• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2094-2112
• /
• 2019

Focusing on the issue that the conventional Kernel Correlation Filter (KCF) algorithm has poor performance in handling scale change and obscured objects, this paper proposes an anti-occlusion and scale adaptive tracking algorithm in the basis of KCF. The average Peak-to Correlation Energy and the peak value of correlation filtering response are used as the confidence indexes to determine whether the target is obscured. In the case of non-occlusion, we modify the searching scheme of the KCF. Instead of searching for a target with a fixed sample size, we search for the target area with multiple scales and then resize it into the sample size to compare with the learnt model. The scale factor with the maximum filter response is the best target scaling and is updated as the optimal scale for the following tracking. Once occlusion is detected, the model updating and scale updating are stopped. Experiments have been conducted on the OTB benchmark video sequences for compassion with other state-of-the-art tracking methods. The results demonstrate the proposed method can effectively improve the tracking success rate and the accuracy in the cases of scale change and occlusion, and meanwhile ensure a real-time performance.

• 드라이브 ㆍ 컨트롤
• /
• 제16권2호
• /
• pp.22-29
• /
• 2019

This study presented a model predictive tracking control algorithm of autonomous truck based on object state estimation using extended Kalman filter. To design the model, the 1-layer laser scanner was used to estimate position and velocity of the object using extended Kalman filter. Based on these estimations, the desired linear path for object tracking was computed. The lateral and yaw angle errors were computed using the computed linear path and relative positions of the truck. The computed errors were used in the model predictive control algorithm to compute the optimal steering angle for object tracking. The performance evaluation was conducted on Matlab/Simulink environments using planar truck model and actual point data obtained from laser scanner. The evaluation results showed that the tracking control algorithm developed in this study can track the object reasonably based on the model predictive control algorithm based on the estimated states.

• 한국항행학회논문지
• /
• 제7권2호
• /
• pp.217-226
• /
• 2003

근래에 Poisson 형의 점프 프로세스를 이용하여 표적의 기동 운동을 모델링하고 이것을 이용한 반복형 최소 분산 선형 필터가 제안되었다. 이 필터에서는 기동 표적의 모델링에 사용한 점프의 상태천이 파라미터가 미리부터 필터에 알려져 있다고 가정하였는데 실제는 이것을 모르는 경우가 많다. 본 논문에서는 이러한 기동 추적과정에 수반되는 모델링 오류가 제안된 추적필터의 성능에 어떤 영향을 미치는지 고려한다. 정성적인 분석을 위해서 상태천이 파라미터를 실제와 다른 값을 사용하고, Monte-Carlo 시뮬레이션을 통해 필터의 성능을 해석한다.

• 한국항공우주학회지
• /
• 제39권11호
• /
• pp.1013-1020
• /
• 2011

본 논문에서는 이동 목표물을 추적하기 위하여, 다수 무인항공기의 측정치를 이용한 목표물의 위치와 속도 추정기법을 제안하였다. 항공기와 목표물 사이의 상대거리와 시선각 정보를 이용하여 목표물의 위치, 속도 성분을 추정하는 확장필터를 구성하였다. 다수의 항공기 간 정보교환과 계산이 용이하도록 공분산 역행렬 형태의 정보필터를 설계하였다. 개별 확장필터, 부분 분산형 확장필터, 분산형 확장필터를 이용한 수치 시뮬레이션을 수행하여, 제안된 분산형 확장필터의 이동 목표물 추정 및 추적 성능을 검증하였다.

• 제어로봇시스템학회논문지
• /
• 제18권7호
• /
• pp.673-679
• /
• 2012

This paper introduces robust tracking algorithm for fast and erratic moving object. CAMSHIFT algorithm has less computation and efficient performance for object tracking. However, the method fails to track a object if it moves out of search window by fast velocity and/or large movement. The size of the search window in CAMSHIFT algorithm should be selected manually also. To solve these problems, we propose an efficient prediction technique for fast movement of object using Kalman Filter with automatic initial setting and variable configuration technique for search window. The proposed method is compared to the traditional CAMSHIFT algorithm for searching and tracking performance of objects on test image frames.

• 전기학회논문지
• /
• 제61권2호
• /
• pp.284-290
• /
• 2012

This paper addresses a new passive target tracking problem using the range differences measured by cooperative UAVs. In order to solve the range difference based passive target tracking problem within the framework of linear robust state estimation, the uncertain linear measurement model which contains the stochastic parameter uncertainty is derived by using the noisy range difference measurements. To cope with the performance degradation due to the stochastic parameter uncertainty, the recently developed non-conservative robust Kalman filtering technique [1] is applied. For the cruciform formation flying UAVs, the relationship between the target tracking performance and the measurement errors is quantitatively analyzed. The proposed filter has practical advantages over the classical nonlinear filters because, for its recursive linear structure, it can provide satisfactory convergence properties and is suitable for real-time multiple UAVs applications. Through the simulations, the usefulness of the proposed method is demonstrated.

• 한국컴퓨터정보학회논문지
• /
• 제22권7호
• /
• pp.47-54
• /
• 2017

Recently, correlation filter based trackers have shown excellent tracking performance and computational efficiency. In order to enhance tracking performance in the correlation filter based tracker, search area which is image patch for finding target must include target. In this paper, two methods to discriminatively represent target in the search area are proposed. Firstly, search area location is estimated using pyramidal Lucas-Kanade algorithm. By estimating search area location before filtering, fast motion target can be included in the search area. Secondly, we investigate multi-channel Local Edge Pattern(LEP) which is insensitive to illumination and noise variation. Qualitative and quantitative experiments are performed with eight dataset, which includes ground truth. In comparison with method without search area estimation, our approach retain tracking for the fast motion target. Additionally, the proposed multi-channel LEP improves discriminative performance compare to existing features.

• 제어로봇시스템학회논문지
• /
• 제16권2호
• /
• pp.177-187
• /
• 2010

A MTG (Multimode Tracking and Guidance) system is employed to compensate for the limitations of individual seekers such as RF (Radio frequency) or IIR (Imaging Infra-red) and to improve the overall tracking and guidance performance in jamming, clutter, and adverse weather environments. In the MTG system, tracking filter, data association, and data fusion methods are important elements to maximize the effectiveness of precision homing missile guidance. This paper proposes the formulation of a Kalman filter for the estimation of line-of-sight rate from seeker measurements in missiles guided by proportional navigation. Also, we suggest the HPDA (Highest Probability Data Association) and data fusion methods of the MTG system for target tracking in the adverse environments. Mont-Carlo simulation is employed to evaluate the overall tracking performance and guidance accuracy.

• 스마트미디어저널
• /
• 제5권1호
• /
• pp.78-87
• /
• 2016

The major problems of recent object tracking methods are related to the inefficient detection of moving objects due to occlusions, noisy background and inconsistent body motion. This paper presents a robust method for the detection and tracking of a moving in infrared animal videos. The tracking system is based on adaptive optical flow generation, Gaussian mixture and Kalman filtering. The adaptive Gaussian model of optical flow (GMOF) is used to extract foreground and noises are removed based on the object motion. Kalman filter enables the prediction of the object position in the presence of partial occlusions, and changes the size of the animal detected automatically along the image sequence. The presented method is evaluated in various environments of unstable background because of winds, and illuminations changes. The results show that our approach is more robust to background noises and performs better than previous methods.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권8호
• /
• pp.883-887
• /
• 2010

3D 얼굴 추적(Face tracking)은 보안감시, HCI(Human-Computer Interface), 엔터테인먼트(Entertainment)등 컴퓨터 비전과 관련된 여러 분야의 핵심 기술로서 많은 연구가 진행되고 있다. 하지만, 광범위한 응용분야에도 불구하고 3D 얼굴 추적의 기본적인 높은 연산 비용으로 인하여 그 응용 분야가 모바일 단말기 등의 저 사양 플랫폼에는 많은 한계가 있어왔다. 본 논문에서는 이러한 3D얼굴 추적의 연산 비용을 효과적으로 해결하고 폭 넓게 응용 분야를 확대하기 위하여 MLESAC(Maximum Likelihood Estimation by Sampling Consensus)을 이용한 움직임 추정(Motion Estimation) 기법과 기존의 파티클 필터(Particle Filter)를 결합하여 실행 속도 면에서 빠르면서도 성능 면에서도 우수한 3D 얼굴 추적 알고리즘을 제안한다.