• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.5
• /
• pp.63-71
• /
• 2008

In this paper, we propose a color based hierarchically propagated particle filter that extends the color based particle filter into the articulated upper body tracking. Since color feature is robust to partial occlusion and rotation, the color based particle filter is widely used for object tracking. However, in articulated body tacking, it is not desirable to use the traditional particle filter because the dimension of the state vector usually is high and thus, many samples are required for robust hacking. To overcome this problem, we use a hierarchical tracking method for each body part based on the blown body part. By using a hierarchical tracking method, we can reduce the number of samples for robust tracking in the cluttered environment. Also for human pose recognition, we classify the human pose into eight categories using Support Vector Machine(SVM) according to the angle between upper- arm and fore-arm. Experimental results show that our proposed method is more efficient than the traditional particle filter.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.4B
• /
• pp.491-504
• /
• 2001

본 논문은 고정된 카메라를 통해 들어오는 도로연상에서 추적되는 다중 차량들의 겹침(occlusion)발생시 칼만 필터와 차량의 특징정보를 이용하여 개별 차량을 분할하고 추적 가능한 시스템을 제안하고 구현하였다. 다중 차량을 추적할 시 가장 큰 문제점이 되고 있는 차량 겹침을 해결하기 위해 카메라와의 거리를 이용하여 해결하는 방법 3D 모델을 이용하여 해결하는 방법, 겹침 추론 등 차량 겹침을 해결하기 위한 여러 가지 방법들이 제시되고 있다. 그러나 영상에 연속적으로 나타나는 다중 차량의 겹침을 단일 차량으로 인식할 수 는 단점이 있다. 따라서 칼만 필터와 차량의 특징 정보로서 차량의 높이와 넓이의 비, 추적에 사용되는 박스에서 차량과 여백의 비를 이용함으로서 연속적으로 나타날 수 있는 차량 겹침을 분할하고 추적 가능하게 하는 시스템을 구현하고 실험하였다. 본 시스템에서는 256X 256의 크기로 15 frames/sec로 저장된 AVI 파일 형식의 동영상을 사용하여 실험에 이용하였으며, 시내 도로에서의 차량들의 실험 결과 기존의 방법 보다 차량 특징 정보를 이용한 방법이 연속적 겹침에 대한 처리에 우수함을 보였다.

• Smart Media Journal
• /
• v.13 no.5
• /
• pp.9-18
• /
• 2024

Multi-Object trajectory modeling is a major challenge in MOT. CenterTrack tried to solve this problem with a Heatmap-based method that tracks the object center position. However, it showed limited performance when tracking objects with complex movements and nonlinearities. Considering the degradation factor of CenterTrack as the dynamic movement of pedestrians, we integrated the EKF into CenterTrack. To demonstrate the superiority of our proposed method, we applied the existing KF and UKF to CenterTrack and compared and evaluated it on various datasets. The experimental results confirmed that when EKF was integrated into CenterTrack, it achieved 73.7% MOTA, making it the most suitable filter for CenterTrack.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2338-2340
• /
• 2004

탐지레이다 또는 TWS 레이다의 측정 정밀도는 추적 필터 설계에서 quantization 문제로써 고려해야 한다. 본 논문에서는 측정 정밀도가 추적필터에서 quantization 문제로 변환됨을 보이고 오차면적과 추정성능을 비교한다. 또한 오차면적을 줄이는 방안과 quantization이 존재하면 측정잡음과 관계한 공정잡음의 power spectral density를 선정함을 보인다.

• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.141-144
• /
• 2009

인터넷에 게시된 글(블로그, 포털 사이트, 게시판 등)에 대한 댓글들 중에서 중복, 광고 등의 스팸성 댓글을 추적하고 이를 필터링 하는 시스템을 개발.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.154-157
• /
• 2000

In this paper, we propose a method for vehicle tracking systems using fuzzy logic. The standard ${\alpha}$-${\beta}$ filter estimates the future target positions using fixed ${\alpha}$,${\beta}$ coefficients. We utilize the if-then fuzzy logic to make ${\alpha}$ and ${\beta}$ coefficients vary with the position. Comparisons are made in tracking vehicles using three different schemes: the standard ${\alpha}$-${\beta}$ filter, ${\alpha}$-${\beta}$ filter using fuzzy logic, and the Kalman filter.

• Journal of Advanced Navigation Technology
• /
• v.19 no.2
• /
• pp.123-132
• /
• 2015

Among various fields of the CNS/ATM, the surveillance field which includes ADS-B system, MLAT system, and WAM system is implemented. These next generation systems provide superior performance in tracking aircrafts. However, They still have error. In this paper, filtering algorithm is proposed in order to enhance aircraft tracking performance of ADS-B, MLAT, and WAM systems. The proposed method is a Robust Interacting Multiple Model filter, called Robust IMM filter, that improves IMM filter. The Robust IMM filter can not only improves the aircraft tracking performance but also track aircraft continually using estimates calculated from the filter when data losses occur. The simulation results of the proposed aircraft tracking methods show that the filtering data provides a better performance up to an average of 19.21%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.5
• /
• pp.539-544
• /
• 2004

We investigate a visual object tracking algorithm based upon particle filters, namely CONDENSATION, in order to combine multiple observation models such as active contours of digitally subtracted image and the particle measurement of object color. The former is applied to matching the contour of the moving target and the latter is used to independently enhance the likelihood of tracking a particular color of the object. Particle filters are more efficient than any other tracking algorithms because the tracking mechanism follows Bayesian inference rule of conditional probability propagation. In the experimental results, it is demonstrated that the suggested contour tracking particle filters prove to be robust in the cluttered environment of robot vision.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.256-263
• /
• 2002

In this study, the tracking of the temporal variation of the frequency and the amplitude in the presence of additive white Gaussian noise is considered using the Extended Kalman filter (EKF. The EKF has many applications and it has been applied to the problem of tracking the time-variable frequency. However the existing EKF frequency trackers could was driven in the small time-variable amplitude or required the additional amplitude tracker in the large time-variable amplitude. In this study, the EKF frequency-amplitude tracker, which could track both frequency and amplitude simultaneously from the measured signal in the relatively large time-variable amplitude environment, is proposed for improving the performance of the time-variable frequency tracking and its performance is verified by the simulation and the experimental work.

• Journal of KIISE:Software and Applications
• /
• v.29 no.5
• /
• pp.319-325
• /
• 2002

Tracking moving objects is one of the most important techniques in motion analysis and understanding, and it has many difficult problems to solve. Especially, estimating and identifying moving objects, when the background and moving objects vary dynamically, are very difficult. It is possible under such a complex environment that targets may disappear totally or partially due to occlusion by other objects. The Kalman filter has been used to estimate motion information and use the information in predicting the appearance of targets in succeeding frames. In this paper, we propose another version of the Kalman filter, to be called structured Kalman filter, which can successfully work its role of estimating motion information under a deteriorating condition such as occlusion. Experimental results show that the suggested approach is very effective in estimating and tracking non-rigid moving objects reliably.