based and LIDAR-based. LIDAR-based methods have the advantage of the wide angle of view and insensitivity of illuminance change while camera-based methods have not. However, there are several problems with 3D LIDAR, such as insufficient resolution to detect distant pedestrians and decrease in detection rate in a complex situation due to segmentation error and occlusion. In this paper, two methods using GM-PHD filter are proposed to improve the poor rates of pedestrian detection algorithms based on 3D LIDAR. First one improves detection performance and resolution of object by automatic accumulation of points in previous frames onto current objects. Second one additionally enhances the detection results by applying the GM-PHD filter which is modified in order to handle the poor situation to classified multi target. A quantitative evaluation with autonomously acquired road environment data shows the proposed methods highly increase the performance of existing pedestrian detection algorithms.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.382-385
• /
• 2007

본 논문에서는 다중 표적의 중첩이라는 상황에 대한 새로운 해결 방식을 소개한다. 비선형 표적의 위치와 속도에 대한 추적을 중심으로 표적과 비표적의 중첩이 일어나는 순간 이후 분리되었을 때 추적중인 표적을 지속적으로 유지할 수 있는 방법에 대해 이야기 하고자 한다. 이 논문에서 제안된 알고리즘은 예측 명중위치 개념과 최대 잡음수준을 이용한 칼만필터 기반의 적응 상호작용 다중모델 기법으로 측정된 위치값과 예측된 명중위치 사이의 차이를 고려한 변형된 칼만필터 개념을 이용한다. 이 논문에서는 비선형 표적의 가속도를 시변 변수인 표적의 추가적인 잡음으로 두고 각각의 가속도 간격의 정도에 따라 얻어지는 모든 잡음에 대한 변수에 의해 각각의 하부 모델들을 특성화시켰다. 제안된 알고리즘은 표적의 운동특성에 따라 적응적으로 기법을 선택할 수 있는 선택적 방식을 구현하고자 한다. 표적의 기동중에 나타나는 가속도를 효과적으로 다루기 위하여 잡음의 크기가 급격히 증가하는 경우 그 증가분을 가속도로 인식하여 기동표적 관계식에 이용한다. 그리고 제안된 알고리즘의 수행 가능성을 보여주기 위하여 몇 가지 예를 제시하였다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.4 no.1
• /
• pp.25-31
• /
• 2008

In this paper, we propose a new method that separates background and foreground from stereo images. This method can be improved automatic target tracking system by using disparity map of the stereo vision system and background-separating mask, which can be obtained camera configuration parameters. We use disparity map and camera configuration parameters to separate object from background. Disparity map is made with block matching algorithm from stereo images. A morphology filter is used to compensate disparity error that can be caused by occlusion area. We could obtain a separated object from background when the proposed method was applied to real stereo cameras system.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2011-2013
• /
• 2001

In this paper the MMAE(Multiple Model Adaptive Estimation) algorithm using the MGEKF(Modified Gain Extended Kalman Filter) of which modes are set to be measurement biases is proposed to enhance the performance of target tracking with bearing only measurements. The state are composed of relative position, relative velocity and taregt acceleration. The mode probability is calculated from the bearing only measurements from the HMS(Hull-Mounted Sonar). The proposed algorithm is tested in a series of computer simulation runs.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.39-49
• /
• 2002

This paper proposes the MAWUPC (Motion Adaptive Weighted Unmatched Pixel Count) algorithm to track multiple objects of similar color The MAWUPC algorithm has the new method that combines color and motion effectively. We apply the MAWUPC algorithm to face and hand tracking against complex background in an image sequence captured by using single camera. The MAWUPC algorithm is an improvement of previously proposed AWUPC (Adaptive weighted Unmatched Pixel Count) algorithm based on the concept of the Moving Color that combines effectively color and motion information. The proposed algorithm incorporates a color transform for enhancing a specific color, the UPC(Unmatched Pixel Count) operation for detecting motion, and the discrete Kalman filter for reflecting motion. The proposed algorithm has advantages in reducing the bad effect of occlusion among target objects and, at the same time, in rejecting static background objects that have a similar color to tracking objects's color. This paper shows the efficiency of the proposed MAWUPC algorithm by face and hands tracking experiments for several image sequences that have complex backgrounds, face-hand occlusion, and hands crossing.

• Journal of Advanced Navigation Technology
• /
• v.1 no.1
• /
• pp.35-46
• /
• 1997

Over last decade Multiple Target Tracking (MTT) has been the subject of numerous presentations and conferences [1979-1900]. Various approaches have been proposed to solve the problem. Representative works in the problem are Nearest Neighbor (NN) method based on non-probabilistic data association (DA), Multiple Hypothesis Test (MHT) and Joint Probabilistic Data Association (JPDA) as the probabilistic approaches. These techniques have their own advantages and limitations in computational requirements and in the tracking performances. In this paper, the three promising algorithms based on the NN standard filter, MHT and JPDA methods are presented and their performances against simulated multiple maneuvering targets are compared through numerical simulations.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.9
• /
• pp.741-748
• /
• 2001

In this paper, we propose a method of tracking and capturing a moving object by a mobile robot. The position of the moving object is acquired from the relation through color-based image information from a 2-DOF active camera mounted on the mobile robot. The direction and rotational angular velocity of the moving object are estimated using a state estimator. A Kalman fiber is used as the state estimator for taking characteristics of robustness against noises and uncertainties included in the input data. After estimating the trajectory of the moving object, we decide on the optimal trajectory and plan the motion of the mobile robot to capture the target object within the shortest distance and time. The effectiveness of the proposed method is demonstrated by the simulations and experiments.